system

Abstract

Provide a system. 【Solution means】 Database connection means for accessing a plurality of database systems and obtaining necessary data, Data integration means for converting data of different formats and structures into a single unified format, Data analysis means for performing statistical analysis, pattern recognition, etc. based on the collected data and extracting useful information, Generative algorithm means for generating new knowledge and proposals from the analysis results of data using artificial intelligence technology, Intelligent advice generation means for providing appropriate and practical proposals to the user based on the analysis results, Data summary generation means for summarizing the analyzed data and providing it to the user visually or as an overview, User interface providing means for enabling the user to access the system, operate, and view information, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern enterprises, data is generally managed in various forms and locations. In this situation, it is difficult to quickly and accurately obtain information from distributed databases and analyze it in a unified manner. As a result, corporate decision-making may be delayed, or appropriate data utilization may not be possible. In addition, there is also a lack of a mechanism to provide intelligent advice that can immediately connect the data analysis results to decision-making. Therefore, improvements for efficient data management and value creation are required.

Means for Solving the Problems

[0005] This invention provides a system including database connection means, data integration means, data analysis means, generation algorithm means, intelligent advice generation means, data summary generation means, and user interface provision means. This system makes it possible to collect data from databases of different formats and integrate them in real time. Furthermore, it includes a mechanism to analyze data using a generation algorithm, generate intelligent advice based on the analysis results, and provide users with a real-time data summary, thereby supporting rapid decision-making.

[0006] A "database connection means" is an interface for accessing multiple database systems and retrieving necessary data.

[0007] A "data integration tool" is a function that converts data of different formats and structures into a single, unified format, enabling centralized management.

[0008] "Data analysis methods" refer to processes that extract useful information by performing statistical analysis, pattern recognition, and other methods based on collected data.

[0009] A "generative algorithm" is a method that uses artificial intelligence technology to generate new knowledge and suggestions from the results of data analysis.

[0010] An "intelligent advice generation method" is a function that provides appropriate and practical suggestions to the user based on the analysis results.

[0011] A "data summary generation method" is a mechanism for summarizing analyzed data and providing it to the user in a visual or overview format.

[0012] "User interface provision means" refers to an interface that enables users to access, operate, and view information within a system. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention provides a system for efficiently collecting, integrating, and analyzing information from multiple different database systems in modern enterprises. Specific embodiments for carrying out this invention are described below.

[0035] This system has database connection means to access multiple database systems and easily retrieve necessary data. The server establishes connections with relational databases, NoSQL databases, and Vector databases, and all data is seamlessly integrated. In the initial connection stage, authentication information for each database is verified, providing secure access.

[0036] Next, the server utilizes data integration tools to convert data collected in different formats into a unified format. This allows for centralized management of different data formats, facilitating subsequent data analysis. The integrated data is then temporarily stored in a securely managed environment.

[0037] Next, the server uses data analysis