system

Abstract

Provide a system. A data acquisition means; A means of text analysis and automatic tagging of acquired data, A means of organizing the acquired data in terms of elimination, combination, exchange, and simplification; A method for evaluating the usability, frequency, substitutability, versatility, and impact of data and generating a data value score; A means for diagnosing the confidentiality of data and setting an appropriate security level; A means for generating and providing the organized data and its evaluation results as a report; A means of providing this data and reports to users and providing an interface for accepting user instructions. A system including:

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 modern companies, the amount of data generated is exploding. However, there is a lack of ways to utilize that data efficiently and effectively, and the shortage of data scientists and other specialized personnel is a particularly serious problem. Furthermore, as the amount of stored data increases, costs also increase, making appropriate data management and security an issue. There is a need for ways to solve these problems and maximize the value of the data held by companies. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a system that utilizes AI technology to acquire data, analyze text and automatically tag it, eliminate, combine, exchange, simplify, and organize data, evaluate data value, diagnose and set security levels, generate and provide reports, and provide interfaces. Specifically, the system efficiently organizes data, provides data according to specific company needs, quantifies the value of the data, and manages it at an appropriate security level, thereby improving data management efficiency and reducing costs.

[0006] A "means for acquiring data" is a device or program that has the functionality to collect and import data from various data sources.

[0007] The "means for analyzing text and automatically tagging" is a device or program that has the function of analyzing the text information of acquired data and automatically assigning related tags.

[0008] "Means for organizing in terms of excluding, combining, exchanging, and simplifying" refers to devices or programs that have the function of classifying, integrating, converting, and simplifying data efficiently and according to purpose.

[0009] A "means for generating a data value score" is a device or program that has the function of evaluating the usability, frequency, substitutability, versatility, and impact of data and calculating a score as a number.

[0010] The "means for setting a security level" refers to a device or program that has the function of diagnosing the confidentiality of data and determining and setting an appropriate security level.

[0011] The "means for generating and providing a report" refers to a device or program that has the function of compiling the organized data and its evaluation results in a report format and providing it to the user.

[0012] "Means for providing an interface for accepting user instructions" refers to a device or program that has the function of providing an operation screen for users to check the details of data and input additional organization and evaluation instructions.

[0013] "Means for analyzing text using natural language processing and performing automatic tagging" refers to a device or program that has the function of analyzing text data using natural language processing (NLP) technology and performing automatic tagging based on meaning, emotion, etc.

[0014] "Means for calculating a data value score for each data item, generating the evaluation results as a management report, and providing it to the user" refers to a device or program that has the function of calculating a data value score for each data item, generating a report summarizing the evaluation results, and providing it to the user. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention is a system for efficiently organizing and utilizing big data held by a company using AI technology. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0037] Server processing

[0038] 1. Importing data

[0039] The server collects data from various data sources within the enterprise, such as databases, file systems, cloud storage, or APIs. For example, the server collects data from the enterprise's CRM system, ERP system, and social media accounts and stores it in a database.

[0040] Examples:

[0041] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[0042] 2. Text analysis and automatic tagging

[0043] The server processes the collected data using text analysis technology, specifically natural language processing (NLP) algorithms, to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize.

[0044] Examples:

[0045] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[0046] 3. ECRS Data Collection

[0047] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining relevant data, the data set is effectively simplified.

[0048] Examples:

[0049] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[0050] 4. Assessing Data Value

[0051] The server evaluates the organized data based on its usability, frequency, substitutability, versatility, and impact, and generates a "data value score." This score is converted into a number and indicates the importance of the data.

[0052] Examples:

[0053] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[0054] 5. Setting the security level

[0055] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[0056] Examples:

[0057] The server is set to the highest security level for data including employees' personal information, and is only accessible to specific users.

[0058] 6. Generate Reports

[0059] The server then compiles a report summarizing the results of the process, including the organization of the data, its value score, and security settings.

[0060] Examples:

[0061] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[0062] Terminal and user processing

[0063] 1. Providing an interface

[0064] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[0065] Examples:

[0066] The device allows users to view data collation results and reports in real time through a web dashboard.

[0067] 2. User operations and instructions

[0068] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[0069] Examples:

[0070] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[0071] In this way, a system that provides a series of functions for efficiently organizing and effectively utilizing the big data held by companies will be realized, maximizing the value of data and helping to improve the efficiency and reduce costs of data management.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[0075] Step 2:

[0076] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[0077] Step 3:

[0078] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[0079] Step 4:

[0080] The server analyzes the stored data using natural language processing (NLP) technology, analyzing the meaning and sentiment of the text data and automatically tagging it.

[0081] Step 5:

[0082] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[0083] Step 6:

[0084] The server organizes the data, eliminating unnecessary data, combining related information, exchanging some information into other formats, and converting it into a simpler structure.

[0085] Step 7:

[0086] The server evaluates each data entry and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[0087] Step 8:

[0088] The server assigns an appropriate security level to each piece of data based on the evaluation results, and implements access control according to the assigned security level.

[0089] Step 9:

[0090] The server compiles the organized data and its evaluation results and generates a report that includes the data organization status, value score, security settings, and more.

[0091] Step 10:

[0092] The server provides the generated report to the user, for example by emailing it or uploading it to a dashboard.

[0093] Step 11:

[0094] The device provides an interface where users can view reports and data, with the ability to drill down into the data and utilize filters and search capabilities.

[0095] Step 12:

[0096] Users can search for data and check the evaluation results via their terminal, and if necessary, give instructions for additional operations or reorganization, enabling further utilization of the data.

[0097] Through these steps, corporate data can be efficiently organized, utilized to the fullest extent, and protected with appropriate security.

[0098] Example 1

[0099] 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."

[0100] Companies possess a large amount of big data, but they need methods to efficiently organize and utilize that data. In particular, they face challenges in integrating and analyzing data collected from a wide variety of sources, assessing its value, and managing it safely.

[0101] 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.

[0102] In this invention, the server includes means for acquiring information, means for analyzing the acquired information using natural language processing and automatically tagging it, means for organizing the acquired information from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the information and generating an information value score, means for assessing the confidentiality of the information and setting an appropriate security level, means for generating and providing a report of the organized information and its evaluation results, and means for providing this information and report to users and providing an interface for accepting user instructions.This makes it possible to efficiently organize big data held by companies, maximize its value, and utilize it safely and effectively.

[0103] "Information" refers to all data obtained from various data sources across the enterprise.

[0104] "Natural language processing" is a general term for techniques and algorithms that enable computers to understand, interpret, and generate human language.

[0105] "Auto-tagging" refers to the process of automatically analyzing the content of collected data and assigning relevant keywords and categories.

[0106] "Exclusion" refers to the act of removing unnecessary information from data.

[0107] "Combining" refers to the act of unifying and integrating different data sets or data items.

[0108] "Exchange" refers to the act of replacing part of a piece of data with other data.

[0109] "Simplification" refers to the act of removing unnecessary parts and simplifying the data structure in order to convert data into a more manageable form.

[0110] The "information value score" is an evaluation value calculated based on the usability, frequency, substitutability, versatility, and impact of information.

[0111] "Confidentiality" refers to the security property that prevents information from being accessed or disclosed unauthorizedly.

[0112] "Security level" is a standard that indicates the strength of security management, set according to the confidentiality and importance of data.

[0113] A "report" is a written or electronic file that compiles organized information and the results of its evaluation.

[0114] "Interface" refers to the user interface through which users access the system and perform operations and give instructions.

[0115] This invention is a system for efficiently organizing and effectively utilizing big data held by companies. The system is mainly composed of servers, terminals, and users, and by clearly defining the roles of each component, it achieves data acquisition, analysis, organization, evaluation, and utilization.

[0116] Server processing

[0117] 1. Importing data

[0118] The server collects data from various company data sources, utilizing databases, file systems, cloud storage, APIs, etc. For example, the server obtains data from the company's customer relationship management system (CRM) or enterprise resource planning system (ERP) and imports it into a local database (e.g., MySQL (registered trademark), PostgreSQL). It also collects feedback data from social media accounts via APIs and stores it in the same way.

[0119] Examples:

[0120] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[0121] 2. Text analysis and automatic tagging

[0122] The server analyzes the collected data using natural language processing (NLP) technology. Specifically, it uses generative AI models (e.g., GPT-3 (registered trademark), BERT) to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize the data.

[0123] Examples:

[0124] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[0125] 3. ECRS Data Collection

[0126] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining related data, the data set is effectively simplified. Also, by simplifying the structure, it becomes easier to access.

[0127] Examples:

[0128] The server removes duplicate customer information, consolidates purchase history data and feedback data, and removes unnecessary data fields to generate a simpler table.

[0129] 4. Assessing Data Value

[0130] The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact. This score is quantified and serves as an evaluation standard for the importance of the data.

[0131] Examples:

[0132] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[0133] 5. Setting the security level

[0134] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[0135] Examples:

[0136] The server is set to the highest security level for data including employees' personal information and is only accessible to specific users.

[0137] 6. Generate Reports

[0138] The server then compiles a report summarizing the results of the process, including information on how the data is organized, its value score, and security settings.

[0139] Examples:

[0140] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[0141] Terminal and user processing

[0142] 1. Providing an interface

[0143] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[0144] Examples:

[0145] The device allows users to view data collation results and reports in real time through a web dashboard.

[0146] 2. User operations and instructions

[0147] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[0148] Examples:

[0149] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[0150] Prompt Sentence Examples

[0151] Examples:

[0152] "Generate a report showing the results of an analysis of the company's customer data. Include, among other things, the percentage of positive and negative feedback, a rating score by product, and a data value score."

[0153] This system allows companies to efficiently organize their big data and maximize its value, while also improving the efficiency and reducing costs of data management.

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1: Collect data

[0156] More specifically: The server collects data from various data sources within the enterprise.

[0157] Inputs: Data sources such as CRM systems, ERP systems, social media accounts, etc.

[0158] Data processing / calculation: The server retrieves data from these data sources using APIs or SQL queries.

[0159] Output: Raw data collected in a local database

[0160] What it does: The server periodically sends API requests to retrieve the latest customer data and feedback data, and retrieves various data from the database using SQL queries and stores them in a local database.

[0161] Step 2: Extract text data

[0162] Specifically: The server extracts text data from the stored database.

[0163] Input: Raw data stored in a local database

[0164] Data processing / calculation: The server runs a SELECT query to extract the required text fields from the database.

[0165] Output: Extracted text data

[0166] Specific operation: The server uses a SELECT statement to retrieve the text field from the feedback table and build a dataset for analysis.

[0167] Step 3: Natural Language Processing and Auto-Tagging

[0168] Specific explanation: The server analyzes the extracted text data using natural language processing (NLP) technology and performs automatic tagging.

[0169] Input: Extracted text data

[0170] Data processing / calculation: Input text data into a generative AI model (e.g., GPT-3, BERT) to obtain analysis results. Based on the analysis results, relevant tags are added.

[0171] Output: A tagged dataset

[0172] Specific operation: The server inputs text data into the generative AI model and updates the tag information in the database based on the analysis results output by the model.

[0173] Step 4: ECRS Data Cleanup

[0174] Specifically: The server organizes the collected and analyzed data in terms of eliminating, combining, exchanging, and simplifying it.

[0175] Input: tagged dataset

[0176] Data processing / calculation: The server removes duplicate data, combines related data, and simplifies by eliminating unnecessary data.

[0177] Output: A cleaned dataset

[0178] Specific operation: The server deletes duplicate records in the database using a DELETE statement, joins the purchase history data and feedback data using a JOIN query, and removes unnecessary data fields to create a simple table.

[0179] Step 5: Assessing the value of your data

[0180] Specific explanation: The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact.

[0181] Input: A cleaned dataset

[0182] Data processing / calculation: Data is evaluated using a formula that calculates a score based on criteria such as usability and frequency, and a value score is generated.

[0183] Output: Data Value Score

[0184] Specific operation: The server executes the function based on the above criteria to calculate a score for each data value, and stores the calculated score in the database.

[0185] Step 6: Set the security level

[0186] Specifically: The server sets an appropriate security level based on the content and importance of the data.

[0187] Input: A curated dataset and its value scores

[0188] Data processing / calculation: Set access control on data based on sensitivity.

[0189] Output: A dataset with security levels set

[0190] What happens: The server uses NLP algorithms to analyze the data content, assigns security tags, and updates the ACL (Access Control List) to set the appropriate security level.

[0191] Step 7: Generate reports

[0192] Detailed explanation: The server summarizes the results of the above processing in a report.

[0193] Input: Dataset with security level

[0194] Data processing / calculation: Report generation algorithms are used to compile summaries of data organization, value scores, security settings, etc.

[0195] Output: Generated report

[0196] Specific operation: The server executes database queries to aggregate various data, generates reports in PDF or HTML format, and delivers the reports to the user via email.

[0197] This will enable companies to efficiently organize the big data they hold, maximizing its value, and utilizing it safely and effectively.

[0198] (Application example 1)

[0199] 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."

[0200] Currently, many companies possess vast amounts of data, but it is difficult to efficiently organize that data and extract valuable information. Logistics centers, in particular, require real-time, reliable information for inventory management and delivery planning. Furthermore, the lack of a system that can assess data value and generate appropriate reports while ensuring data confidentiality makes it difficult to simultaneously achieve both logistics efficiency and data security. Therefore, there is a need for a method to achieve efficient data management and value assessment in logistics centers.

[0201] 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.

[0202] In this invention, the server includes means for acquiring data, means for text analysis of the acquired data and automatic tagging, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for assessing the confidentiality of the data and setting an appropriate security level, means for generating and providing a report of the organized data and its evaluation results, means for providing this data and report to a user and providing an interface for accepting user instructions, means for collecting logistics management information and evaluating the utilization rate, sales volume, and supply risk of each item, and means for generating a report showing inventory status and delivery risk based on the evaluated information, thereby enabling efficient data management and value assessment at a logistics center.

[0203] "Data acquisition means" is a function for collecting necessary data from a specific data source.

[0204] "Text analysis means" refers to a technique for interpreting collected data using natural language processing technology and analyzing its meaning.

[0205] "Automatic tagging means" is a function that automatically assigns appropriate tags to analyzed data, making it easier to classify and search the data.

[0206] "Data reduction methods" are methods for optimizing collected data in terms of eliminating, combining, exchanging, and simplifying it.

[0207] "Data value assessment means" is a function for evaluating the usability, frequency, substitutability, versatility, and impact of data, and generating a data value score.

[0208] "Security setting means" is a means for diagnosing the confidentiality of data and setting an appropriate security level.

[0209] The "report generation means" is a function for creating a report based on the organized data and its evaluation results and providing it to the user.

[0210] The "interface providing means" refers to means including a screen and an input device for providing data and reports to a user and receiving instructions from the user.

[0211] The "logistics management information collection means" is a function for collecting information related to inventory and delivery at the logistics center.

[0212] The "utilization rate evaluation means" is a means for evaluating the utilization rate and inventory trends of each item.

[0213] The "sales number evaluation means" is a means for evaluating the sales number of each item and recording it as data.

[0214] The "supply risk assessment means" is a function for assessing potential risks in the supply of each item.

[0215] The "inventory status report generating means" is a function that generates a report showing the inventory status and delivery risk at the logistics center.

[0216] The system embodying the present invention provides functions for efficient data management and value assessment in a logistics center. Specific embodiments will be described below.

[0217] Server processing

[0218] 1. Data Collection Methods

[0219] The server retrieves data from the inventory management system at the logistics center using cloud storage, API interfaces (Flask, Django), etc. For example, product inventory status data is extracted from the inventory management system and stored in a database on the cloud.

[0220] 2. Text Analysis Methods

[0221] The server analyzes the collected data using natural language processing technology (NLTK, spaCy). This allows product descriptions and historical data to be interpreted. The analyzed data is automatically tagged with tags such as "low stock" or "high demand."

[0222] 3. Data organization methods

[0223] The server optimizes the collected data in terms of deduplication, data integration, data exchange, and data simplification. This allows for efficient management of ongoing order information and supply data. For example, information from different warehouses for the same product can be combined and managed as a single data set.

[0224] 4. Data Value Assessment Methods

[0225] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score. Scikit-learn is used for the evaluation, and product availability and supply risk are displayed numerically. For example, the server calculates a score for Product A, such as availability of 70%, sales volume of 500, and supply risk of 20%.

[0226] 5. Security Configuration Methods

[0227] The server assesses the confidentiality of the data and sets an appropriate security level using AWS (registered trademark) IAM or OAuth 2.0. For example, a high security level is set for personal customer data, allowing only specific users to access it.

[0228] 6. Report Generation Methods

[0229] The server creates reports based on the organized data and its evaluation results and provides them to users. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[0230] Terminal and user processing

[0231] 1. Means of providing interface

[0232] The terminal is implemented as a web or mobile application and provides an interface for users to view data and reports, for example, allowing users to check inventory status and evaluation results in real time through a web dashboard.

[0233] 2. User operations and instructions

[0234] Through the device, users can search, evaluate, and reorganize data, for example by filtering the availability of specific products or by requesting the import of new data.

[0235] Specific examples

[0236] For example, the system acquires inventory management data from a logistics center, evaluates the utilization rate, sales volume, and supply risk for each product, and generates a score based on the results. It also uses this data to create reports showing inventory status and delay risks.

[0237] Example prompts for generative AI models

[0238] Prompt: Obtain inventory management data for a distribution center, evaluate utilization rate, sales volume, and supply risk for each product, and generate a score based on that. Also, use that data to create a report showing stock status and risk of delays.

[0239] In this way, a system is provided that enables efficient data management and value assessment in a logistics center.

[0240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0241] Step 1: Collect data

[0242] The server retrieves data from the inventory management system of the logistics center. Specifically, it uses cloud storage and API interfaces (Flask, Django) to store information such as the inventory status, shipping history, and receiving history of each item in a cloud database.

[0243] Input: Data from inventory management system

[0244] Output: Inventory status, shipping history, and receiving history data stored in a cloud database

[0245] Step 2: Text analysis and auto-tagging

[0246] The server analyzes the collected data using natural language processing technology (NLTK, spaCy), which interprets the meaning of product descriptions and historical data and automatically assigns relevant tags.

[0247] Input: Data stored in a cloud database

[0248] Output: Analysis results and assigned tags (e.g., "Low stock" or "High demand")

[0249] Step 3: Data organization

[0250] The server optimizes the acquired data in terms of deduplication, data merging, data exchange, and data simplification. For example, data from different warehouses for the same product can be merged and compiled into a single data set.

[0251] Input: tagged data

[0252] Output: Optimized dataset

[0253] Step 4: Data Value Assessment

[0254] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score using Scikit-learn, which numerically displays the availability rate, sales volume, and supply risk of each item.

[0255] Input: Optimized dataset

[0256] Output: Data value score (e.g., availability 70%, sales volume 500, supply risk 20%)

[0257] Step 5: Security Settings

[0258] The server assesses the confidentiality of the data and sets an appropriate security level using AWS IAM and OAuth 2.0. For example, a high security level is set for data containing customer personal information, allowing only specific users to access it.

[0259] Input: Data Value Score

[0260] Output: A secured dataset

[0261] Step 6: Generate reports

[0262] The server creates reports based on the organized data and its evaluation results and provides them to the user. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[0263] Input: Secured dataset

[0264] Output: Generated report

[0265] Step 7: Providing an Interface

[0266] The device provides an interface for users to view data and reports through a web or mobile application, and allows users to search, evaluate, and reorganize the data through the interface.

[0267] Input: User instructions and operations

[0268] Output: Search results, evaluation results, reorganized data

[0269] In this way, by going through each step, efficient data management and value assessment can be achieved at the logistics center.

[0270] 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.

[0271] This invention is a system that uses AI technology to efficiently organize and utilize big data held by companies, and also incorporates an emotion engine that recognizes user emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0272] Server processing

[0273] 1. Importing data

[0274] The server accesses various data sources of the company and gathers data, retrieving it via databases, file systems, cloud storage, APIs, etc., and stores it in temporary storage.

[0275] Examples:

[0276] The server retrieves customer data from the company's CRM system and also retrieves feedback data from social media accounts via API.

[0277] 2. Text analysis and automatic tagging

[0278] The server analyzes the collected data using natural language processing (NLP) technology, and automatically assigns tags to the data based on the analysis results, making it easier to search and classify the data.

[0279] Examples:

[0280] The server analyzes the text data of customer feedback and assigns tags such as "positive," "negative," and "product name."

[0281] 3. ECRS Data Collection

[0282] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it: unnecessary data is removed, related information is combined, and some information is converted into other formats.

[0283] Examples:

[0284] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[0285] 4. Assessing Data Value

[0286] The server evaluates the organized data and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[0287] Examples:

[0288] The server calculates a score for product review data based on the number of monthly views and the level of detail in the reviews, and evaluates the value of each product.

[0289] 5. Setting the security level

[0290] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data.

[0291] Examples:

[0292] The server is set to the highest security level for data including employees' personal information, and only allows access by specific users.

[0293] 6. Generate Reports

[0294] The server then compiles a report summarizing the results of the process, including the data organization status, value score, and security settings.

[0295] Examples:

[0296] The server generates a report detailing the entire data, ECRS sorting results, data value score, and security level, and provides it to the user.

[0297] 7. Emotion Engine Processing

[0298] The server uses an emotion engine to analyze user input information, which analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate their emotional state.

[0299] Examples:

[0300] The system evaluates emotions from feedback information entered by the user and the tone of chat messages to determine the user's emotional state.

[0301] 8. Emotional Feedback

[0302] The server adjusts the way the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby providing information that best suits the user's current emotional state.

[0303] Examples:

[0304] If the user judges the feedback information to be positive, effective suggestions are displayed to the user in a positive tone.

[0305] Terminal and user processing

[0306] 1. Providing an interface

[0307] The device provides an interface that allows users to view data and reports, including the ability to view data details and use filters and search functions.

[0308] Examples:

[0309] The device allows users to view data compilation results and reports in real time through a web dashboard.

[0310] 2. User operations and instructions

[0311] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[0312] Examples:

[0313] From the web dashboard, users can apply specific filters, direct detailed data analysis, or request new data imports.

[0314] Through these steps, corporate data can be efficiently organized, utilized to the highest degree, and protected with appropriate security. Furthermore, the emotion engine presents data optimally according to the user's emotional state.

[0315] The processing flow will be explained below.

[0316] Step 1:

[0317] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[0318] Step 2:

[0319] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[0320] Step 3:

[0321] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[0322] Step 4:

[0323] The server analyzes the stored data using natural language processing (NLP) technology, specifically analyzing the text information within the data to extract meaning and sentiment.

[0324] Step 5:

[0325] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[0326] Step 6:

[0327] The server organizes the data in terms of ECRS (Eliminate, Combine, Exchange, Simplify), which eliminates redundancies in the dataset and integrates relevant information.

[0328] Step 7:

[0329] The server evaluates each data entry and calculates a data value score, based on criteria such as frequency of use and impact on profits.

[0330] Step 8:

[0331] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby realizing access control according to the confidentiality of the data.

[0332] Step 9:

[0333] The server generates a report based on the organized data and the evaluation results, including the data organization status, value score for each data entry, and security level.

[0334] Step 10:

[0335] The server provides the generated report to the user, either by emailing it or uploading it to a web dashboard.

[0336] Step 11:

[0337] The server analyzes the user's input information using an emotion engine, which evaluates the user's emotional state in real time.

[0338] Step 12:

[0339] The device will adjust how it displays data based on the user's emotional state: for example, if the user is feeling stressed, it will prioritize displaying concise, easy-to-understand information.

[0340] Step 13:

[0341] The terminal provides an interface for viewing data and reports, with filters and search capabilities to make it easier for users to find the information they need.

[0342] Step 14:

[0343] Users can search, evaluate, and reorganize data via their devices. Furthermore, they can refer to the results of the emotion engine to further utilize the data.

[0344] Through these steps, a company's big data can be efficiently organized and effectively utilized. Furthermore, the emotion engine analyzes the user's emotional state, enabling optimal information to be provided.

[0345] Example 2

[0346] 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."

[0347] Modern companies possess vast amounts of data, but they face challenges in efficiently organizing and utilizing this data. Furthermore, traditional data organization systems do not take into account the user's emotional state and lack means to optimize the user experience.

[0348] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0349] In this invention, the server includes: means for acquiring data; means for analyzing the acquired data using natural language processing and automatically tagging it; means for organizing the acquired data from the perspectives of elimination, combination, exchange, and simplification; means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score; means for assessing the confidentiality of the data and setting an appropriate security level; means for generating and providing the organized data and its evaluation results as a report; means for analyzing the acquired data and user-entered information using an emotion engine and evaluating the user's emotional state; means for adjusting the data display method based on the evaluated emotional state; and means for providing the data and report to the user and for providing an interface for accepting user instructions. This makes it possible to efficiently organize the vast amount of data held by a company and present optimal data according to the user's emotional state.

[0350] "Means of acquiring data" refers to the methods and technologies used to collect data from various data sources held by the company and store it in temporary storage.

[0351] "Natural language processing" refers to the techniques and methods that allow computers to understand, interpret, and generate human language.

[0352] "Text analysis" is the process of analyzing textual information using natural language processing technology and extracting meaning and structure from its content.

[0353] "Auto-tagging" is the process of automatically assigning relevant keywords and categories to data based on the results of text analysis.

[0354] "Means of organizing in terms of elimination, combination, exchange, and simplification" refers to techniques and methods for eliminating data duplication, combining related information, exchanging data formats as necessary, and simplifying and organizing data.

[0355] The "data value score" is a score calculated based on evaluation criteria such as the data's usability, frequency, substitutability, versatility, and impact.

[0356] "Means for diagnosing confidentiality and setting an appropriate security level" refers to techniques and methods for determining whether data contains confidential information and applying security measures as necessary.

[0357] The "means for generating and providing a report" refers to a technique and method for creating a report summarizing the organized data and its evaluation results and providing it to the user.

[0358] An "emotion engine" is a system and technology that analyzes a user's input information (key input, voice, facial expression, etc.) and evaluates their emotional state.

[0359] The "means for providing an interface" refers to the technology and method for providing a user interface that allows a user to view data and reports and to perform operations and give instructions.

[0360] This invention is a utilization system that uses AI technology to efficiently organize big data held by companies and incorporates an emotion engine that recognizes user emotions. This system is mainly composed of a server, a terminal, and a user. Detailed embodiments of the system are described below.

[0361] Server embodiment

[0362] 1. Importing data

[0363] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect data, which is then stored in temporary storage.

[0364] Example: A server makes an API call to retrieve customer data from a CRM system and temporarily stores that data.

[0365] 2. Text analysis and automatic tagging

[0366] The server uses natural language processing (NLP) technology to analyze the collected data and automatically assigns tags to the data based on the results. This is done using a Python NLP library (such as spaCy or nltk).

[0367] Example: The server analyzes the text of customer feedback and assigns tags such as "positive," "negative," and "product name."

[0368] 3. ECRS Data Collection

[0369] The server organizes the data using methods such as eliminating, combining, exchanging, and simplifying, using SQL queries and other database management tools.

[0370] Example: The server removes duplicate customer information and combines purchase history and feedback data.

[0371] 4. Assessing Data Value

[0372] The server calculates a value score for the organized data based on evaluation criteria, including usability, frequency, substitutability, versatility, and impact.

[0373] Example: The server calculates a score based on the number of monthly views and the detail of the reviews, and records this in a database.

[0374] 5. Setting the security level

[0375] The server assesses the sensitivity of the data and sets an appropriate security level using a data classification tool (e.g., Apache Ranger).

[0376] Example: The server is set to the highest security level for data including employee personal information, and only specific users can access it.

[0377] 6. Generate Reports

[0378] The server then compiles the organized data and evaluation results into a report that summarizes the results. This report is generated in PDF format and provided to the user.

[0379] Example: The server generates a PDF report containing a summary of the data, a value score, and a security level and sends it to the user's email address.

[0380] 7. Emotion Engine Processing

[0381] The server analyzes the user's input (keystrokes, voice, facial expressions, etc.) to assess their emotional state in real time, using the Google® Cloud Speech-to-Text API for voice input analysis.

[0382] Example: The server assesses the user's emotional state based on feedback information and the tone of their chat messages.

[0383] 8. Emotional Feedback

[0384] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, dynamically updating the interface using React.js.

[0385] Example: If a user judges the feedback information to be positive, provide them with effective suggestions in a positive tone.

[0386] Terminal embodiment

[0387] 1. Providing an interface

[0388] The terminal provides an interface where users can view data and reports, using a web dashboard powered by React.js.

[0389] Example: The device allows users to view data compilation results and reports in real time through a web dashboard.

[0390] 2. User operations and instructions

[0391] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[0392] Example: A user uses the filter feature in a web dashboard to select a specific data set and request detailed data analysis.

[0393] Example: Example of a prompt sentence to input to a generative AI model

[0394] 1. Prompt for further analysis of positive feedback

[0395] "Perform detailed analysis of positive customer feedback and generate reports with relevant product information."

[0396] 2. Prompt to import new data from a specific data source

[0397] "Import the latest customer feedback data from your social media accounts, then perform text analysis and tagging."

[0398] 3. Prompts that display recommendations based on the sentiment assessment results

[0399] "If the user's emotional state is positive, show them the latest product recommendations."

[0400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0401] Step 1: Import data

[0402] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect the required data. This processing step involves retrieving the data from the data sources and storing it in temporary storage.

[0403] Input: Acquiring target data through API calls or database queries

[0404] Data processing: Analyzes response data from APIs and query results, and converts formats

[0405] Output: The converted data is saved in temporary storage.

[0406] Specific operation: The server uses the API to access the CRM system, retrieve customer data, convert it to JSON format, and save it in storage.

[0407] Step 2: Text analysis and auto-tagging

[0408] The server analyzes the collected data using natural language processing (NLP) technology and automatically assigns tags to the data based on the analysis results. This process involves semantic analysis and tagging of text data.

[0409] Input: Text data stored in temporary storage

[0410] Data processing: Perform text and semantic analysis using NLP techniques (e.g., spaCy or nltk) to extract specific keywords and categories.

[0411] Output: Data tagged based on the analysis results

[0412] Specific operation: The server uses Python's nltk library to analyze the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[0413] Step 3: ECRS Data Cleanup

[0414] The server organizes the collected and tagged data in terms of elimination, combination, exchange, and simplification, a process that includes removing unnecessary data and converting data formats.

[0415] Input: tagged data

[0416] Data processing: Deleting duplicate data, merging related data, converting some data formats, deleting unnecessary data

[0417] Output: Organized and consolidated data

[0418] What happens: The server uses SQL queries to remove duplicate customer information and combines purchase history data with feedback data.

[0419] Step 4: Assessing the value of your data

[0420] The server evaluates the organized data and calculates a data value score. In this step, scoring is based on multiple evaluation criteria.

[0421] Input: Organized and consolidated data

[0422] Data processing: Calculate a score based on the evaluation criteria of usability, frequency, substitutability, versatility, and impact.

[0423] Output: Dataset with data value scores

[0424] Specific operation: The server uses an algorithm to calculate a score for product review data based on the number of monthly views and the detail level of the review, and records this in a database.

[0425] Step 5: Set the security level

[0426] The server assesses the confidentiality of the data and sets an appropriate security level, which ensures strict access control for important data.

[0427] Input: Organized and scored data

[0428] Data processing: Use data classification tools to identify sensitive information and set appropriate security levels

[0429] Output: A dataset with security levels set

[0430] Specific operation: The server uses Apache Ranger to set the highest security for data including employee personal information and control it so that only specific users can access it.

[0431] Step 6: Generate reports

[0432] The server creates a report based on the organized data and its evaluation results and provides it to the user. This process includes summarizing the results and creating a report.

[0433] Input: Organized and secured data

[0434] Data processing: Data summaries, value scores, and security levels are compiled and converted into report formats such as PDF.

[0435] Output: Report provided to the user

[0436] Specific operation: The server generates a PDF report detailing the entire data, ECRS sorting results, data value score, and security level, and sends it to the user's email address.

[0437] Step 7: Emotion Engine Processing

[0438] The server analyzes the user's input information (keystrokes, voice, facial expressions, etc.) and evaluates the user's emotional state in real time. An emotion analysis engine is used in this step.

[0439] Input: Real-time user input information (text, voice, facial expressions)

[0440] Data processing: Using emotion analysis technology, we evaluate the user's emotional state from input information.

[0441] Output: Evaluated user emotional state data

[0442] How it works: The server analyzes the voice data using the Google Cloud Speech-to-Text API and evaluates the user's emotions in real time.

[0443] Step 8: Emotional Feedback

[0444] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby improving the user experience.

[0445] Input: User's emotional state data as assessed by the emotion engine

[0446] Data manipulation: Adjusting interface content based on the user's emotional state

[0447] Output: The adapted interface presented to the user

[0448] How it works: The server dynamically updates the interface using React.js, displaying positive tone suggestions to users in a positive emotional state.

[0449] (Application example 2)

[0450] 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."

[0451] Conventional big data management systems focused on efficiently organizing and utilizing data, but it was difficult to understand user emotions and provide optimal suggestions and information based on those emotions. Furthermore, online shopping sites are seeking to improve the user experience, necessitating greater personalization. To address this, technology is needed that can analyze user emotions and use them to suggest products and provide services.

[0452] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data, means for text analysis and automatic tagging of the acquired data, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for diagnosing the confidentiality of the data and setting an appropriate security level, means for generating and providing the organized data and its evaluation results as a report, means for recognizing user emotions, means for adjusting the information display method and product proposals based on the user's emotional state, and means for providing this data and report to the user and providing an interface that accepts user instructions. This makes it possible to provide optimal product proposals and information based on the user's emotions.

[0453] A "data acquisition means" is a system or method for collecting and temporarily storing data from various data sources.

[0454] "Means for text analysis and automatic tagging" refers to a system or method that uses natural language processing technology to analyze acquired text data and automatically assign relevant tags.

[0455] "Means of organizing in terms of elimination, combination, replacement, and simplification" refers to a system or method that eliminates unnecessary parts of data, combines related information, and, if necessary, changes the format to make the whole easier to understand and simplify.

[0456] A "means for generating a data value score" is a system or method that evaluates the usability, frequency, substitutability, versatility, and impact of data, and assigns a score to the data based on these evaluation criteria.

[0457] A "means for diagnosing data confidentiality and setting an appropriate security level" is a system or method that performs a process of thoroughly evaluating the confidentiality of data and setting an appropriate security level based on the results.

[0458] The "means for generating and providing a report" refers to a system or method for generating a report summarizing the organized and evaluated data and providing it to a user.

[0459] "Means for recognizing user emotions" refers to a system or method for analyzing a user's emotional state through user input data or facial recognition.

[0460] "Means for adjusting information display methods and product recommendations based on the user's emotional state" refers to a system or method that changes the content and tone of displayed information, product recommendations, etc., depending on the user's recognized emotions.

[0461] A "means for providing an interface" is a system or method that provides a user interface for a user to view and provide instructions for data and reports.

[0462] MODE FOR CARRYING OUT THE INVENTION

[0463] This invention is a system that uses AI technology to efficiently organize and utilize big data and recognize user emotions. Below, we will explain how to specifically implement this system.

[0464] Server processing

[0465] 1. Importing data

[0466] The server accesses the company's data sources and retrieves data using means such as databases, file systems, cloud storage, and APIs, and stores it in temporary storage. For example, it retrieves customer data from a CRM system and feedback data from social media accounts via APIs.

[0467] 2. Text analysis and automatic tagging

[0468] The server analyzes the acquired data using natural language processing (NLP) technology and automatically assigns tags. For example, it analyzes customer feedback text and assigns tags such as "positive," "negative," and "product name."

[0469] 3. ECRS Data Collection

[0470] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it. It removes unnecessary data, combines related information, and converts some information into other formats. For example, it removes duplicate customer information and combines purchase history data and feedback data.

[0471] 4. Generating a Data Value Score

[0472] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the level of detail of the reviews, and the value of each product is assessed.

[0473] 5. Setting the security level

[0474] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data. For example, data containing personal information of employees is set to the highest security level, allowing only specific users to access it.

[0475] 6. Generate Reports

[0476] The server then compiles the results of the above process into a report, which includes the data organization status, value score, and security settings. For example, a report detailing the entire data, ECRS organization results, data value score, and security level can be generated and provided to the user.

[0477] 7. Emotion Engine Processing

[0478] The server uses an emotion engine to analyze user input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state.

[0479] 8. Emotional Feedback

[0480] The server adjusts the way data is displayed and product suggestions are made based on the user's emotional state as assessed by the emotion engine. For example, if a user's feedback information is judged to be positive, the server will display effective suggestions in a positive tone to the user.

[0481] Hardware and software used

[0482] Hardware:

[0483] Server: Data analysis and storage

[0484] Smartphone: User emotion analysis and interface provision

[0485] Camera: Emotion Analysis with Facial Recognition

[0486] software:

[0487] Natural Language Processing (NLP): Text analysis and tagging (e.g., Google Cloud Natural Language API)

[0488] Machine learning model: Emotion engine (e.g., OpenAI's GPT-3, Amazon Rekognition)

[0489] Database: Data integration and management (e.g., MySQL, PostgreSQL)

[0490] Specific examples

[0491] For example, if a user enters negative feedback such as "I don't know how to use this product," the emotion engine analyzes the content and recommends easy-to-understand how-to videos or FAQ sections. Also, if a user smiles through their smartphone camera, the emotion engine detects positive emotions and notifies the user of new products or exclusive coupons.

[0492] Example prompts to input to a generative AI model:

[0493] The user typed "I don't know how to use this product." The sentiment engine analyzed this feedback and determined the negative sentiment. Think about the best suggestion to make the user interested in reading more. Possible actions could be to provide a link to a how-to video or a guide to the FAQ section.

[0494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0495] Step 1:

[0496] Importing Data

[0497] The server accesses various data sources within the company to retrieve the required data. Specifically, data is retrieved via databases, file systems, cloud storage, APIs, etc., and then stored in temporary storage. For example, customer data may be retrieved from a company's CRM system, and feedback data may be retrieved from social media accounts via APIs. The input is the data source, and the output is the raw data stored in temporary storage.

[0498] Step 2:

[0499] Text analysis and auto-tagging

[0500] The server uses natural language processing (NLP) technology to perform text analysis on the data stored in temporary storage and automatically assign tags. For example, it analyzes customer feedback text and assigns tags such as positive, negative, and product names. The input is raw text data, and the output is the analyzed results and the associated tags. Specifically, it uses an NLP model (e.g., Google Cloud Natural Language API) to analyze the text and assign relevant tags.

[0501] Step 3:

[0502] ECRS data organization

[0503] The server organizes the analyzed data in terms of eliminating, combining, exchanging, and simplifying. It removes duplicate data, combines related information, and changes the data format as needed. For example, it removes duplicate customer information and combines purchase history data and feedback data. The input is tagged data, and the output is organized data. Specific operations include filtering and integrating data using database operations (e.g., MySQL).

[0504] Step 4:

[0505] Generating a Data Value Score

[0506] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the detail of the reviews, and the value of each product is evaluated. The input is the organized data, and the output is a data value score. Specifically, a numerical analysis algorithm is used to calculate a score based on each evaluation criterion.

[0507] Step 5:

[0508] Security Level Settings

[0509] The server assesses the confidentiality of the data and sets an appropriate security level. For example, it sets the highest security level for data containing personal employee information, allowing only specific users to access it. The input is the data value score and organized data, and the output is the set security level. Specifically, it sets appropriate access control using a security policy management system (e.g., AWS IAM).

[0510] Step 6:

[0511] Generate reports

[0512] The server compiles the results of the above processing into a report as a summary. The report includes the data organization status, value score, and security settings. For example, a report detailing the overall data, ECRS organization results, data value score, and security level is generated and provided to the user. The input is the result data generated at each stage of the processing, and the output is the completed report. Specifically, the data analysis results are compiled into a report format using document generation software (e.g., LaTeX, MICROSOFT(R) OFFICE(R)).

[0513] Step 7:

[0514] Emotion engine processing

[0515] The server uses an emotion engine to analyze the user's input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state. The input is the user's real-time data, and the output is the emotion analysis results. Specifically, emotion analysis is performed using a machine learning model (e.g., OpenAI GPT-3, Amazon Rekognition).

[0516] Step 8:

[0517] Emotion-based feedback

[0518] The server adjusts how data is displayed and how products are suggested based on the user's emotional state as assessed by the emotion engine. For example, if the user's emotion is judged to be positive, it displays effective product suggestions in a positive tone. The input is the emotion analysis results, and the output is tailored suggestions and information based on that emotion. Specific operations include dynamically changing content using a user interface system (e.g., web dashboard, mobile app).

[0519] This will enable optimal product suggestions and information provision based on the user's emotions.

[0520] 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.

[0521] 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.

[0522] 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.

[0523] [Second embodiment]

[0524] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0525] 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.

[0526] 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).

[0527] 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.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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."

[0536] This invention is a system for efficiently organizing and utilizing big data held by a company using AI technology. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0537] Server processing

[0538] 1. Importing data

[0539] The server collects data from various data sources within the enterprise, such as databases, file systems, cloud storage, or APIs. For example, the server collects data from the enterprise's CRM system, ERP system, and social media accounts and stores it in a database.

[0540] Examples:

[0541] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[0542] 2. Text analysis and automatic tagging

[0543] The server processes the collected data using text analysis technology, specifically natural language processing (NLP) algorithms, to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize.

[0544] Examples:

[0545] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[0546] 3. ECRS Data Collection

[0547] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining relevant data, the data set is effectively simplified.

[0548] Examples:

[0549] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[0550] 4. Assessing Data Value

[0551] The server evaluates the organized data based on its usability, frequency, substitutability, versatility, and impact, and generates a "data value score." This score is converted into a number and indicates the importance of the data.

[0552] Examples:

[0553] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[0554] 5. Setting the security level

[0555] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[0556] Examples:

[0557] The server is set to the highest security level for data including employees' personal information, and is only accessible to specific users.

[0558] 6. Generate Reports

[0559] The server then compiles a report summarizing the results of the process, including the organization of the data, its value score, and security settings.

[0560] Examples:

[0561] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[0562] Terminal and user processing

[0563] 1. Providing an interface

[0564] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[0565] Examples:

[0566] The device allows users to view data collation results and reports in real time through a web dashboard.

[0567] 2. User operations and instructions

[0568] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[0569] Examples:

[0570] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[0571] In this way, a system that provides a series of functions for efficiently organizing and effectively utilizing the big data held by companies will be realized, maximizing the value of data and helping to improve the efficiency and reduce costs of data management.

[0572] The processing flow will be explained below.

[0573] Step 1:

[0574] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[0575] Step 2:

[0576] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[0577] Step 3:

[0578] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[0579] Step 4:

[0580] The server analyzes the stored data using natural language processing (NLP) technology, analyzing the meaning and sentiment of the text data and automatically tagging it.

[0581] Step 5:

[0582] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[0583] Step 6:

[0584] The server organizes the data, eliminating unnecessary data, combining related information, exchanging some information into other formats, and converting it into a simpler structure.

[0585] Step 7:

[0586] The server evaluates each data entry and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[0587] Step 8:

[0588] The server assigns an appropriate security level to each piece of data based on the evaluation results, and implements access control according to the assigned security level.

[0589] Step 9:

[0590] The server compiles the organized data and its evaluation results and generates a report that includes the data organization status, value score, security settings, and more.

[0591] Step 10:

[0592] The server provides the generated report to the user, for example by emailing it or uploading it to a dashboard.

[0593] Step 11:

[0594] The device provides an interface where users can view reports and data, with the ability to drill down into the data and utilize filters and search capabilities.

[0595] Step 12:

[0596] Users can search for data and check the evaluation results via their terminal, and if necessary, give instructions for additional operations or reorganization, enabling further utilization of the data.

[0597] Through these steps, corporate data can be efficiently organized, utilized to the fullest extent, and protected with appropriate security.

[0598] Example 1

[0599] 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."

[0600] Companies possess a large amount of big data, but they need methods to efficiently organize and utilize that data. In particular, they face challenges in integrating and analyzing data collected from a wide variety of sources, assessing its value, and managing it safely.

[0601] 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.

[0602] In this invention, the server includes means for acquiring information, means for analyzing the acquired information using natural language processing and automatically tagging it, means for organizing the acquired information from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the information and generating an information value score, means for assessing the confidentiality of the information and setting an appropriate security level, means for generating and providing a report of the organized information and its evaluation results, and means for providing this information and report to users and providing an interface for accepting user instructions.This makes it possible to efficiently organize big data held by companies, maximize its value, and utilize it safely and effectively.

[0603] "Information" refers to all data obtained from various data sources across the enterprise.

[0604] "Natural language processing" is a general term for techniques and algorithms that enable computers to understand, interpret, and generate human language.

[0605] "Auto-tagging" refers to the process of automatically analyzing the content of collected data and assigning relevant keywords and categories.

[0606] "Exclusion" refers to the act of removing unnecessary information from data.

[0607] "Combining" refers to the act of unifying and integrating different data sets or data items.

[0608] "Exchange" refers to the act of replacing part of a piece of data with other data.

[0609] "Simplification" refers to the act of removing unnecessary parts and simplifying the data structure in order to convert data into a more manageable form.

[0610] The "information value score" is an evaluation value calculated based on the usability, frequency, substitutability, versatility, and impact of information.

[0611] "Confidentiality" refers to the security property that prevents information from being accessed or disclosed unauthorizedly.

[0612] "Security level" is a standard that indicates the strength of security management, set according to the confidentiality and importance of data.

[0613] A "report" is a written or electronic file that compiles organized information and the results of its evaluation.

[0614] "Interface" refers to the user interface through which users access the system and perform operations and give instructions.

[0615] This invention is a system for efficiently organizing and effectively utilizing big data held by companies. The system is mainly composed of servers, terminals, and users, and by clearly defining the roles of each component, it achieves data acquisition, analysis, organization, evaluation, and utilization.

[0616] Server processing

[0617] 1. Importing data

[0618] The server collects data from various company data sources, utilizing databases, file systems, cloud storage, APIs, etc. For example, the server retrieves data from the company's customer relationship management system (CRM) and enterprise resource planning system (ERP) and imports it into a local database (e.g., MySQL, PostgreSQL). It also collects feedback data from social media accounts via APIs and stores it in the same way.

[0619] Examples:

[0620] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[0621] 2. Text analysis and automatic tagging

[0622] The server analyzes the collected data using natural language processing (NLP) techniques. Specifically, it uses generative AI models (e.g., GPT-3, BERT) to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize the data.

[0623] Examples:

[0624] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[0625] 3. ECRS Data Collection

[0626] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining related data, the data set is effectively simplified. Also, by simplifying the structure, it becomes easier to access.

[0627] Examples:

[0628] The server removes duplicate customer information, consolidates purchase history data and feedback data, and removes unnecessary data fields to generate a simpler table.

[0629] 4. Assessing Data Value

[0630] The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact. This score is quantified and serves as an evaluation standard for the importance of the data.

[0631] Examples:

[0632] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[0633] 5. Setting the security level

[0634] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[0635] Examples:

[0636] The server is set to the highest security level for data including employees' personal information and is only accessible to specific users.

[0637] 6. Generate Reports

[0638] The server then compiles a report summarizing the results of the process, including information on how the data is organized, its value score, and security settings.

[0639] Examples:

[0640] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[0641] Terminal and user processing

[0642] 1. Providing an interface

[0643] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[0644] Examples:

[0645] The device allows users to view data collation results and reports in real time through a web dashboard.

[0646] 2. User operations and instructions

[0647] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[0648] Examples:

[0649] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[0650] Prompt Sentence Examples

[0651] Examples:

[0652] "Generate a report showing the results of an analysis of the company's customer data. Include, among other things, the percentage of positive and negative feedback, a rating score by product, and a data value score."

[0653] This system allows companies to efficiently organize their big data and maximize its value, while also improving the efficiency and reducing costs of data management.

[0654] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0655] Step 1: Collect data

[0656] More specifically: The server collects data from various data sources within the enterprise.

[0657] Inputs: Data sources such as CRM systems, ERP systems, social media accounts, etc.

[0658] Data processing / calculation: The server retrieves data from these data sources using APIs or SQL queries.

[0659] Output: Raw data collected in a local database

[0660] What it does: The server periodically sends API requests to retrieve the latest customer data and feedback data, and retrieves various data from the database using SQL queries and stores them in a local database.

[0661] Step 2: Extract text data

[0662] Specifically: The server extracts text data from the stored database.

[0663] Input: Raw data stored in a local database

[0664] Data processing / calculation: The server runs a SELECT query to extract the required text fields from the database.

[0665] Output: Extracted text data

[0666] Specific operation: The server uses a SELECT statement to retrieve the text field from the feedback table and build a dataset for analysis.

[0667] Step 3: Natural Language Processing and Auto-Tagging

[0668] Specific explanation: The server analyzes the extracted text data using natural language processing (NLP) technology and performs automatic tagging.

[0669] Input: Extracted text data

[0670] Data processing / calculation: Input text data into a generative AI model (e.g., GPT-3, BERT) to obtain analysis results. Based on the analysis results, relevant tags are added.

[0671] Output: A tagged dataset

[0672] Specific operation: The server inputs text data into the generative AI model and updates the tag information in the database based on the analysis results output by the model.

[0673] Step 4: ECRS Data Cleanup

[0674] Specifically: The server organizes the collected and analyzed data in terms of eliminating, combining, exchanging, and simplifying it.

[0675] Input: tagged dataset

[0676] Data processing / calculation: The server removes duplicate data, combines related data, and simplifies by eliminating unnecessary data.

[0677] Output: A cleaned dataset

[0678] Specific operation: The server deletes duplicate records in the database using a DELETE statement, joins the purchase history data and feedback data using a JOIN query, and removes unnecessary data fields to create a simple table.

[0679] Step 5: Assessing the value of your data

[0680] Specific explanation: The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact.

[0681] Input: A cleaned dataset

[0682] Data processing / calculation: Data is evaluated using a formula that calculates a score based on criteria such as usability and frequency, and a value score is generated.

[0683] Output: Data Value Score

[0684] Specific operation: The server executes the function based on the above criteria to calculate a score for each data value, and stores the calculated score in the database.

[0685] Step 6: Set the security level

[0686] Specifically: The server sets an appropriate security level based on the content and importance of the data.

[0687] Input: A curated dataset and its value scores

[0688] Data processing / calculation: Set access control on data based on sensitivity.

[0689] Output: A dataset with security levels set

[0690] What happens: The server uses NLP algorithms to analyze the data content, assigns security tags, and updates the ACL (Access Control List) to set the appropriate security level.

[0691] Step 7: Generate reports

[0692] Detailed explanation: The server summarizes the results of the above processing in a report.

[0693] Input: Dataset with security level

[0694] Data processing / calculation: Report generation algorithms are used to compile summaries of data organization, value scores, security settings, etc.

[0695] Output: Generated report

[0696] Specific operation: The server executes database queries to aggregate various data, generates reports in PDF or HTML format, and delivers the reports to the user via email.

[0697] This will enable companies to efficiently organize the big data they hold, maximizing its value, and utilizing it safely and effectively.

[0698] (Application example 1)

[0699] 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."

[0700] Currently, many companies possess vast amounts of data, but it is difficult to efficiently organize that data and extract valuable information. Logistics centers, in particular, require real-time, reliable information for inventory management and delivery planning. Furthermore, the lack of a system that can assess data value and generate appropriate reports while ensuring data confidentiality makes it difficult to simultaneously achieve both logistics efficiency and data security. Therefore, there is a need for a method to achieve efficient data management and value assessment in logistics centers.

[0701] 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.

[0702] In this invention, the server includes means for acquiring data, means for text analysis of the acquired data and automatic tagging, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for assessing the confidentiality of the data and setting an appropriate security level, means for generating and providing a report of the organized data and its evaluation results, means for providing this data and report to a user and providing an interface for accepting user instructions, means for collecting logistics management information and evaluating the utilization rate, sales volume, and supply risk of each item, and means for generating a report showing inventory status and delivery risk based on the evaluated information, thereby enabling efficient data management and value assessment at a logistics center.

[0703] "Data acquisition means" is a function for collecting necessary data from a specific data source.

[0704] "Text analysis means" refers to a technique for interpreting collected data using natural language processing technology and analyzing its meaning.

[0705] "Automatic tagging means" is a function that automatically assigns appropriate tags to analyzed data, making it easier to classify and search the data.

[0706] "Data reduction methods" are methods for optimizing collected data in terms of eliminating, combining, exchanging, and simplifying it.

[0707] "Data value assessment means" is a function for evaluating the usability, frequency, substitutability, versatility, and impact of data, and generating a data value score.

[0708] "Security setting means" is a means for diagnosing the confidentiality of data and setting an appropriate security level.

[0709] The "report generation means" is a function for creating a report based on the organized data and its evaluation results and providing it to the user.

[0710] The "interface providing means" refers to means including a screen and an input device for providing data and reports to a user and receiving instructions from the user.

[0711] The "logistics management information collection means" is a function for collecting information related to inventory and delivery at the logistics center.

[0712] The "utilization rate evaluation means" is a means for evaluating the utilization rate and inventory trends of each item.

[0713] The "sales number evaluation means" is a means for evaluating the sales number of each item and recording it as data.

[0714] The "supply risk assessment means" is a function for assessing potential risks in the supply of each item.

[0715] The "inventory status report generating means" is a function that generates a report showing the inventory status and delivery risk at the logistics center.

[0716] The system embodying the present invention provides functions for efficient data management and value assessment in a logistics center. Specific embodiments will be described below.

[0717] Server processing

[0718] 1. Data Collection Methods

[0719] The server retrieves data from the inventory management system at the logistics center using cloud storage, API interfaces (Flask, Django), etc. For example, product inventory status data is extracted from the inventory management system and stored in a database on the cloud.

[0720] 2. Text Analysis Methods

[0721] The server analyzes the collected data using natural language processing technology (NLTK, spaCy). This allows product descriptions and historical data to be interpreted. The analyzed data is automatically tagged with tags such as "low stock" or "high demand."

[0722] 3. Data organization methods

[0723] The server optimizes the collected data in terms of deduplication, data integration, data exchange, and data simplification. This allows for efficient management of ongoing order information and supply data. For example, information from different warehouses for the same product can be combined and managed as a single data set.

[0724] 4. Data Value Assessment Methods

[0725] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score. Scikit-learn is used for the evaluation, and product availability and supply risk are displayed numerically. For example, the server calculates a score for Product A, such as availability of 70%, sales volume of 500, and supply risk of 20%.

[0726] 5. Security Configuration Methods

[0727] The server assesses the confidentiality of the data and sets an appropriate security level using AWS IAM and OAuth 2.0. For example, a high security level is set for personal customer data, allowing only specific users to access it.

[0728] 6. Report Generation Methods

[0729] The server creates reports based on the organized data and its evaluation results and provides them to users. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[0730] Terminal and user processing

[0731] 1. Means of providing interface

[0732] The terminal is implemented as a web or mobile application and provides an interface for users to view data and reports, for example, allowing users to check inventory status and evaluation results in real time through a web dashboard.

[0733] 2. User operations and instructions

[0734] Through the device, users can search, evaluate, and reorganize data, for example by filtering the availability of specific products or by requesting the import of new data.

[0735] Specific examples

[0736] For example, the system acquires inventory management data from a logistics center, evaluates the utilization rate, sales volume, and supply risk for each product, and generates a score based on the results. It also uses this data to create reports showing inventory status and delay risks.

[0737] Example prompts for generative AI models

[0738] Prompt: Obtain inventory management data for a distribution center, evaluate utilization rate, sales volume, and supply risk for each product, and generate a score based on that. Also, use that data to create a report showing stock status and risk of delays.

[0739] In this way, a system is provided that enables efficient data management and value assessment in a logistics center.

[0740] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0741] Step 1: Collect data

[0742] The server retrieves data from the inventory management system of the logistics center. Specifically, it uses cloud storage and API interfaces (Flask, Django) to store information such as the inventory status, shipping history, and receiving history of each item in a cloud database.

[0743] Input: Data from inventory management system

[0744] Output: Inventory status, shipping history, and receiving history data stored in a cloud database

[0745] Step 2: Text analysis and auto-tagging

[0746] The server analyzes the collected data using natural language processing technology (NLTK, spaCy), which interprets the meaning of product descriptions and historical data and automatically assigns relevant tags.

[0747] Input: Data stored in a cloud database

[0748] Output: Analysis results and assigned tags (e.g., "Low stock" or "High demand")

[0749] Step 3: Data organization

[0750] The server optimizes the acquired data in terms of deduplication, data merging, data exchange, and data simplification. For example, data from different warehouses for the same product can be merged and compiled into a single data set.

[0751] Input: tagged data

[0752] Output: Optimized dataset

[0753] Step 4: Data Value Assessment

[0754] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score using Scikit-learn, which numerically displays the availability rate, sales volume, and supply risk of each item.

[0755] Input: Optimized dataset

[0756] Output: Data value score (e.g., availability 70%, sales volume 500, supply risk 20%)

[0757] Step 5: Security Settings

[0758] The server assesses the confidentiality of the data and sets an appropriate security level using AWS IAM and OAuth 2.0. For example, a high security level is set for data containing customer personal information, allowing only specific users to access it.

[0759] Input: Data Value Score

[0760] Output: A secured dataset

[0761] Step 6: Generate reports

[0762] The server creates reports based on the organized data and its evaluation results and provides them to the user. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[0763] Input: Secured dataset

[0764] Output: Generated report

[0765] Step 7: Providing an Interface

[0766] The device provides an interface for users to view data and reports through a web or mobile application, and allows users to search, evaluate, and reorganize the data through the interface.

[0767] Input: User instructions and operations

[0768] Output: Search results, evaluation results, reorganized data

[0769] In this way, by going through each step, efficient data management and value assessment can be achieved at the logistics center.

[0770] 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.

[0771] This invention is a system that uses AI technology to efficiently organize and utilize big data held by companies, and also incorporates an emotion engine that recognizes user emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[0772] Server processing

[0773] 1. Importing data

[0774] The server accesses various data sources of the company and gathers data, retrieving it via databases, file systems, cloud storage, APIs, etc., and stores it in temporary storage.

[0775] Examples:

[0776] The server retrieves customer data from the company's CRM system and also retrieves feedback data from social media accounts via API.

[0777] 2. Text analysis and automatic tagging

[0778] The server analyzes the collected data using natural language processing (NLP) technology, and automatically assigns tags to the data based on the analysis results, making it easier to search and classify the data.

[0779] Examples:

[0780] The server analyzes the text data of customer feedback and assigns tags such as "positive," "negative," and "product name."

[0781] 3. ECRS Data Collection

[0782] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it: unnecessary data is removed, related information is combined, and some information is converted into other formats.

[0783] Examples:

[0784] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[0785] 4. Assessing Data Value

[0786] The server evaluates the organized data and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[0787] Examples:

[0788] The server calculates a score for product review data based on the number of monthly views and the level of detail in the reviews, and evaluates the value of each product.

[0789] 5. Setting the security level

[0790] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data.

[0791] Examples:

[0792] The server is set to the highest security level for data including employees' personal information, and only allows access by specific users.

[0793] 6. Generate Reports

[0794] The server then compiles a report summarizing the results of the process, including the data organization status, value score, and security settings.

[0795] Examples:

[0796] The server generates a report detailing the entire data, ECRS sorting results, data value score, and security level, and provides it to the user.

[0797] 7. Emotion Engine Processing

[0798] The server uses an emotion engine to analyze user input information, which analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate their emotional state.

[0799] Examples:

[0800] The system evaluates emotions from feedback information entered by the user and the tone of chat messages to determine the user's emotional state.

[0801] 8. Emotional Feedback

[0802] The server adjusts the way the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby providing information that best suits the user's current emotional state.

[0803] Examples:

[0804] If the user judges the feedback information to be positive, effective suggestions are displayed to the user in a positive tone.

[0805] Terminal and user processing

[0806] 1. Providing an interface

[0807] The device provides an interface that allows users to view data and reports, including the ability to view data details and use filters and search functions.

[0808] Examples:

[0809] The device allows users to view data compilation results and reports in real time through a web dashboard.

[0810] 2. User operations and instructions

[0811] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[0812] Examples:

[0813] From the web dashboard, users can apply specific filters, direct detailed data analysis, or request new data imports.

[0814] Through these steps, corporate data can be efficiently organized, utilized to the highest degree, and protected with appropriate security. Furthermore, the emotion engine presents data optimally according to the user's emotional state.

[0815] The processing flow will be explained below.

[0816] Step 1:

[0817] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[0818] Step 2:

[0819] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[0820] Step 3:

[0821] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[0822] Step 4:

[0823] The server analyzes the stored data using natural language processing (NLP) technology, specifically analyzing the text information within the data to extract meaning and sentiment.

[0824] Step 5:

[0825] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[0826] Step 6:

[0827] The server organizes the data in terms of ECRS (Eliminate, Combine, Exchange, Simplify), which eliminates redundancies in the dataset and integrates relevant information.

[0828] Step 7:

[0829] The server evaluates each data entry and calculates a data value score, based on criteria such as frequency of use and impact on profits.

[0830] Step 8:

[0831] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby realizing access control according to the confidentiality of the data.

[0832] Step 9:

[0833] The server generates a report based on the organized data and the evaluation results, including the data organization status, value score for each data entry, and security level.

[0834] Step 10:

[0835] The server provides the generated report to the user, either by emailing it or uploading it to a web dashboard.

[0836] Step 11:

[0837] The server analyzes the user's input information using an emotion engine, which evaluates the user's emotional state in real time.

[0838] Step 12:

[0839] The device will adjust how it displays data based on the user's emotional state: for example, if the user is feeling stressed, it will prioritize displaying concise, easy-to-understand information.

[0840] Step 13:

[0841] The terminal provides an interface for viewing data and reports, with filters and search capabilities to make it easier for users to find the information they need.

[0842] Step 14:

[0843] Users can search, evaluate, and reorganize data via their devices. Furthermore, they can refer to the results of the emotion engine to further utilize the data.

[0844] Through these steps, a company's big data can be efficiently organized and effectively utilized. Furthermore, the emotion engine analyzes the user's emotional state, enabling optimal information to be provided.

[0845] Example 2

[0846] 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."

[0847] Modern companies possess vast amounts of data, but they face challenges in efficiently organizing and utilizing this data. Furthermore, traditional data organization systems do not take into account the user's emotional state and lack means to optimize the user experience.

[0848] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0849] In this invention, the server includes: means for acquiring data; means for analyzing the acquired data using natural language processing and automatically tagging it; means for organizing the acquired data from the perspectives of elimination, combination, exchange, and simplification; means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score; means for assessing the confidentiality of the data and setting an appropriate security level; means for generating and providing the organized data and its evaluation results as a report; means for analyzing the acquired data and user-entered information using an emotion engine and evaluating the user's emotional state; means for adjusting the data display method based on the evaluated emotional state; and means for providing the data and report to the user and for providing an interface for accepting user instructions. This makes it possible to efficiently organize the vast amount of data held by a company and present optimal data according to the user's emotional state.

[0850] "Means of acquiring data" refers to the methods and technologies used to collect data from various data sources held by the company and store it in temporary storage.

[0851] "Natural language processing" refers to the techniques and methods that allow computers to understand, interpret, and generate human language.

[0852] "Text analysis" is the process of analyzing textual information using natural language processing technology and extracting meaning and structure from its content.

[0853] "Auto-tagging" is the process of automatically assigning relevant keywords and categories to data based on the results of text analysis.

[0854] "Means of organizing in terms of elimination, combination, exchange, and simplification" refers to techniques and methods for eliminating data duplication, combining related information, exchanging data formats as necessary, and simplifying and organizing data.

[0855] The "data value score" is a score calculated based on evaluation criteria such as the data's usability, frequency, substitutability, versatility, and impact.

[0856] "Means for diagnosing confidentiality and setting an appropriate security level" refers to techniques and methods for determining whether data contains confidential information and applying security measures as necessary.

[0857] The "means for generating and providing a report" refers to a technique and method for creating a report summarizing the organized data and its evaluation results and providing it to the user.

[0858] An "emotion engine" is a system and technology that analyzes a user's input information (key input, voice, facial expression, etc.) and evaluates their emotional state.

[0859] The "means for providing an interface" refers to the technology and method for providing a user interface that allows a user to view data and reports and to perform operations and give instructions.

[0860] This invention is a utilization system that uses AI technology to efficiently organize big data held by companies and incorporates an emotion engine that recognizes user emotions. This system is mainly composed of a server, a terminal, and a user. Detailed embodiments of the system are described below.

[0861] Server embodiment

[0862] 1. Importing data

[0863] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect data, which is then stored in temporary storage.

[0864] Example: A server makes an API call to retrieve customer data from a CRM system and temporarily stores that data.

[0865] 2. Text analysis and automatic tagging

[0866] The server uses natural language processing (NLP) technology to analyze the collected data and automatically assigns tags to the data based on the results. This is done using a Python NLP library (such as spaCy or nltk).

[0867] Example: The server analyzes the text of customer feedback and assigns tags such as "positive," "negative," and "product name."

[0868] 3. ECRS Data Collection

[0869] The server organizes the data using methods such as eliminating, combining, exchanging, and simplifying, using SQL queries and other database management tools.

[0870] Example: The server removes duplicate customer information and combines purchase history and feedback data.

[0871] 4. Assessing Data Value

[0872] The server calculates a value score for the organized data based on evaluation criteria, including usability, frequency, substitutability, versatility, and impact.

[0873] Example: The server calculates a score based on the number of monthly views and the detail of the reviews, and records this in a database.

[0874] 5. Setting the security level

[0875] The server assesses the sensitivity of the data and sets an appropriate security level using data classification tools (e.g., Apache Ranger).

[0876] Example: The server is set to the highest security level for data including employee personal information, and only specific users can access it.

[0877] 6. Generate Reports

[0878] The server then compiles the organized data and evaluation results into a report that summarizes the results. This report is generated in PDF format and provided to the user.

[0879] Example: The server generates a PDF report containing a summary of the data, a value score, and a security level and sends it to the user's email address.

[0880] 7. Emotion Engine Processing

[0881] The server analyzes the user's input (keystrokes, voice, facial expressions, etc.) to assess their emotional state in real time, using the Google Cloud Speech-to-Text API for voice input analysis.

[0882] Example: The server assesses the user's emotional state based on feedback information and the tone of their chat messages.

[0883] 8. Emotional Feedback

[0884] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, dynamically updating the interface using React.js.

[0885] Example: If a user judges the feedback information to be positive, provide them with effective suggestions in a positive tone.

[0886] Terminal embodiment

[0887] 1. Providing an interface

[0888] The terminal provides an interface where users can view data and reports, using a web dashboard powered by React.js.

[0889] Example: The device allows users to view data compilation results and reports in real time through a web dashboard.

[0890] 2. User operations and instructions

[0891] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[0892] Example: A user uses the filter feature in a web dashboard to select a specific data set and request detailed data analysis.

[0893] Example: Example of a prompt sentence to input to a generative AI model

[0894] 1. Prompt for further analysis of positive feedback

[0895] "Perform detailed analysis of positive customer feedback and generate reports with relevant product information."

[0896] 2. Prompt to import new data from a specific data source

[0897] "Import the latest customer feedback data from your social media accounts, then perform text analysis and tagging."

[0898] 3. Prompts that display recommendations based on the sentiment assessment results

[0899] "If the user's emotional state is positive, show them the latest product recommendations."

[0900] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0901] Step 1: Import data

[0902] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect the required data. This processing step involves retrieving the data from the data sources and storing it in temporary storage.

[0903] Input: Acquiring target data through API calls or database queries

[0904] Data processing: Analyzes response data from APIs and query results, and converts formats

[0905] Output: The converted data is saved in temporary storage.

[0906] Specific operation: The server uses the API to access the CRM system, retrieve customer data, convert it to JSON format, and save it in storage.

[0907] Step 2: Text analysis and auto-tagging

[0908] The server analyzes the collected data using natural language processing (NLP) technology and automatically assigns tags to the data based on the analysis results. This process involves semantic analysis and tagging of text data.

[0909] Input: Text data stored in temporary storage

[0910] Data processing: Perform text and semantic analysis using NLP techniques (e.g., spaCy or nltk) to extract specific keywords and categories.

[0911] Output: Data tagged based on the analysis results

[0912] Specific operation: The server uses Python's nltk library to analyze the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[0913] Step 3: ECRS Data Cleanup

[0914] The server organizes the collected and tagged data in terms of elimination, combination, exchange, and simplification, a process that includes removing unnecessary data and converting data formats.

[0915] Input: tagged data

[0916] Data processing: Deleting duplicate data, merging related data, converting some data formats, deleting unnecessary data

[0917] Output: Organized and consolidated data

[0918] What happens: The server uses SQL queries to remove duplicate customer information and combines purchase history data with feedback data.

[0919] Step 4: Assessing the value of your data

[0920] The server evaluates the organized data and calculates a data value score. In this step, scoring is based on multiple evaluation criteria.

[0921] Input: Organized and consolidated data

[0922] Data processing: Calculate a score based on the evaluation criteria of usability, frequency, substitutability, versatility, and impact.

[0923] Output: Dataset with data value scores

[0924] Specific operation: The server uses an algorithm to calculate a score for product review data based on the number of monthly views and the detail level of the review, and records this in a database.

[0925] Step 5: Set the security level

[0926] The server assesses the confidentiality of the data and sets an appropriate security level, which ensures strict access control for important data.

[0927] Input: Organized and scored data

[0928] Data processing: Use data classification tools to identify sensitive information and set appropriate security levels

[0929] Output: A dataset with security levels set

[0930] Specific operation: The server uses Apache Ranger to set the highest security for data including employee personal information and control it so that only specific users can access it.

[0931] Step 6: Generate reports

[0932] The server creates a report based on the organized data and its evaluation results and provides it to the user. This process includes summarizing the results and creating a report.

[0933] Input: Organized and secured data

[0934] Data processing: Data summaries, value scores, and security levels are compiled and converted into report formats such as PDF.

[0935] Output: Report provided to the user

[0936] Specific operation: The server generates a PDF report detailing the entire data, ECRS sorting results, data value score, and security level, and sends it to the user's email address.

[0937] Step 7: Emotion Engine Processing

[0938] The server analyzes the user's input information (keystrokes, voice, facial expressions, etc.) and evaluates the user's emotional state in real time. An emotion analysis engine is used in this step.

[0939] Input: Real-time user input information (text, voice, facial expressions)

[0940] Data processing: Using emotion analysis technology, we evaluate the user's emotional state from input information.

[0941] Output: Evaluated user emotional state data

[0942] How it works: The server analyzes the voice data using the Google Cloud Speech-to-Text API and evaluates the user's emotions in real time.

[0943] Step 8: Emotional Feedback

[0944] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby improving the user experience.

[0945] Input: User's emotional state data as assessed by the emotion engine

[0946] Data manipulation: Adjusting interface content based on the user's emotional state

[0947] Output: The adapted interface presented to the user

[0948] How it works: The server dynamically updates the interface using React.js, displaying positive tone suggestions to users in a positive emotional state.

[0949] (Application example 2)

[0950] 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."

[0951] Conventional big data management systems focused on efficiently organizing and utilizing data, but it was difficult to understand user emotions and provide optimal suggestions and information based on those emotions. Furthermore, online shopping sites are seeking to improve the user experience, necessitating greater personalization. To address this, technology is needed that can analyze user emotions and use them to suggest products and provide services.

[0952] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data, means for text analysis and automatic tagging of the acquired data, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for diagnosing the confidentiality of the data and setting an appropriate security level, means for generating and providing the organized data and its evaluation results as a report, means for recognizing user emotions, means for adjusting the information display method and product proposals based on the user's emotional state, and means for providing this data and report to the user and providing an interface that accepts user instructions. This makes it possible to provide optimal product proposals and information based on the user's emotions.

[0953] A "data acquisition means" is a system or method for collecting and temporarily storing data from various data sources.

[0954] "Means for text analysis and automatic tagging" refers to a system or method that uses natural language processing technology to analyze acquired text data and automatically assign relevant tags.

[0955] "Means of organizing in terms of elimination, combination, replacement, and simplification" refers to a system or method that eliminates unnecessary parts of data, combines related information, and, if necessary, changes the format to make the whole easier to understand and simplify.

[0956] A "means for generating a data value score" is a system or method that evaluates the usability, frequency, substitutability, versatility, and impact of data, and assigns a score to the data based on these evaluation criteria.

[0957] A "means for diagnosing data confidentiality and setting an appropriate security level" is a system or method that performs a process of thoroughly evaluating the confidentiality of data and setting an appropriate security level based on the results.

[0958] The "means for generating and providing a report" refers to a system or method for generating a report summarizing the organized and evaluated data and providing it to a user.

[0959] "Means for recognizing user emotions" refers to a system or method for analyzing a user's emotional state through user input data or facial recognition.

[0960] "Means for adjusting information display methods and product recommendations based on the user's emotional state" refers to a system or method that changes the content and tone of displayed information, product recommendations, etc., depending on the user's recognized emotions.

[0961] A "means for providing an interface" is a system or method that provides a user interface for a user to view and provide instructions for data and reports.

[0962] MODE FOR CARRYING OUT THE INVENTION

[0963] This invention is a system that uses AI technology to efficiently organize and utilize big data and recognize user emotions. Below, we will explain how to specifically implement this system.

[0964] Server processing

[0965] 1. Importing data

[0966] The server accesses the company's data sources and retrieves data using means such as databases, file systems, cloud storage, and APIs, and stores it in temporary storage. For example, it retrieves customer data from a CRM system and feedback data from social media accounts via APIs.

[0967] 2. Text analysis and automatic tagging

[0968] The server analyzes the acquired data using natural language processing (NLP) technology and automatically assigns tags. For example, it analyzes customer feedback text and assigns tags such as "positive," "negative," and "product name."

[0969] 3. ECRS Data Collection

[0970] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it. It removes unnecessary data, combines related information, and converts some information into other formats. For example, it removes duplicate customer information and combines purchase history data and feedback data.

[0971] 4. Generating a Data Value Score

[0972] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the level of detail of the reviews, and the value of each product is assessed.

[0973] 5. Setting the security level

[0974] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data. For example, data containing personal information of employees is set to the highest security level, allowing only specific users to access it.

[0975] 6. Generate Reports

[0976] The server then compiles the results of the above process into a report, which includes the data organization status, value score, and security settings. For example, a report detailing the entire data, ECRS organization results, data value score, and security level can be generated and provided to the user.

[0977] 7. Emotion Engine Processing

[0978] The server uses an emotion engine to analyze user input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state.

[0979] 8. Emotional Feedback

[0980] The server adjusts the way data is displayed and product suggestions are made based on the user's emotional state as assessed by the emotion engine. For example, if a user's feedback information is judged to be positive, the server will display effective suggestions in a positive tone to the user.

[0981] Hardware and software used

[0982] Hardware:

[0983] Server: Data analysis and storage

[0984] Smartphone: User emotion analysis and interface provision

[0985] Camera: Emotion Analysis with Facial Recognition

[0986] software:

[0987] Natural Language Processing (NLP): Text analysis and tagging (e.g., Google Cloud Natural Language API)

[0988] Machine learning models: emotion engines (e.g., OpenAI's GPT-3, Amazon Rekognition)

[0989] Database: Data integration and management (e.g., MySQL, PostgreSQL)

[0990] Specific examples

[0991] For example, if a user enters negative feedback such as "I don't know how to use this product," the emotion engine analyzes the content and recommends easy-to-understand how-to videos or FAQ sections. Also, if a user smiles through their smartphone camera, the emotion engine detects positive emotions and notifies the user of new products or exclusive coupons.

[0992] Example prompts to input to a generative AI model:

[0993] The user typed "I don't know how to use this product." The sentiment engine analyzed this feedback and determined the negative sentiment. Think about the best suggestion to make the user interested in reading more. Possible actions could be to provide a link to a how-to video or a guide to the FAQ section.

[0994] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0995] Step 1:

[0996] Importing Data

[0997] The server accesses various data sources within the company to retrieve the required data. Specifically, data is retrieved via databases, file systems, cloud storage, APIs, etc., and then stored in temporary storage. For example, customer data may be retrieved from a company's CRM system, and feedback data may be retrieved from social media accounts via APIs. The input is the data source, and the output is the raw data stored in temporary storage.

[0998] Step 2:

[0999] Text analysis and auto-tagging

[1000] The server uses natural language processing (NLP) technology to perform text analysis on the data stored in temporary storage and automatically assign tags. For example, it analyzes customer feedback text and assigns tags such as positive, negative, and product names. The input is raw text data, and the output is the analyzed results and the associated tags. Specifically, it uses an NLP model (e.g., Google Cloud Natural Language API) to analyze the text and assign relevant tags.

[1001] Step 3:

[1002] ECRS data organization

[1003] The server organizes the analyzed data in terms of eliminating, combining, exchanging, and simplifying. It removes duplicate data, combines related information, and changes the data format as needed. For example, it removes duplicate customer information and combines purchase history data and feedback data. The input is tagged data, and the output is organized data. Specific operations include filtering and integrating data using database operations (e.g., MySQL).

[1004] Step 4:

[1005] Generating a Data Value Score

[1006] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the detail of the reviews, and the value of each product is evaluated. The input is the organized data, and the output is a data value score. Specifically, a numerical analysis algorithm is used to calculate a score based on each evaluation criterion.

[1007] Step 5:

[1008] Security Level Settings

[1009] The server assesses the confidentiality of the data and sets an appropriate security level. For example, it sets the highest security level for data containing personal employee information, allowing only specific users to access it. The input is the data value score and organized data, and the output is the set security level. Specifically, it sets appropriate access control using a security policy management system (e.g., AWS IAM).

[1010] Step 6:

[1011] Generate reports

[1012] The server compiles the results of the above processing into a report as a summary. The report includes the data organization status, value score, and security settings. For example, a report detailing the overall data, ECRS organization results, data value score, and security level is generated and provided to the user. The input is the result data generated at each stage of the processing, and the output is the completed report. Specifically, the data analysis results are compiled into a report format using document generation software (e.g., LaTeX, Microsoft Office).

[1013] Step 7:

[1014] Emotion engine processing

[1015] The server uses an emotion engine to analyze the user's input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state. The input is the user's real-time data, and the output is the emotion analysis results. Specifically, emotion analysis is performed using a machine learning model (e.g., OpenAI GPT-3, Amazon Rekognition).

[1016] Step 8:

[1017] Emotion-based feedback

[1018] The server adjusts how data is displayed and how products are suggested based on the user's emotional state as assessed by the emotion engine. For example, if the user's emotion is judged to be positive, it displays effective product suggestions in a positive tone. The input is the emotion analysis results, and the output is tailored suggestions and information based on that emotion. Specific operations include dynamically changing content using a user interface system (e.g., web dashboard, mobile app).

[1019] This will enable optimal product suggestions and information provision based on the user's emotions.

[1020] 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.

[1021] 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.

[1022] 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.

[1023] [Third embodiment]

[1024] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1025] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1026] 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).

[1027] 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.

[1028] 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.

[1029] 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).

[1030] 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.

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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."

[1036] This invention is a system for efficiently organizing and utilizing big data held by a company using AI technology. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1037] Server processing

[1038] 1. Importing data

[1039] The server collects data from various data sources within the enterprise, such as databases, file systems, cloud storage, or APIs. For example, the server collects data from the enterprise's CRM system, ERP system, and social media accounts and stores it in a database.

[1040] Examples:

[1041] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[1042] 2. Text analysis and automatic tagging

[1043] The server processes the collected data using text analysis technology, specifically natural language processing (NLP) algorithms, to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize.

[1044] Examples:

[1045] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[1046] 3. ECRS Data Collection

[1047] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining relevant data, the data set is effectively simplified.

[1048] Examples:

[1049] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[1050] 4. Assessing Data Value

[1051] The server evaluates the organized data based on its usability, frequency, substitutability, versatility, and impact, and generates a "data value score." This score is converted into a number and indicates the importance of the data.

[1052] Examples:

[1053] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[1054] 5. Setting the security level

[1055] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[1056] Examples:

[1057] The server is set to the highest security level for data including employees' personal information, and is only accessible to specific users.

[1058] 6. Generate Reports

[1059] The server then compiles a report summarizing the results of the process, including the organization of the data, its value score, and security settings.

[1060] Examples:

[1061] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[1062] Terminal and user processing

[1063] 1. Providing an interface

[1064] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[1065] Examples:

[1066] The device allows users to view data collation results and reports in real time through a web dashboard.

[1067] 2. User operations and instructions

[1068] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[1069] Examples:

[1070] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[1071] In this way, a system that provides a series of functions for efficiently organizing and effectively utilizing the big data held by companies will be realized, maximizing the value of data and helping to improve the efficiency and reduce costs of data management.

[1072] The processing flow will be explained below.

[1073] Step 1:

[1074] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[1075] Step 2:

[1076] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[1077] Step 3:

[1078] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[1079] Step 4:

[1080] The server analyzes the stored data using natural language processing (NLP) technology, analyzing the meaning and sentiment of the text data and automatically tagging it.

[1081] Step 5:

[1082] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[1083] Step 6:

[1084] The server organizes the data, eliminating unnecessary data, combining related information, exchanging some information into other formats, and converting it into a simpler structure.

[1085] Step 7:

[1086] The server evaluates each data entry and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[1087] Step 8:

[1088] The server assigns an appropriate security level to each piece of data based on the evaluation results, and implements access control according to the assigned security level.

[1089] Step 9:

[1090] The server compiles the organized data and its evaluation results and generates a report that includes the data organization status, value score, security settings, and more.

[1091] Step 10:

[1092] The server provides the generated report to the user, for example by emailing it or uploading it to a dashboard.

[1093] Step 11:

[1094] The device provides an interface where users can view reports and data, with the ability to drill down into the data and utilize filters and search capabilities.

[1095] Step 12:

[1096] Users can search for data and check the evaluation results via their terminal, and if necessary, give instructions for additional operations or reorganization, enabling further utilization of the data.

[1097] Through these steps, corporate data can be efficiently organized, utilized to the fullest extent, and protected with appropriate security.

[1098] Example 1

[1099] 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."

[1100] Companies possess a large amount of big data, but they need methods to efficiently organize and utilize that data. In particular, they face challenges in integrating and analyzing data collected from a wide variety of sources, assessing its value, and managing it safely.

[1101] 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.

[1102] In this invention, the server includes means for acquiring information, means for analyzing the acquired information using natural language processing and automatically tagging it, means for organizing the acquired information from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the information and generating an information value score, means for assessing the confidentiality of the information and setting an appropriate security level, means for generating and providing a report of the organized information and its evaluation results, and means for providing this information and report to users and providing an interface for accepting user instructions.This makes it possible to efficiently organize big data held by companies, maximize its value, and utilize it safely and effectively.

[1103] "Information" refers to all data obtained from various data sources across the enterprise.

[1104] "Natural language processing" is a general term for techniques and algorithms that enable computers to understand, interpret, and generate human language.

[1105] "Auto-tagging" refers to the process of automatically analyzing the content of collected data and assigning relevant keywords and categories.

[1106] "Exclusion" refers to the act of removing unnecessary information from data.

[1107] "Combining" refers to the act of unifying and integrating different data sets or data items.

[1108] "Exchange" refers to the act of replacing part of a piece of data with other data.

[1109] "Simplification" refers to the act of removing unnecessary parts and simplifying the data structure in order to convert data into a more manageable form.

[1110] The "information value score" is an evaluation value calculated based on the usability, frequency, substitutability, versatility, and impact of information.

[1111] "Confidentiality" refers to the security property that prevents information from being accessed or disclosed unauthorizedly.

[1112] "Security level" is a standard that indicates the strength of security management, set according to the confidentiality and importance of data.

[1113] A "report" is a written or electronic file that compiles organized information and the results of its evaluation.

[1114] "Interface" refers to the user interface through which users access the system and perform operations and give instructions.

[1115] This invention is a system for efficiently organizing and effectively utilizing big data held by companies. The system is mainly composed of servers, terminals, and users, and by clearly defining the roles of each component, it achieves data acquisition, analysis, organization, evaluation, and utilization.

[1116] Server processing

[1117] 1. Importing data

[1118] The server collects data from various company data sources, utilizing databases, file systems, cloud storage, APIs, etc. For example, the server retrieves data from the company's customer relationship management system (CRM) and enterprise resource planning system (ERP) and imports it into a local database (e.g., MySQL, PostgreSQL). It also collects feedback data from social media accounts via APIs and stores it in the same way.

[1119] Examples:

[1120] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[1121] 2. Text analysis and automatic tagging

[1122] The server analyzes the collected data using natural language processing (NLP) techniques. Specifically, it uses generative AI models (e.g., GPT-3, BERT) to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize the data.

[1123] Examples:

[1124] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[1125] 3. ECRS Data Collection

[1126] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining related data, the data set is effectively simplified. Also, by simplifying the structure, it becomes easier to access.

[1127] Examples:

[1128] The server removes duplicate customer information, consolidates purchase history data and feedback data, and removes unnecessary data fields to generate a simpler table.

[1129] 4. Assessing Data Value

[1130] The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact. This score is quantified and serves as an evaluation standard for the importance of the data.

[1131] Examples:

[1132] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[1133] 5. Setting the security level

[1134] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[1135] Examples:

[1136] The server is set to the highest security level for data including employees' personal information and is only accessible to specific users.

[1137] 6. Generate Reports

[1138] The server then compiles a report summarizing the results of the process, including information on how the data is organized, its value score, and security settings.

[1139] Examples:

[1140] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[1141] Terminal and user processing

[1142] 1. Providing an interface

[1143] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[1144] Examples:

[1145] The device allows users to view data collation results and reports in real time through a web dashboard.

[1146] 2. User operations and instructions

[1147] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[1148] Examples:

[1149] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[1150] Prompt Sentence Examples

[1151] Examples:

[1152] "Generate a report showing the results of an analysis of the company's customer data. Include, among other things, the percentage of positive and negative feedback, a rating score by product, and a data value score."

[1153] This system allows companies to efficiently organize their big data and maximize its value, while also improving the efficiency and reducing costs of data management.

[1154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1155] Step 1: Collect data

[1156] More specifically: The server collects data from various data sources within the enterprise.

[1157] Inputs: Data sources such as CRM systems, ERP systems, social media accounts, etc.

[1158] Data processing / calculation: The server retrieves data from these data sources using APIs or SQL queries.

[1159] Output: Raw data collected in a local database

[1160] What it does: The server periodically sends API requests to retrieve the latest customer data and feedback data, and retrieves various data from the database using SQL queries and stores them in a local database.

[1161] Step 2: Extract text data

[1162] Specifically: The server extracts text data from the stored database.

[1163] Input: Raw data stored in a local database

[1164] Data processing / calculation: The server runs a SELECT query to extract the required text fields from the database.

[1165] Output: Extracted text data

[1166] Specific operation: The server uses a SELECT statement to retrieve the text field from the feedback table and build a dataset for analysis.

[1167] Step 3: Natural Language Processing and Auto-Tagging

[1168] Specific explanation: The server analyzes the extracted text data using natural language processing (NLP) technology and performs automatic tagging.

[1169] Input: Extracted text data

[1170] Data processing / calculation: Input text data into a generative AI model (e.g., GPT-3, BERT) to obtain analysis results. Based on the analysis results, relevant tags are added.

[1171] Output: A tagged dataset

[1172] Specific operation: The server inputs text data into the generative AI model and updates the tag information in the database based on the analysis results output by the model.

[1173] Step 4: ECRS Data Cleanup

[1174] Specifically: The server organizes the collected and analyzed data in terms of eliminating, combining, exchanging, and simplifying it.

[1175] Input: tagged dataset

[1176] Data processing / calculation: The server removes duplicate data, combines related data, and simplifies by eliminating unnecessary data.

[1177] Output: A cleaned dataset

[1178] Specific operation: The server deletes duplicate records in the database using a DELETE statement, joins the purchase history data and feedback data using a JOIN query, and removes unnecessary data fields to create a simple table.

[1179] Step 5: Assessing the value of your data

[1180] Specific explanation: The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact.

[1181] Input: A cleaned dataset

[1182] Data processing / calculation: Data is evaluated using a formula that calculates a score based on criteria such as usability and frequency, and a value score is generated.

[1183] Output: Data Value Score

[1184] Specific operation: The server executes the function based on the above criteria to calculate a score for each data value, and stores the calculated score in the database.

[1185] Step 6: Set the security level

[1186] Specifically: The server sets an appropriate security level based on the content and importance of the data.

[1187] Input: A curated dataset and its value scores

[1188] Data processing / calculation: Set access control on data based on sensitivity.

[1189] Output: A dataset with security levels set

[1190] What happens: The server uses NLP algorithms to analyze the data content, assigns security tags, and updates the ACL (Access Control List) to set the appropriate security level.

[1191] Step 7: Generate reports

[1192] Detailed explanation: The server summarizes the results of the above processing in a report.

[1193] Input: Dataset with security level

[1194] Data processing / calculation: Report generation algorithms are used to compile summaries of data organization, value scores, security settings, etc.

[1195] Output: Generated report

[1196] Specific operation: The server executes database queries to aggregate various data, generates reports in PDF or HTML format, and delivers the reports to the user via email.

[1197] This will enable companies to efficiently organize the big data they hold, maximizing its value, and utilizing it safely and effectively.

[1198] (Application example 1)

[1199] 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."

[1200] Currently, many companies possess vast amounts of data, but it is difficult to efficiently organize that data and extract valuable information. Logistics centers, in particular, require real-time, reliable information for inventory management and delivery planning. Furthermore, the lack of a system that can assess data value and generate appropriate reports while ensuring data confidentiality makes it difficult to simultaneously achieve both logistics efficiency and data security. Therefore, there is a need for a method to achieve efficient data management and value assessment in logistics centers.

[1201] 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.

[1202] In this invention, the server includes means for acquiring data, means for text analysis of the acquired data and automatic tagging, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for assessing the confidentiality of the data and setting an appropriate security level, means for generating and providing a report of the organized data and its evaluation results, means for providing this data and report to a user and providing an interface for accepting user instructions, means for collecting logistics management information and evaluating the utilization rate, sales volume, and supply risk of each item, and means for generating a report showing inventory status and delivery risk based on the evaluated information, thereby enabling efficient data management and value assessment at a logistics center.

[1203] "Data acquisition means" is a function for collecting necessary data from a specific data source.

[1204] "Text analysis means" refers to a technique for interpreting collected data using natural language processing technology and analyzing its meaning.

[1205] "Automatic tagging means" is a function that automatically assigns appropriate tags to analyzed data, making it easier to classify and search the data.

[1206] "Data reduction methods" are methods for optimizing collected data in terms of eliminating, combining, exchanging, and simplifying it.

[1207] "Data value assessment means" is a function for evaluating the usability, frequency, substitutability, versatility, and impact of data, and generating a data value score.

[1208] "Security setting means" is a means for diagnosing the confidentiality of data and setting an appropriate security level.

[1209] The "report generation means" is a function for creating a report based on the organized data and its evaluation results and providing it to the user.

[1210] The "interface providing means" refers to means including a screen and an input device for providing data and reports to a user and receiving instructions from the user.

[1211] The "logistics management information collection means" is a function for collecting information related to inventory and delivery at the logistics center.

[1212] The "utilization rate evaluation means" is a means for evaluating the utilization rate and inventory trends of each item.

[1213] The "sales number evaluation means" is a means for evaluating the sales number of each item and recording it as data.

[1214] The "supply risk assessment means" is a function for assessing potential risks in the supply of each item.

[1215] The "inventory status report generating means" is a function that generates a report showing the inventory status and delivery risk at the logistics center.

[1216] The system embodying the present invention provides functions for efficient data management and value assessment in a logistics center. Specific embodiments will be described below.

[1217] Server processing

[1218] 1. Data Collection Methods

[1219] The server retrieves data from the inventory management system at the logistics center using cloud storage, API interfaces (Flask, Django), etc. For example, product inventory status data is extracted from the inventory management system and stored in a database on the cloud.

[1220] 2. Text Analysis Methods

[1221] The server analyzes the collected data using natural language processing technology (NLTK, spaCy). This allows product descriptions and historical data to be interpreted. The analyzed data is automatically tagged with tags such as "low stock" or "high demand."

[1222] 3. Data organization methods

[1223] The server optimizes the collected data in terms of deduplication, data integration, data exchange, and data simplification. This allows for efficient management of ongoing order information and supply data. For example, information from different warehouses for the same product can be combined and managed as a single data set.

[1224] 4. Data Value Assessment Methods

[1225] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score. Scikit-learn is used for the evaluation, and product availability and supply risk are displayed numerically. For example, the server calculates a score for Product A, such as availability of 70%, sales volume of 500, and supply risk of 20%.

[1226] 5. Security Configuration Methods

[1227] The server assesses the confidentiality of the data and sets an appropriate security level using AWS IAM and OAuth 2.0. For example, a high security level is set for personal customer data, allowing only specific users to access it.

[1228] 6. Report Generation Methods

[1229] The server creates reports based on the organized data and its evaluation results and provides them to users. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[1230] Terminal and user processing

[1231] 1. Means of providing interface

[1232] The terminal is implemented as a web or mobile application and provides an interface for users to view data and reports, for example, allowing users to check inventory status and evaluation results in real time through a web dashboard.

[1233] 2. User operations and instructions

[1234] Through the device, users can search, evaluate, and reorganize data, for example by filtering the availability of specific products or by requesting the import of new data.

[1235] Specific examples

[1236] For example, the system acquires inventory management data from a logistics center, evaluates the utilization rate, sales volume, and supply risk for each product, and generates a score based on the results. It also uses this data to create reports showing inventory status and delay risks.

[1237] Example prompts for generative AI models

[1238] Prompt: Obtain inventory management data for a distribution center, evaluate utilization rate, sales volume, and supply risk for each product, and generate a score based on that. Also, use that data to create a report showing stock status and risk of delays.

[1239] In this way, a system is provided that enables efficient data management and value assessment in a logistics center.

[1240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1241] Step 1: Collect data

[1242] The server retrieves data from the inventory management system of the logistics center. Specifically, it uses cloud storage and API interfaces (Flask, Django) to store information such as the inventory status, shipping history, and receiving history of each item in a cloud database.

[1243] Input: Data from inventory management system

[1244] Output: Inventory status, shipping history, and receiving history data stored in a cloud database

[1245] Step 2: Text analysis and auto-tagging

[1246] The server analyzes the collected data using natural language processing technology (NLTK, spaCy), which interprets the meaning of product descriptions and historical data and automatically assigns relevant tags.

[1247] Input: Data stored in a cloud database

[1248] Output: Analysis results and assigned tags (e.g., "Low stock" or "High demand")

[1249] Step 3: Data organization

[1250] The server optimizes the acquired data in terms of deduplication, data merging, data exchange, and data simplification. For example, data from different warehouses for the same product can be merged and compiled into a single data set.

[1251] Input: tagged data

[1252] Output: Optimized dataset

[1253] Step 4: Data Value Assessment

[1254] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score using Scikit-learn, which numerically displays the availability rate, sales volume, and supply risk of each item.

[1255] Input: Optimized dataset

[1256] Output: Data value score (e.g., availability 70%, sales volume 500, supply risk 20%)

[1257] Step 5: Security Settings

[1258] The server assesses the confidentiality of the data and sets an appropriate security level using AWS IAM and OAuth 2.0. For example, a high security level is set for data containing customer personal information, allowing only specific users to access it.

[1259] Input: Data Value Score

[1260] Output: A secured dataset

[1261] Step 6: Generate reports

[1262] The server creates reports based on the organized data and its evaluation results and provides them to the user. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[1263] Input: Secured dataset

[1264] Output: Generated report

[1265] Step 7: Providing an Interface

[1266] The device provides an interface for users to view data and reports through a web or mobile application, and allows users to search, evaluate, and reorganize the data through the interface.

[1267] Input: User instructions and operations

[1268] Output: Search results, evaluation results, reorganized data

[1269] In this way, by going through each step, efficient data management and value assessment can be achieved at the logistics center.

[1270] 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.

[1271] This invention is a system that uses AI technology to efficiently organize and utilize big data held by companies, and also incorporates an emotion engine that recognizes user emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1272] Server processing

[1273] 1. Importing data

[1274] The server accesses various data sources of the company and gathers data, retrieving it via databases, file systems, cloud storage, APIs, etc., and stores it in temporary storage.

[1275] Examples:

[1276] The server retrieves customer data from the company's CRM system and also retrieves feedback data from social media accounts via API.

[1277] 2. Text analysis and automatic tagging

[1278] The server analyzes the collected data using natural language processing (NLP) technology, and automatically assigns tags to the data based on the analysis results, making it easier to search and classify the data.

[1279] Examples:

[1280] The server analyzes the text data of customer feedback and assigns tags such as "positive," "negative," and "product name."

[1281] 3. ECRS Data Collection

[1282] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it: unnecessary data is removed, related information is combined, and some information is converted into other formats.

[1283] Examples:

[1284] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[1285] 4. Assessing Data Value

[1286] The server evaluates the organized data and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[1287] Examples:

[1288] The server calculates a score for product review data based on the number of monthly views and the level of detail in the reviews, and evaluates the value of each product.

[1289] 5. Setting the security level

[1290] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data.

[1291] Examples:

[1292] The server is set to the highest security level for data including employees' personal information, and only allows access by specific users.

[1293] 6. Generate Reports

[1294] The server then compiles a report summarizing the results of the process, including the data organization status, value score, and security settings.

[1295] Examples:

[1296] The server generates a report detailing the entire data, ECRS sorting results, data value score, and security level, and provides it to the user.

[1297] 7. Emotion Engine Processing

[1298] The server uses an emotion engine to analyze user input information, which analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate their emotional state.

[1299] Examples:

[1300] The system evaluates emotions from feedback information entered by the user and the tone of chat messages to determine the user's emotional state.

[1301] 8. Emotional Feedback

[1302] The server adjusts the way the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby providing information that best suits the user's current emotional state.

[1303] Examples:

[1304] If the user judges the feedback information to be positive, effective suggestions are displayed to the user in a positive tone.

[1305] Terminal and user processing

[1306] 1. Providing an interface

[1307] The device provides an interface that allows users to view data and reports, including the ability to view data details and use filters and search functions.

[1308] Examples:

[1309] The device allows users to view data compilation results and reports in real time through a web dashboard.

[1310] 2. User operations and instructions

[1311] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[1312] Examples:

[1313] From the web dashboard, users can apply specific filters, direct detailed data analysis, or request new data imports.

[1314] Through these steps, corporate data can be efficiently organized, utilized to the highest degree, and protected with appropriate security. Furthermore, the emotion engine presents data optimally according to the user's emotional state.

[1315] The processing flow will be explained below.

[1316] Step 1:

[1317] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[1318] Step 2:

[1319] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[1320] Step 3:

[1321] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[1322] Step 4:

[1323] The server analyzes the stored data using natural language processing (NLP) technology, specifically analyzing the text information within the data to extract meaning and sentiment.

[1324] Step 5:

[1325] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[1326] Step 6:

[1327] The server organizes the data in terms of ECRS (Eliminate, Combine, Exchange, Simplify), which eliminates redundancies in the dataset and integrates relevant information.

[1328] Step 7:

[1329] The server evaluates each data entry and calculates a data value score, based on criteria such as frequency of use and impact on profits.

[1330] Step 8:

[1331] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby realizing access control according to the confidentiality of the data.

[1332] Step 9:

[1333] The server generates a report based on the organized data and the evaluation results, including the data organization status, value score for each data entry, and security level.

[1334] Step 10:

[1335] The server provides the generated report to the user, either by emailing it or uploading it to a web dashboard.

[1336] Step 11:

[1337] The server analyzes the user's input information using an emotion engine, which evaluates the user's emotional state in real time.

[1338] Step 12:

[1339] The device will adjust how it displays data based on the user's emotional state: for example, if the user is feeling stressed, it will prioritize displaying concise, easy-to-understand information.

[1340] Step 13:

[1341] The terminal provides an interface for viewing data and reports, with filters and search capabilities to make it easier for users to find the information they need.

[1342] Step 14:

[1343] Users can search, evaluate, and reorganize data via their devices. Furthermore, they can refer to the results of the emotion engine to further utilize the data.

[1344] Through these steps, a company's big data can be efficiently organized and effectively utilized. Furthermore, the emotion engine analyzes the user's emotional state, enabling optimal information to be provided.

[1345] Example 2

[1346] 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."

[1347] Modern companies possess vast amounts of data, but they face challenges in efficiently organizing and utilizing this data. Furthermore, traditional data organization systems do not take into account the user's emotional state and lack means to optimize the user experience.

[1348] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1349] In this invention, the server includes: means for acquiring data; means for analyzing the acquired data using natural language processing and automatically tagging it; means for organizing the acquired data from the perspectives of elimination, combination, exchange, and simplification; means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score; means for assessing the confidentiality of the data and setting an appropriate security level; means for generating and providing the organized data and its evaluation results as a report; means for analyzing the acquired data and user-entered information using an emotion engine and evaluating the user's emotional state; means for adjusting the data display method based on the evaluated emotional state; and means for providing the data and report to the user and for providing an interface for accepting user instructions. This makes it possible to efficiently organize the vast amount of data held by a company and present optimal data according to the user's emotional state.

[1350] "Means of acquiring data" refers to the methods and technologies used to collect data from various data sources held by the company and store it in temporary storage.

[1351] "Natural language processing" refers to the techniques and methods that allow computers to understand, interpret, and generate human language.

[1352] "Text analysis" is the process of analyzing textual information using natural language processing technology and extracting meaning and structure from its content.

[1353] "Auto-tagging" is the process of automatically assigning relevant keywords and categories to data based on the results of text analysis.

[1354] "Means of organizing in terms of elimination, combination, exchange, and simplification" refers to techniques and methods for eliminating data duplication, combining related information, exchanging data formats as necessary, and simplifying and organizing data.

[1355] The "data value score" is a score calculated based on evaluation criteria such as the data's usability, frequency, substitutability, versatility, and impact.

[1356] "Means for diagnosing confidentiality and setting an appropriate security level" refers to techniques and methods for determining whether data contains confidential information and applying security measures as necessary.

[1357] The "means for generating and providing a report" refers to a technique and method for creating a report summarizing the organized data and its evaluation results and providing it to the user.

[1358] An "emotion engine" is a system and technology that analyzes a user's input information (key input, voice, facial expression, etc.) and evaluates their emotional state.

[1359] The "means for providing an interface" refers to the technology and method for providing a user interface that allows a user to view data and reports and to perform operations and give instructions.

[1360] This invention is a utilization system that uses AI technology to efficiently organize big data held by companies and incorporates an emotion engine that recognizes user emotions. This system is mainly composed of a server, a terminal, and a user. Detailed embodiments of the system are described below.

[1361] Server embodiment

[1362] 1. Importing data

[1363] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect data, which is then stored in temporary storage.

[1364] Example: A server makes an API call to retrieve customer data from a CRM system and temporarily stores that data.

[1365] 2. Text analysis and automatic tagging

[1366] The server uses natural language processing (NLP) technology to analyze the collected data and automatically assigns tags to the data based on the results. This is done using a Python NLP library (such as spaCy or nltk).

[1367] Example: The server analyzes the text of customer feedback and assigns tags such as "positive," "negative," and "product name."

[1368] 3. ECRS Data Collection

[1369] The server organizes the data using methods such as eliminating, combining, exchanging, and simplifying, using SQL queries and other database management tools.

[1370] Example: The server removes duplicate customer information and combines purchase history and feedback data.

[1371] 4. Assessing Data Value

[1372] The server calculates a value score for the organized data based on evaluation criteria, including usability, frequency, substitutability, versatility, and impact.

[1373] Example: The server calculates a score based on the number of monthly views and the detail of the reviews, and records this in a database.

[1374] 5. Setting the security level

[1375] The server assesses the sensitivity of the data and sets an appropriate security level using data classification tools (e.g., Apache Ranger).

[1376] Example: The server is set to the highest security level for data including employee personal information, and only specific users can access it.

[1377] 6. Generate Reports

[1378] The server then compiles the organized data and evaluation results into a report that summarizes the results. This report is generated in PDF format and provided to the user.

[1379] Example: The server generates a PDF report containing a summary of the data, a value score, and a security level and sends it to the user's email address.

[1380] 7. Emotion Engine Processing

[1381] The server analyzes the user's input (keystrokes, voice, facial expressions, etc.) to assess their emotional state in real time, using the Google Cloud Speech-to-Text API for voice input analysis.

[1382] Example: The server assesses the user's emotional state based on feedback information and the tone of their chat messages.

[1383] 8. Emotional Feedback

[1384] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, dynamically updating the interface using React.js.

[1385] Example: If a user judges the feedback information to be positive, provide them with effective suggestions in a positive tone.

[1386] Terminal embodiment

[1387] 1. Providing an interface

[1388] The terminal provides an interface where users can view data and reports, using a web dashboard powered by React.js.

[1389] Example: The device allows users to view data compilation results and reports in real time through a web dashboard.

[1390] 2. User operations and instructions

[1391] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[1392] Example: A user uses the filter feature in a web dashboard to select a specific data set and request detailed data analysis.

[1393] Example: Example of a prompt sentence to input to a generative AI model

[1394] 1. Prompt for further analysis of positive feedback

[1395] "Perform detailed analysis of positive customer feedback and generate reports with relevant product information."

[1396] 2. Prompt to import new data from a specific data source

[1397] "Import the latest customer feedback data from your social media accounts, then perform text analysis and tagging."

[1398] 3. Prompts that display recommendations based on the sentiment assessment results

[1399] "If the user's emotional state is positive, show them the latest product recommendations."

[1400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1401] Step 1: Import data

[1402] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect the required data. This processing step involves retrieving the data from the data sources and storing it in temporary storage.

[1403] Input: Acquiring target data through API calls or database queries

[1404] Data processing: Analyzes response data from APIs and query results, and converts formats

[1405] Output: The converted data is saved in temporary storage.

[1406] Specific operation: The server uses the API to access the CRM system, retrieve customer data, convert it to JSON format, and save it in storage.

[1407] Step 2: Text analysis and auto-tagging

[1408] The server analyzes the collected data using natural language processing (NLP) technology and automatically assigns tags to the data based on the analysis results. This process involves semantic analysis and tagging of text data.

[1409] Input: Text data stored in temporary storage

[1410] Data processing: Perform text and semantic analysis using NLP techniques (e.g., spaCy or nltk) to extract specific keywords and categories.

[1411] Output: Data tagged based on the analysis results

[1412] Specific operation: The server uses Python's nltk library to analyze the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[1413] Step 3: ECRS Data Cleanup

[1414] The server organizes the collected and tagged data in terms of elimination, combination, exchange, and simplification, a process that includes removing unnecessary data and converting data formats.

[1415] Input: tagged data

[1416] Data processing: Deleting duplicate data, merging related data, converting some data formats, deleting unnecessary data

[1417] Output: Organized and consolidated data

[1418] What happens: The server uses SQL queries to remove duplicate customer information and combines purchase history data with feedback data.

[1419] Step 4: Assessing the value of your data

[1420] The server evaluates the organized data and calculates a data value score. In this step, scoring is based on multiple evaluation criteria.

[1421] Input: Organized and consolidated data

[1422] Data processing: Calculate a score based on the evaluation criteria of usability, frequency, substitutability, versatility, and impact.

[1423] Output: Dataset with data value scores

[1424] Specific operation: The server uses an algorithm to calculate a score for product review data based on the number of monthly views and the detail level of the review, and records this in a database.

[1425] Step 5: Set the security level

[1426] The server assesses the confidentiality of the data and sets an appropriate security level, which ensures strict access control for important data.

[1427] Input: Organized and scored data

[1428] Data processing: Use data classification tools to identify sensitive information and set appropriate security levels

[1429] Output: A dataset with security levels set

[1430] Specific operation: The server uses Apache Ranger to set the highest security for data including employee personal information and control it so that only specific users can access it.

[1431] Step 6: Generate reports

[1432] The server creates a report based on the organized data and its evaluation results and provides it to the user. This process includes summarizing the results and creating a report.

[1433] Input: Organized and secured data

[1434] Data processing: Data summaries, value scores, and security levels are compiled and converted into report formats such as PDF.

[1435] Output: Report provided to the user

[1436] Specific operation: The server generates a PDF report detailing the entire data, ECRS sorting results, data value score, and security level, and sends it to the user's email address.

[1437] Step 7: Emotion Engine Processing

[1438] The server analyzes the user's input information (keystrokes, voice, facial expressions, etc.) and evaluates the user's emotional state in real time. An emotion analysis engine is used in this step.

[1439] Input: Real-time user input information (text, voice, facial expressions)

[1440] Data processing: Using emotion analysis technology, we evaluate the user's emotional state from input information.

[1441] Output: Evaluated user emotional state data

[1442] How it works: The server analyzes the voice data using the Google Cloud Speech-to-Text API and evaluates the user's emotions in real time.

[1443] Step 8: Emotional Feedback

[1444] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby improving the user experience.

[1445] Input: User's emotional state data as assessed by the emotion engine

[1446] Data manipulation: Adjusting interface content based on the user's emotional state

[1447] Output: The adapted interface presented to the user

[1448] How it works: The server dynamically updates the interface using React.js, displaying positive tone suggestions to users in a positive emotional state.

[1449] (Application example 2)

[1450] 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."

[1451] Conventional big data management systems focused on efficiently organizing and utilizing data, but it was difficult to understand user emotions and provide optimal suggestions and information based on those emotions. Furthermore, online shopping sites are seeking to improve the user experience, necessitating greater personalization. To address this, technology is needed that can analyze user emotions and use them to suggest products and provide services.

[1452] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data, means for text analysis and automatic tagging of the acquired data, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for diagnosing the confidentiality of the data and setting an appropriate security level, means for generating and providing the organized data and its evaluation results as a report, means for recognizing user emotions, means for adjusting the information display method and product proposals based on the user's emotional state, and means for providing this data and report to the user and providing an interface that accepts user instructions. This makes it possible to provide optimal product proposals and information based on the user's emotions.

[1453] A "data acquisition means" is a system or method for collecting and temporarily storing data from various data sources.

[1454] "Means for text analysis and automatic tagging" refers to a system or method that uses natural language processing technology to analyze acquired text data and automatically assign relevant tags.

[1455] "Means of organizing in terms of elimination, combination, replacement, and simplification" refers to a system or method that eliminates unnecessary parts of data, combines related information, and, if necessary, changes the format to make the whole easier to understand and simplify.

[1456] A "means for generating a data value score" is a system or method that evaluates the usability, frequency, substitutability, versatility, and impact of data, and assigns a score to the data based on these evaluation criteria.

[1457] A "means for diagnosing data confidentiality and setting an appropriate security level" is a system or method that performs a process of thoroughly evaluating the confidentiality of data and setting an appropriate security level based on the results.

[1458] The "means for generating and providing a report" refers to a system or method for generating a report summarizing the organized and evaluated data and providing it to a user.

[1459] "Means for recognizing user emotions" refers to a system or method for analyzing a user's emotional state through user input data or facial recognition.

[1460] "Means for adjusting information display methods and product recommendations based on the user's emotional state" refers to a system or method that changes the content and tone of displayed information, product recommendations, etc., depending on the user's recognized emotions.

[1461] A "means for providing an interface" is a system or method that provides a user interface for a user to view and provide instructions for data and reports.

[1462] MODE FOR CARRYING OUT THE INVENTION

[1463] This invention is a system that uses AI technology to efficiently organize and utilize big data and recognize user emotions. Below, we will explain how to specifically implement this system.

[1464] Server processing

[1465] 1. Importing data

[1466] The server accesses the company's data sources and retrieves data using means such as databases, file systems, cloud storage, and APIs, and stores it in temporary storage. For example, it retrieves customer data from a CRM system and feedback data from social media accounts via APIs.

[1467] 2. Text analysis and automatic tagging

[1468] The server analyzes the acquired data using natural language processing (NLP) technology and automatically assigns tags. For example, it analyzes customer feedback text and assigns tags such as "positive," "negative," and "product name."

[1469] 3. ECRS Data Collection

[1470] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it. It removes unnecessary data, combines related information, and converts some information into other formats. For example, it removes duplicate customer information and combines purchase history data and feedback data.

[1471] 4. Generating a Data Value Score

[1472] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the level of detail of the reviews, and the value of each product is assessed.

[1473] 5. Setting the security level

[1474] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data. For example, data containing personal information of employees is set to the highest security level, allowing only specific users to access it.

[1475] 6. Generate Reports

[1476] The server then compiles the results of the above process into a report, which includes the data organization status, value score, and security settings. For example, a report detailing the entire data, ECRS organization results, data value score, and security level can be generated and provided to the user.

[1477] 7. Emotion Engine Processing

[1478] The server uses an emotion engine to analyze user input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state.

[1479] 8. Emotional Feedback

[1480] The server adjusts the way data is displayed and product suggestions are made based on the user's emotional state as assessed by the emotion engine. For example, if a user's feedback information is judged to be positive, the server will display effective suggestions in a positive tone to the user.

[1481] Hardware and software used

[1482] Hardware:

[1483] Server: Data analysis and storage

[1484] Smartphone: User emotion analysis and interface provision

[1485] Camera: Emotion Analysis with Facial Recognition

[1486] software:

[1487] Natural Language Processing (NLP): Text analysis and tagging (e.g., Google Cloud Natural Language API)

[1488] Machine learning models: emotion engines (e.g., OpenAI's GPT-3, Amazon Rekognition)

[1489] Database: Data integration and management (e.g., MySQL, PostgreSQL)

[1490] Specific examples

[1491] For example, if a user enters negative feedback such as "I don't know how to use this product," the emotion engine analyzes the content and recommends easy-to-understand how-to videos or FAQ sections. Also, if a user smiles through their smartphone camera, the emotion engine detects positive emotions and notifies the user of new products or exclusive coupons.

[1492] Example prompts to input to a generative AI model:

[1493] The user typed "I don't know how to use this product." The sentiment engine analyzed this feedback and determined the negative sentiment. Think about the best suggestion to make the user interested in reading more. Possible actions could be to provide a link to a how-to video or a guide to the FAQ section.

[1494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1495] Step 1:

[1496] Importing Data

[1497] The server accesses various data sources within the company to retrieve the required data. Specifically, data is retrieved via databases, file systems, cloud storage, APIs, etc., and then stored in temporary storage. For example, customer data may be retrieved from a company's CRM system, and feedback data may be retrieved from social media accounts via APIs. The input is the data source, and the output is the raw data stored in temporary storage.

[1498] Step 2:

[1499] Text analysis and auto-tagging

[1500] The server uses natural language processing (NLP) technology to perform text analysis on the data stored in temporary storage and automatically assign tags. For example, it analyzes customer feedback text and assigns tags such as positive, negative, and product names. The input is raw text data, and the output is the analyzed results and the associated tags. Specifically, it uses an NLP model (e.g., Google Cloud Natural Language API) to analyze the text and assign relevant tags.

[1501] Step 3:

[1502] ECRS data organization

[1503] The server organizes the analyzed data in terms of eliminating, combining, exchanging, and simplifying. It removes duplicate data, combines related information, and changes the data format as needed. For example, it removes duplicate customer information and combines purchase history data and feedback data. The input is tagged data, and the output is organized data. Specific operations include filtering and integrating data using database operations (e.g., MySQL).

[1504] Step 4:

[1505] Generating a Data Value Score

[1506] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the detail of the reviews, and the value of each product is evaluated. The input is the organized data, and the output is a data value score. Specifically, a numerical analysis algorithm is used to calculate a score based on each evaluation criterion.

[1507] Step 5:

[1508] Security Level Settings

[1509] The server assesses the confidentiality of the data and sets an appropriate security level. For example, it sets the highest security level for data containing personal employee information, allowing only specific users to access it. The input is the data value score and organized data, and the output is the set security level. Specifically, it sets appropriate access control using a security policy management system (e.g., AWS IAM).

[1510] Step 6:

[1511] Generate reports

[1512] The server compiles the results of the above processing into a report as a summary. The report includes the data organization status, value score, and security settings. For example, a report detailing the overall data, ECRS organization results, data value score, and security level is generated and provided to the user. The input is the result data generated at each stage of the processing, and the output is the completed report. Specifically, the data analysis results are compiled into a report format using document generation software (e.g., LaTeX, Microsoft Office).

[1513] Step 7:

[1514] Emotion engine processing

[1515] The server uses an emotion engine to analyze the user's input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state. The input is the user's real-time data, and the output is the emotion analysis results. Specifically, emotion analysis is performed using a machine learning model (e.g., OpenAI GPT-3, Amazon Rekognition).

[1516] Step 8:

[1517] Emotion-based feedback

[1518] The server adjusts how data is displayed and how products are suggested based on the user's emotional state as assessed by the emotion engine. For example, if the user's emotion is judged to be positive, it displays effective product suggestions in a positive tone. The input is the emotion analysis results, and the output is tailored suggestions and information based on that emotion. Specific operations include dynamically changing content using a user interface system (e.g., web dashboard, mobile app).

[1519] This will enable optimal product suggestions and information provision based on the user's emotions.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] [Fourth embodiment]

[1524] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1525] 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.

[1526] 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).

[1527] 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.

[1528] 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.

[1529] 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).

[1530] 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.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] 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.

[1535] 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.

[1536] 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."

[1537] This invention is a system for efficiently organizing and utilizing big data held by a company using AI technology. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1538] Server processing

[1539] 1. Importing data

[1540] The server collects data from various data sources within the enterprise, such as databases, file systems, cloud storage, or APIs. For example, the server collects data from the enterprise's CRM system, ERP system, and social media accounts and stores it in a database.

[1541] Examples:

[1542] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[1543] 2. Text analysis and automatic tagging

[1544] The server processes the collected data using text analysis technology, specifically natural language processing (NLP) algorithms, to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize.

[1545] Examples:

[1546] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[1547] 3. ECRS Data Collection

[1548] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining relevant data, the data set is effectively simplified.

[1549] Examples:

[1550] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[1551] 4. Assessing Data Value

[1552] The server evaluates the organized data based on its usability, frequency, substitutability, versatility, and impact, and generates a "data value score." This score is converted into a number and indicates the importance of the data.

[1553] Examples:

[1554] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[1555] 5. Setting the security level

[1556] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[1557] Examples:

[1558] The server is set to the highest security level for data including employees' personal information, and is only accessible to specific users.

[1559] 6. Generate Reports

[1560] The server then compiles a report summarizing the results of the process, including the organization of the data, its value score, and security settings.

[1561] Examples:

[1562] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[1563] Terminal and user processing

[1564] 1. Providing an interface

[1565] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[1566] Examples:

[1567] The device allows users to view data collation results and reports in real time through a web dashboard.

[1568] 2. User operations and instructions

[1569] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[1570] Examples:

[1571] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[1572] In this way, a system that provides a series of functions for efficiently organizing and effectively utilizing the big data held by companies will be realized, maximizing the value of data and helping to improve the efficiency and reduce costs of data management.

[1573] The processing flow will be explained below.

[1574] Step 1:

[1575] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[1576] Step 2:

[1577] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[1578] Step 3:

[1579] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[1580] Step 4:

[1581] The server analyzes the stored data using natural language processing (NLP) technology, analyzing the meaning and sentiment of the text data and automatically tagging it.

[1582] Step 5:

[1583] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[1584] Step 6:

[1585] The server organizes the data, eliminating unnecessary data, combining related information, exchanging some information into other formats, and converting it into a simpler structure.

[1586] Step 7:

[1587] The server evaluates each data entry and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[1588] Step 8:

[1589] The server assigns an appropriate security level to each piece of data based on the evaluation results, and implements access control according to the assigned security level.

[1590] Step 9:

[1591] The server compiles the organized data and its evaluation results and generates a report that includes the data organization status, value score, security settings, and more.

[1592] Step 10:

[1593] The server provides the generated report to the user, for example by emailing it or uploading it to a dashboard.

[1594] Step 11:

[1595] The device provides an interface where users can view reports and data, with the ability to drill down into the data and utilize filters and search capabilities.

[1596] Step 12:

[1597] Users can search for data and check the evaluation results via their terminal, and if necessary, give instructions for additional operations or reorganization, enabling further utilization of the data.

[1598] Through these steps, corporate data can be efficiently organized, utilized to the fullest extent, and protected with appropriate security.

[1599] Example 1

[1600] 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."

[1601] Companies possess a large amount of big data, but they need methods to efficiently organize and utilize that data. In particular, they face challenges in integrating and analyzing data collected from a wide variety of sources, assessing its value, and managing it safely.

[1602] 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.

[1603] In this invention, the server includes means for acquiring information, means for analyzing the acquired information using natural language processing and automatically tagging it, means for organizing the acquired information from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the information and generating an information value score, means for assessing the confidentiality of the information and setting an appropriate security level, means for generating and providing a report of the organized information and its evaluation results, and means for providing this information and report to users and providing an interface for accepting user instructions.This makes it possible to efficiently organize big data held by companies, maximize its value, and utilize it safely and effectively.

[1604] "Information" refers to all data obtained from various data sources across the enterprise.

[1605] "Natural language processing" is a general term for techniques and algorithms that enable computers to understand, interpret, and generate human language.

[1606] "Auto-tagging" refers to the process of automatically analyzing the content of collected data and assigning relevant keywords and categories.

[1607] "Exclusion" refers to the act of removing unnecessary information from data.

[1608] "Combining" refers to the act of unifying and integrating different data sets or data items.

[1609] "Exchange" refers to the act of replacing part of a piece of data with other data.

[1610] "Simplification" refers to the act of removing unnecessary parts and simplifying the data structure in order to convert data into a more manageable form.

[1611] The "information value score" is an evaluation value calculated based on the usability, frequency, substitutability, versatility, and impact of information.

[1612] "Confidentiality" refers to the security property that prevents information from being accessed or disclosed unauthorizedly.

[1613] "Security level" is a standard that indicates the strength of security management, set according to the confidentiality and importance of data.

[1614] A "report" is a written or electronic file that compiles organized information and the results of its evaluation.

[1615] "Interface" refers to the user interface through which users access the system and perform operations and give instructions.

[1616] This invention is a system for efficiently organizing and effectively utilizing big data held by companies. The system is mainly composed of servers, terminals, and users, and by clearly defining the roles of each component, it achieves data acquisition, analysis, organization, evaluation, and utilization.

[1617] Server processing

[1618] 1. Importing data

[1619] The server collects data from various company data sources, utilizing databases, file systems, cloud storage, APIs, etc. For example, the server retrieves data from the company's customer relationship management system (CRM) and enterprise resource planning system (ERP) and imports it into a local database (e.g., MySQL, PostgreSQL). It also collects feedback data from social media accounts via APIs and stores it in the same way.

[1620] Examples:

[1621] The server retrieves customer data from the CRM system and imports it into a local database, and also retrieves feedback data from the company's social media accounts via API and stores it as well.

[1622] 2. Text analysis and automatic tagging

[1623] The server analyzes the collected data using natural language processing (NLP) techniques. Specifically, it uses generative AI models (e.g., GPT-3, BERT) to analyze the meaning of the data and automatically assign relevant tags, making it easier to search and categorize the data.

[1624] Examples:

[1625] The server analyzes the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[1626] 3. ECRS Data Collection

[1627] The server organizes the collected data in terms of elimination, combination, exchange, and simplification. By eliminating unnecessary data and combining related data, the data set is effectively simplified. Also, by simplifying the structure, it becomes easier to access.

[1628] Examples:

[1629] The server removes duplicate customer information, consolidates purchase history data and feedback data, and removes unnecessary data fields to generate a simpler table.

[1630] 4. Assessing Data Value

[1631] The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact. This score is quantified and serves as an evaluation standard for the importance of the data.

[1632] Examples:

[1633] The server calculates a score based on the product review data, such as the number of monthly views and the level of detail in the reviews, to assess the value of each product.

[1634] 5. Setting the security level

[1635] The server sets an appropriate security level based on the content and importance of the data, thereby implementing strict access control for highly confidential data.

[1636] Examples:

[1637] The server is set to the highest security level for data including employees' personal information and is only accessible to specific users.

[1638] 6. Generate Reports

[1639] The server then compiles a report summarizing the results of the process, including information on how the data is organized, its value score, and security settings.

[1640] Examples:

[1641] The server generates a report detailing the data summary, ECRS sorting results, data value score, and security level, and provides it to the user.

[1642] Terminal and user processing

[1643] 1. Providing an interface

[1644] The terminal provides an interface for users to view data and reports, which can be implemented as a web or mobile application.

[1645] Examples:

[1646] The device allows users to view data collation results and reports in real time through a web dashboard.

[1647] 2. User operations and instructions

[1648] Users can search, evaluate, and reorganize data through their terminals, allowing them to reevaluate and analyze the data in detail as needed.

[1649] Examples:

[1650] From the web dashboard, users can apply specific filters, direct further data analysis, or request new data imports.

[1651] Prompt Sentence Examples

[1652] Examples:

[1653] "Generate a report showing the results of an analysis of the company's customer data. Include, among other things, the percentage of positive and negative feedback, a rating score by product, and a data value score."

[1654] This system allows companies to efficiently organize their big data and maximize its value, while also improving the efficiency and reducing costs of data management.

[1655] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1656] Step 1: Collect data

[1657] More specifically: The server collects data from various data sources within the enterprise.

[1658] Inputs: Data sources such as CRM systems, ERP systems, social media accounts, etc.

[1659] Data processing / calculation: The server retrieves data from these data sources using APIs or SQL queries.

[1660] Output: Raw data collected in a local database

[1661] What it does: The server periodically sends API requests to retrieve the latest customer data and feedback data, and retrieves various data from the database using SQL queries and stores them in a local database.

[1662] Step 2: Extract text data

[1663] Specifically: The server extracts text data from the stored database.

[1664] Input: Raw data stored in a local database

[1665] Data processing / calculation: The server runs a SELECT query to extract the required text fields from the database.

[1666] Output: Extracted text data

[1667] Specific operation: The server uses a SELECT statement to retrieve the text field from the feedback table and build a dataset for analysis.

[1668] Step 3: Natural Language Processing and Auto-Tagging

[1669] Specific explanation: The server analyzes the extracted text data using natural language processing (NLP) technology and performs automatic tagging.

[1670] Input: Extracted text data

[1671] Data processing / calculation: Input text data into a generative AI model (e.g., GPT-3, BERT) to obtain analysis results. Based on the analysis results, relevant tags are added.

[1672] Output: A tagged dataset

[1673] Specific operation: The server inputs text data into the generative AI model and updates the tag information in the database based on the analysis results output by the model.

[1674] Step 4: ECRS Data Cleanup

[1675] Specifically: The server organizes the collected and analyzed data in terms of eliminating, combining, exchanging, and simplifying it.

[1676] Input: tagged dataset

[1677] Data processing / calculation: The server removes duplicate data, combines related data, and simplifies by eliminating unnecessary data.

[1678] Output: A cleaned dataset

[1679] Specific operation: The server deletes duplicate records in the database using a DELETE statement, joins the purchase history data and feedback data using a JOIN query, and removes unnecessary data fields to create a simple table.

[1680] Step 5: Assessing the value of your data

[1681] Specific explanation: The server generates a data value score for the organized data based on its usability, frequency, substitutability, versatility, and impact.

[1682] Input: A cleaned dataset

[1683] Data processing / calculation: Data is evaluated using a formula that calculates a score based on criteria such as usability and frequency, and a value score is generated.

[1684] Output: Data Value Score

[1685] Specific operation: The server executes the function based on the above criteria to calculate a score for each data value, and stores the calculated score in the database.

[1686] Step 6: Set the security level

[1687] Specifically: The server sets an appropriate security level based on the content and importance of the data.

[1688] Input: A curated dataset and its value scores

[1689] Data processing / calculation: Set access control on data based on sensitivity.

[1690] Output: A dataset with security levels set

[1691] What happens: The server uses NLP algorithms to analyze the data content, assigns security tags, and updates the ACL (Access Control List) to set the appropriate security level.

[1692] Step 7: Generate reports

[1693] Detailed explanation: The server summarizes the results of the above processing in a report.

[1694] Input: Dataset with security level

[1695] Data processing / calculation: Report generation algorithms are used to compile summaries of data organization, value scores, security settings, etc.

[1696] Output: Generated report

[1697] Specific operation: The server executes database queries to aggregate various data, generates reports in PDF or HTML format, and delivers the reports to the user via email.

[1698] This will enable companies to efficiently organize the big data they hold, maximizing its value, and utilizing it safely and effectively.

[1699] (Application example 1)

[1700] 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."

[1701] Currently, many companies possess vast amounts of data, but it is difficult to efficiently organize that data and extract valuable information. Logistics centers, in particular, require real-time, reliable information for inventory management and delivery planning. Furthermore, the lack of a system that can assess data value and generate appropriate reports while ensuring data confidentiality makes it difficult to simultaneously achieve both logistics efficiency and data security. Therefore, there is a need for a method to achieve efficient data management and value assessment in logistics centers.

[1702] 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.

[1703] In this invention, the server includes means for acquiring data, means for text analysis of the acquired data and automatic tagging, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for assessing the confidentiality of the data and setting an appropriate security level, means for generating and providing a report of the organized data and its evaluation results, means for providing this data and report to a user and providing an interface for accepting user instructions, means for collecting logistics management information and evaluating the utilization rate, sales volume, and supply risk of each item, and means for generating a report showing inventory status and delivery risk based on the evaluated information, thereby enabling efficient data management and value assessment at a logistics center.

[1704] "Data acquisition means" is a function for collecting necessary data from a specific data source.

[1705] "Text analysis means" refers to a technique for interpreting collected data using natural language processing technology and analyzing its meaning.

[1706] "Automatic tagging means" is a function that automatically assigns appropriate tags to analyzed data, making it easier to classify and search the data.

[1707] "Data reduction methods" are methods for optimizing collected data in terms of eliminating, combining, exchanging, and simplifying it.

[1708] "Data value assessment means" is a function for evaluating the usability, frequency, substitutability, versatility, and impact of data, and generating a data value score.

[1709] "Security setting means" is a means for diagnosing the confidentiality of data and setting an appropriate security level.

[1710] The "report generation means" is a function for creating a report based on the organized data and its evaluation results and providing it to the user.

[1711] The "interface providing means" refers to means including a screen and an input device for providing data and reports to a user and receiving instructions from the user.

[1712] The "logistics management information collection means" is a function for collecting information related to inventory and delivery at the logistics center.

[1713] The "utilization rate evaluation means" is a means for evaluating the utilization rate and inventory trends of each item.

[1714] The "sales number evaluation means" is a means for evaluating the sales number of each item and recording it as data.

[1715] The "supply risk assessment means" is a function for assessing potential risks in the supply of each item.

[1716] The "inventory status report generating means" is a function that generates a report showing the inventory status and delivery risk at the logistics center.

[1717] The system embodying the present invention provides functions for efficient data management and value assessment in a logistics center. Specific embodiments will be described below.

[1718] Server processing

[1719] 1. Data Collection Methods

[1720] The server retrieves data from the inventory management system at the logistics center using cloud storage, API interfaces (Flask, Django), etc. For example, product inventory status data is extracted from the inventory management system and stored in a database on the cloud.

[1721] 2. Text Analysis Methods

[1722] The server analyzes the collected data using natural language processing technology (NLTK, spaCy). This allows product descriptions and historical data to be interpreted. The analyzed data is automatically tagged with tags such as "low stock" or "high demand."

[1723] 3. Data organization methods

[1724] The server optimizes the collected data in terms of deduplication, data integration, data exchange, and data simplification. This allows for efficient management of ongoing order information and supply data. For example, information from different warehouses for the same product can be combined and managed as a single data set.

[1725] 4. Data Value Assessment Methods

[1726] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score. Scikit-learn is used for the evaluation, and product availability and supply risk are displayed numerically. For example, the server calculates a score for Product A, such as availability of 70%, sales volume of 500, and supply risk of 20%.

[1727] 5. Security Configuration Methods

[1728] The server assesses the confidentiality of the data and sets an appropriate security level using AWS IAM and OAuth 2.0. For example, a high security level is set for personal customer data, allowing only specific users to access it.

[1729] 6. Report Generation Methods

[1730] The server creates reports based on the organized data and its evaluation results and provides them to users. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[1731] Terminal and user processing

[1732] 1. Means of providing interface

[1733] The terminal is implemented as a web or mobile application and provides an interface for users to view data and reports, for example, allowing users to check inventory status and evaluation results in real time through a web dashboard.

[1734] 2. User operations and instructions

[1735] Through the device, users can search, evaluate, and reorganize data, for example by filtering the availability of specific products or by requesting the import of new data.

[1736] Specific examples

[1737] For example, the system acquires inventory management data from a logistics center, evaluates the utilization rate, sales volume, and supply risk for each product, and generates a score based on the results. It also uses this data to create reports showing inventory status and delay risks.

[1738] Example prompts for generative AI models

[1739] Prompt: Obtain inventory management data for a distribution center, evaluate utilization rate, sales volume, and supply risk for each product, and generate a score based on that. Also, use that data to create a report showing stock status and risk of delays.

[1740] In this way, a system is provided that enables efficient data management and value assessment in a logistics center.

[1741] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1742] Step 1: Collect data

[1743] The server retrieves data from the inventory management system of the logistics center. Specifically, it uses cloud storage and API interfaces (Flask, Django) to store information such as the inventory status, shipping history, and receiving history of each item in a cloud database.

[1744] Input: Data from inventory management system

[1745] Output: Inventory status, shipping history, and receiving history data stored in a cloud database

[1746] Step 2: Text analysis and auto-tagging

[1747] The server analyzes the collected data using natural language processing technology (NLTK, spaCy), which interprets the meaning of product descriptions and historical data and automatically assigns relevant tags.

[1748] Input: Data stored in a cloud database

[1749] Output: Analysis results and assigned tags (e.g., "Low stock" or "High demand")

[1750] Step 3: Data organization

[1751] The server optimizes the acquired data in terms of deduplication, data merging, data exchange, and data simplification. For example, data from different warehouses for the same product can be merged and compiled into a single data set.

[1752] Input: tagged data

[1753] Output: Optimized dataset

[1754] Step 4: Data Value Assessment

[1755] The server evaluates the data's usability, frequency, substitutability, versatility, and impact, and generates a data value score using Scikit-learn, which numerically displays the availability rate, sales volume, and supply risk of each item.

[1756] Input: Optimized dataset

[1757] Output: Data value score (e.g., availability 70%, sales volume 500, supply risk 20%)

[1758] Step 5: Security Settings

[1759] The server assesses the confidentiality of the data and sets an appropriate security level using AWS IAM and OAuth 2.0. For example, a high security level is set for data containing customer personal information, allowing only specific users to access it.

[1760] Input: Data Value Score

[1761] Output: A secured dataset

[1762] Step 6: Generate reports

[1763] The server creates reports based on the organized data and its evaluation results and provides them to the user. This process uses Matplotlib and Jinja2. For example, reports such as "This week's inventory status" and "List of products at risk of delay" are automatically generated and notified to the user.

[1764] Input: Secured dataset

[1765] Output: Generated report

[1766] Step 7: Providing an Interface

[1767] The device provides an interface for users to view data and reports through a web or mobile application, and allows users to search, evaluate, and reorganize the data through the interface.

[1768] Input: User instructions and operations

[1769] Output: Search results, evaluation results, reorganized data

[1770] In this way, by going through each step, efficient data management and value assessment can be achieved at the logistics center.

[1771] 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.

[1772] This invention is a system that uses AI technology to efficiently organize and utilize big data held by companies, and also incorporates an emotion engine that recognizes user emotions. This system is composed of a server, a terminal, and a user. Specific embodiments of the system are described below.

[1773] Server processing

[1774] 1. Importing data

[1775] The server accesses various data sources of the company and gathers data, retrieving it via databases, file systems, cloud storage, APIs, etc., and stores it in temporary storage.

[1776] Examples:

[1777] The server retrieves customer data from the company's CRM system and also retrieves feedback data from social media accounts via API.

[1778] 2. Text analysis and automatic tagging

[1779] The server analyzes the collected data using natural language processing (NLP) technology, and automatically assigns tags to the data based on the analysis results, making it easier to search and classify the data.

[1780] Examples:

[1781] The server analyzes the text data of customer feedback and assigns tags such as "positive," "negative," and "product name."

[1782] 3. ECRS Data Collection

[1783] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it: unnecessary data is removed, related information is combined, and some information is converted into other formats.

[1784] Examples:

[1785] The server removes duplicate customer information and consolidates purchase history data and feedback data.

[1786] 4. Assessing Data Value

[1787] The server evaluates the organized data and calculates a data value score based on criteria including usability, frequency, substitutability, versatility, and impact.

[1788] Examples:

[1789] The server calculates a score for product review data based on the number of monthly views and the level of detail in the reviews, and evaluates the value of each product.

[1790] 5. Setting the security level

[1791] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data.

[1792] Examples:

[1793] The server is set to the highest security level for data including employees' personal information, and only allows access by specific users.

[1794] 6. Generate Reports

[1795] The server then compiles a report summarizing the results of the process, including the data organization status, value score, and security settings.

[1796] Examples:

[1797] The server generates a report detailing the entire data, ECRS sorting results, data value score, and security level, and provides it to the user.

[1798] 7. Emotion Engine Processing

[1799] The server uses an emotion engine to analyze user input information, which analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate their emotional state.

[1800] Examples:

[1801] The system evaluates emotions from feedback information entered by the user and the tone of chat messages to determine the user's emotional state.

[1802] 8. Emotional Feedback

[1803] The server adjusts the way the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby providing information that best suits the user's current emotional state.

[1804] Examples:

[1805] If the user judges the feedback information to be positive, effective suggestions are displayed to the user in a positive tone.

[1806] Terminal and user processing

[1807] 1. Providing an interface

[1808] The device provides an interface that allows users to view data and reports, including the ability to view data details and use filters and search functions.

[1809] Examples:

[1810] The device allows users to view data compilation results and reports in real time through a web dashboard.

[1811] 2. User operations and instructions

[1812] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[1813] Examples:

[1814] From the web dashboard, users can apply specific filters, direct detailed data analysis, or request new data imports.

[1815] Through these steps, corporate data can be efficiently organized, utilized to the highest degree, and protected with appropriate security. Furthermore, the emotion engine presents data optimally according to the user's emotional state.

[1816] The processing flow will be explained below.

[1817] Step 1:

[1818] The server accesses various corporate data sources, such as databases, file systems, cloud storage, and APIs, and establishes a connection with the necessary credentials to collect data.

[1819] Step 2:

[1820] The server retrieves data from connected data sources, for example, by executing SQL queries to extract data from a database or by sending API requests to retrieve data from a cloud service.

[1821] Step 3:

[1822] The server stores the acquired data in temporary storage, which aggregates the data for subsequent processing. The storage format is chosen to be efficient for processing, such as JSON or CSV.

[1823] Step 4:

[1824] The server analyzes the stored data using natural language processing (NLP) technology, specifically analyzing the text information within the data to extract meaning and sentiment.

[1825] Step 5:

[1826] The server automatically tags the data based on the analysis results. For example, it assigns tags such as "positive," "negative," and "product name" to text data of customer feedback.

[1827] Step 6:

[1828] The server organizes the data in terms of ECRS (Eliminate, Combine, Exchange, Simplify), which eliminates redundancies in the dataset and integrates relevant information.

[1829] Step 7:

[1830] The server evaluates each data entry and calculates a data value score, based on criteria such as frequency of use and impact on profits.

[1831] Step 8:

[1832] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby realizing access control according to the confidentiality of the data.

[1833] Step 9:

[1834] The server generates a report based on the organized data and the evaluation results, including the data organization status, value score for each data entry, and security level.

[1835] Step 10:

[1836] The server provides the generated report to the user, either by emailing it or uploading it to a web dashboard.

[1837] Step 11:

[1838] The server analyzes the user's input information using an emotion engine, which evaluates the user's emotional state in real time.

[1839] Step 12:

[1840] The device will adjust how it displays data based on the user's emotional state: for example, if the user is feeling stressed, it will prioritize displaying concise, easy-to-understand information.

[1841] Step 13:

[1842] The terminal provides an interface for viewing data and reports, with filters and search capabilities to make it easier for users to find the information they need.

[1843] Step 14:

[1844] Users can search, evaluate, and reorganize data via their devices. Furthermore, they can refer to the results of the emotion engine to further utilize the data.

[1845] Through these steps, a company's big data can be efficiently organized and effectively utilized. Furthermore, the emotion engine analyzes the user's emotional state, enabling optimal information to be provided.

[1846] Example 2

[1847] 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."

[1848] Modern companies possess vast amounts of data, but they face challenges in efficiently organizing and utilizing this data. Furthermore, traditional data organization systems do not take into account the user's emotional state and lack means to optimize the user experience.

[1849] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1850] In this invention, the server includes: means for acquiring data; means for analyzing the acquired data using natural language processing and automatically tagging it; means for organizing the acquired data from the perspectives of elimination, combination, exchange, and simplification; means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score; means for assessing the confidentiality of the data and setting an appropriate security level; means for generating and providing the organized data and its evaluation results as a report; means for analyzing the acquired data and user-entered information using an emotion engine and evaluating the user's emotional state; means for adjusting the data display method based on the evaluated emotional state; and means for providing the data and report to the user and for providing an interface for accepting user instructions. This makes it possible to efficiently organize the vast amount of data held by a company and present optimal data according to the user's emotional state.

[1851] "Means of acquiring data" refers to the methods and technologies used to collect data from various data sources held by the company and store it in temporary storage.

[1852] "Natural language processing" refers to the techniques and methods that allow computers to understand, interpret, and generate human language.

[1853] "Text analysis" is the process of analyzing textual information using natural language processing technology and extracting meaning and structure from its content.

[1854] "Auto-tagging" is the process of automatically assigning relevant keywords and categories to data based on the results of text analysis.

[1855] "Means of organizing in terms of elimination, combination, exchange, and simplification" refers to techniques and methods for eliminating data duplication, combining related information, exchanging data formats as necessary, and simplifying and organizing data.

[1856] The "data value score" is a score calculated based on evaluation criteria such as the data's usability, frequency, substitutability, versatility, and impact.

[1857] "Means for diagnosing confidentiality and setting an appropriate security level" refers to techniques and methods for determining whether data contains confidential information and applying security measures as necessary.

[1858] The "means for generating and providing a report" refers to a technique and method for creating a report summarizing the organized data and its evaluation results and providing it to the user.

[1859] An "emotion engine" is a system and technology that analyzes a user's input information (key input, voice, facial expression, etc.) and evaluates their emotional state.

[1860] The "means for providing an interface" refers to the technology and method for providing a user interface that allows a user to view data and reports and to perform operations and give instructions.

[1861] This invention is a utilization system that uses AI technology to efficiently organize big data held by companies and incorporates an emotion engine that recognizes user emotions. This system is mainly composed of a server, a terminal, and a user. Detailed embodiments of the system are described below.

[1862] Server embodiment

[1863] 1. Importing data

[1864] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect data, which is then stored in temporary storage.

[1865] Example: A server makes an API call to retrieve customer data from a CRM system and temporarily stores that data.

[1866] 2. Text analysis and automatic tagging

[1867] The server uses natural language processing (NLP) technology to analyze the collected data and automatically assigns tags to the data based on the results. This is done using a Python NLP library (such as spaCy or nltk).

[1868] Example: The server analyzes the text of customer feedback and assigns tags such as "positive," "negative," and "product name."

[1869] 3. ECRS Data Collection

[1870] The server organizes the data using methods such as eliminating, combining, exchanging, and simplifying, using SQL queries and other database management tools.

[1871] Example: The server removes duplicate customer information and combines purchase history and feedback data.

[1872] 4. Assessing Data Value

[1873] The server calculates a value score for the organized data based on evaluation criteria, including usability, frequency, substitutability, versatility, and impact.

[1874] Example: The server calculates a score based on the number of monthly views and the detail of the reviews, and records this in a database.

[1875] 5. Setting the security level

[1876] The server assesses the sensitivity of the data and sets an appropriate security level using data classification tools (e.g., Apache Ranger).

[1877] Example: The server is set to the highest security level for data including employee personal information, and only specific users can access it.

[1878] 6. Generate Reports

[1879] The server then compiles the organized data and evaluation results into a report that summarizes the results. This report is generated in PDF format and provided to the user.

[1880] Example: The server generates a PDF report containing a summary of the data, a value score, and a security level and sends it to the user's email address.

[1881] 7. Emotion Engine Processing

[1882] The server analyzes the user's input (keystrokes, voice, facial expressions, etc.) to assess their emotional state in real time, using the Google Cloud Speech-to-Text API for voice input analysis.

[1883] Example: The server assesses the user's emotional state based on feedback information and the tone of their chat messages.

[1884] 8. Emotional Feedback

[1885] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, dynamically updating the interface using React.js.

[1886] Example: If a user judges the feedback information to be positive, provide them with effective suggestions in a positive tone.

[1887] Terminal embodiment

[1888] 1. Providing an interface

[1889] The terminal provides an interface where users can view data and reports, using a web dashboard powered by React.js.

[1890] Example: The device allows users to view data compilation results and reports in real time through a web dashboard.

[1891] 2. User operations and instructions

[1892] The user can then use their device to search, evaluate, and reorganize the data, optionally using additional information based on the results of the emotion engine.

[1893] Example: A user uses the filter feature in a web dashboard to select a specific data set and request detailed data analysis.

[1894] Example: Example of a prompt sentence to input to a generative AI model

[1895] 1. Prompt for further analysis of positive feedback

[1896] "Perform detailed analysis of positive customer feedback and generate reports with relevant product information."

[1897] 2. Prompt to import new data from a specific data source

[1898] "Import the latest customer feedback data from your social media accounts, then perform text analysis and tagging."

[1899] 3. Prompts that display recommendations based on the sentiment assessment results

[1900] "If the user's emotional state is positive, show them the latest product recommendations."

[1901] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1902] Step 1: Import data

[1903] The server accesses various data sources of the company (databases, file systems, cloud storage, APIs, etc.) to collect the required data. This processing step involves retrieving the data from the data sources and storing it in temporary storage.

[1904] Input: Acquiring target data through API calls or database queries

[1905] Data processing: Analyzes response data from APIs and query results, and converts formats

[1906] Output: The converted data is saved in temporary storage.

[1907] Specific operation: The server uses the API to access the CRM system, retrieve customer data, convert it to JSON format, and save it in storage.

[1908] Step 2: Text analysis and auto-tagging

[1909] The server analyzes the collected data using natural language processing (NLP) technology and automatically assigns tags to the data based on the analysis results. This process involves semantic analysis and tagging of text data.

[1910] Input: Text data stored in temporary storage

[1911] Data processing: Perform text and semantic analysis using NLP techniques (e.g., spaCy or nltk) to extract specific keywords and categories.

[1912] Output: Data tagged based on the analysis results

[1913] Specific operation: The server uses Python's nltk library to analyze the text data of customer feedback and automatically assigns tags such as "positive," "negative," and "product name."

[1914] Step 3: ECRS Data Cleanup

[1915] The server organizes the collected and tagged data in terms of elimination, combination, exchange, and simplification, a process that includes removing unnecessary data and converting data formats.

[1916] Input: tagged data

[1917] Data processing: Deleting duplicate data, merging related data, converting some data formats, deleting unnecessary data

[1918] Output: Organized and consolidated data

[1919] What happens: The server uses SQL queries to remove duplicate customer information and combines purchase history data with feedback data.

[1920] Step 4: Assessing the value of your data

[1921] The server evaluates the organized data and calculates a data value score. In this step, scoring is based on multiple evaluation criteria.

[1922] Input: Organized and consolidated data

[1923] Data processing: Calculate a score based on the evaluation criteria of usability, frequency, substitutability, versatility, and impact.

[1924] Output: Dataset with data value scores

[1925] Specific operation: The server uses an algorithm to calculate a score for product review data based on the number of monthly views and the detail level of the review, and records this in a database.

[1926] Step 5: Set the security level

[1927] The server assesses the confidentiality of the data and sets an appropriate security level, which ensures strict access control for important data.

[1928] Input: Organized and scored data

[1929] Data processing: Use data classification tools to identify sensitive information and set appropriate security levels

[1930] Output: A dataset with security levels set

[1931] Specific operation: The server uses Apache Ranger to set the highest security for data including employee personal information and control it so that only specific users can access it.

[1932] Step 6: Generate reports

[1933] The server creates a report based on the organized data and its evaluation results and provides it to the user. This process includes summarizing the results and creating a report.

[1934] Input: Organized and secured data

[1935] Data processing: Data summaries, value scores, and security levels are compiled and converted into report formats such as PDF.

[1936] Output: Report provided to the user

[1937] Specific operation: The server generates a PDF report detailing the entire data, ECRS sorting results, data value score, and security level, and sends it to the user's email address.

[1938] Step 7: Emotion Engine Processing

[1939] The server analyzes the user's input information (keystrokes, voice, facial expressions, etc.) and evaluates the user's emotional state in real time. An emotion analysis engine is used in this step.

[1940] Input: Real-time user input information (text, voice, facial expressions)

[1941] Data processing: Using emotion analysis technology, we evaluate the user's emotional state from input information.

[1942] Output: Evaluated user emotional state data

[1943] How it works: The server analyzes the voice data using the Google Cloud Speech-to-Text API and evaluates the user's emotions in real time.

[1944] Step 8: Emotional Feedback

[1945] The server adjusts how the data is displayed based on the user's emotional state as assessed by the emotion engine, thereby improving the user experience.

[1946] Input: User's emotional state data as assessed by the emotion engine

[1947] Data manipulation: Adjusting interface content based on the user's emotional state

[1948] Output: The adapted interface presented to the user

[1949] How it works: The server dynamically updates the interface using React.js, displaying positive tone suggestions to users in a positive emotional state.

[1950] (Application example 2)

[1951] 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."

[1952] Conventional big data management systems focused on efficiently organizing and utilizing data, but it was difficult to understand user emotions and provide optimal suggestions and information based on those emotions. Furthermore, online shopping sites are seeking to improve the user experience, necessitating greater personalization. To address this, technology is needed that can analyze user emotions and use them to suggest products and provide services.

[1953] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data, means for text analysis and automatic tagging of the acquired data, means for organizing the acquired data from the perspectives of elimination, combination, replacement, and simplification, means for evaluating the usability, frequency, substitutability, versatility, and impact of the data and generating a data value score, means for diagnosing the confidentiality of the data and setting an appropriate security level, means for generating and providing the organized data and its evaluation results as a report, means for recognizing user emotions, means for adjusting the information display method and product proposals based on the user's emotional state, and means for providing this data and report to the user and providing an interface that accepts user instructions. This makes it possible to provide optimal product proposals and information based on the user's emotions.

[1954] A "data acquisition means" is a system or method for collecting and temporarily storing data from various data sources.

[1955] "Means for text analysis and automatic tagging" refers to a system or method that uses natural language processing technology to analyze acquired text data and automatically assign relevant tags.

[1956] "Means of organizing in terms of elimination, combination, replacement, and simplification" refers to a system or method that eliminates unnecessary parts of data, combines related information, and, if necessary, changes the format to make the whole easier to understand and simplify.

[1957] A "means for generating a data value score" is a system or method that evaluates the usability, frequency, substitutability, versatility, and impact of data, and assigns a score to the data based on these evaluation criteria.

[1958] A "means for diagnosing data confidentiality and setting an appropriate security level" is a system or method that performs a process of thoroughly evaluating the confidentiality of data and setting an appropriate security level based on the results.

[1959] The "means for generating and providing a report" refers to a system or method for generating a report summarizing the organized and evaluated data and providing it to a user.

[1960] "Means for recognizing user emotions" refers to a system or method for analyzing a user's emotional state through user input data or facial recognition.

[1961] "Means for adjusting information display methods and product recommendations based on the user's emotional state" refers to a system or method that changes the content and tone of displayed information, product recommendations, etc., depending on the user's recognized emotions.

[1962] A "means for providing an interface" is a system or method that provides a user interface for a user to view and provide instructions for data and reports.

[1963] MODE FOR CARRYING OUT THE INVENTION

[1964] This invention is a system that uses AI technology to efficiently organize and utilize big data and recognize user emotions. Below, we will explain how to specifically implement this system.

[1965] Server processing

[1966] 1. Importing data

[1967] The server accesses the company's data sources and retrieves data using means such as databases, file systems, cloud storage, and APIs, and stores it in temporary storage. For example, it retrieves customer data from a CRM system and feedback data from social media accounts via APIs.

[1968] 2. Text analysis and automatic tagging

[1969] The server analyzes the acquired data using natural language processing (NLP) technology and automatically assigns tags. For example, it analyzes customer feedback text and assigns tags such as "positive," "negative," and "product name."

[1970] 3. ECRS Data Collection

[1971] The server organizes the data in terms of eliminating, combining, exchanging, and simplifying it. It removes unnecessary data, combines related information, and converts some information into other formats. For example, it removes duplicate customer information and combines purchase history data and feedback data.

[1972] 4. Generating a Data Value Score

[1973] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the level of detail of the reviews, and the value of each product is assessed.

[1974] 5. Setting the security level

[1975] The server diagnoses the confidentiality of the data and sets an appropriate security level, thereby implementing strict access control for highly confidential data. For example, data containing personal information of employees is set to the highest security level, allowing only specific users to access it.

[1976] 6. Generate Reports

[1977] The server then compiles the results of the above process into a report, which includes the data organization status, value score, and security settings. For example, a report detailing the entire data, ECRS organization results, data value score, and security level can be generated and provided to the user.

[1978] 7. Emotion Engine Processing

[1979] The server uses an emotion engine to analyze user input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state.

[1980] 8. Emotional Feedback

[1981] The server adjusts the way data is displayed and product suggestions are made based on the user's emotional state as assessed by the emotion engine. For example, if a user's feedback information is judged to be positive, the server will display effective suggestions in a positive tone to the user.

[1982] Hardware and software used

[1983] Hardware:

[1984] Server: Data analysis and storage

[1985] Smartphone: User emotion analysis and interface provision

[1986] Camera: Emotion Analysis with Facial Recognition

[1987] software:

[1988] Natural Language Processing (NLP): Text analysis and tagging (e.g., Google Cloud Natural Language API)

[1989] Machine learning models: emotion engines (e.g., OpenAI's GPT-3, Amazon Rekognition)

[1990] Database: Data integration and management (e.g., MySQL, PostgreSQL)

[1991] Specific examples

[1992] For example, if a user enters negative feedback such as "I don't know how to use this product," the emotion engine analyzes the content and recommends easy-to-understand how-to videos or FAQ sections. Also, if a user smiles through their smartphone camera, the emotion engine detects positive emotions and notifies the user of new products or exclusive coupons.

[1993] Example prompts to input to a generative AI model:

[1994] The user typed "I don't know how to use this product." The sentiment engine analyzed this feedback and determined the negative sentiment. Think about the best suggestion to make the user interested in reading more. Possible actions could be to provide a link to a how-to video or a guide to the FAQ section.

[1995] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1996] Step 1:

[1997] Importing Data

[1998] The server accesses various data sources within the company to retrieve the required data. Specifically, data is retrieved via databases, file systems, cloud storage, APIs, etc., and then stored in temporary storage. For example, customer data may be retrieved from a company's CRM system, and feedback data may be retrieved from social media accounts via APIs. The input is the data source, and the output is the raw data stored in temporary storage.

[1999] Step 2:

[2000] Text analysis and auto-tagging

[2001] The server uses natural language processing (NLP) technology to perform text analysis on the data stored in temporary storage and automatically assign tags. For example, it analyzes customer feedback text and assigns tags such as positive, negative, and product names. The input is raw text data, and the output is the analyzed results and the associated tags. Specifically, it uses an NLP model (e.g., Google Cloud Natural Language API) to analyze the text and assign relevant tags.

[2002] Step 3:

[2003] ECRS data organization

[2004] The server organizes the analyzed data in terms of eliminating, combining, exchanging, and simplifying. It removes duplicate data, combines related information, and changes the data format as needed. For example, it removes duplicate customer information and combines purchase history data and feedback data. The input is tagged data, and the output is organized data. Specific operations include filtering and integrating data using database operations (e.g., MySQL).

[2005] Step 4:

[2006] Generating a Data Value Score

[2007] The server evaluates the organized data and calculates a data value score. Evaluation criteria include usability, frequency, substitutability, versatility, and impact. For example, for product review data, a score is calculated based on the number of monthly views and the detail of the reviews, and the value of each product is evaluated. The input is the organized data, and the output is a data value score. Specifically, a numerical analysis algorithm is used to calculate a score based on each evaluation criterion.

[2008] Step 5:

[2009] Security Level Settings

[2010] The server assesses the confidentiality of the data and sets an appropriate security level. For example, it sets the highest security level for data containing personal employee information, allowing only specific users to access it. The input is the data value score and organized data, and the output is the set security level. Specifically, it sets appropriate access control using a security policy management system (e.g., AWS IAM).

[2011] Step 6:

[2012] Generate reports

[2013] The server compiles the results of the above processing into a report as a summary. The report includes the data organization status, value score, and security settings. For example, a report detailing the overall data, ECRS organization results, data value score, and security level is generated and provided to the user. The input is the result data generated at each stage of the processing, and the output is the completed report. Specifically, the data analysis results are compiled into a report format using document generation software (e.g., LaTeX, Microsoft Office).

[2014] Step 7:

[2015] Emotion engine processing

[2016] The server uses an emotion engine to analyze the user's input information. The emotion engine analyzes the user's keystrokes, voice, facial expressions, etc. in real time to evaluate the user's emotional state. For example, it evaluates emotions from the feedback information and tone of chat messages entered by the user to determine the user's emotional state. The input is the user's real-time data, and the output is the emotion analysis results. Specifically, emotion analysis is performed using a machine learning model (e.g., OpenAI GPT-3, Amazon Rekognition).

[2017] Step 8:

[2018] Emotion-based feedback

[2019] The server adjusts how data is displayed and how products are suggested based on the user's emotional state as assessed by the emotion engine. For example, if the user's emotion is judged to be positive, it displays effective product suggestions in a positive tone. The input is the emotion analysis results, and the output is tailored suggestions and information based on that emotion. Specific operations include dynamically changing content using a user interface system (e.g., web dashboard, mobile app).

[2020] This will enable optimal product suggestions and information provision based on the user's emotions.

[2021] 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.

[2022] 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.

[2023] 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 robot 414.

[2024] 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.

[2025] 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.

[2026] 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.

[2027] 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).

[2028] 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.

[2029] 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 "...

Claims

1. A means of obtaining the data; A means of text analysis and automatic tagging of acquired data, A means of organizing the acquired data in terms of elimination, combination, exchange, and simplification; A method for evaluating the usability, frequency, substitutability, versatility, and impact of data and generating a data value score; A means for diagnosing the confidentiality of data and setting an appropriate security level; A means for generating and providing the organized data and its evaluation results as a report; A means of providing this data and reports to users and providing an interface for accepting user instructions. A system including:

2. The system according to claim 1 , further comprising means for performing text analysis of the acquired data using natural language processing and performing automatic tagging.

3. The system according to claim 1, further comprising means for calculating a data value score for each data item, generating the evaluation results as a report for data management, and providing the report to the user.

Images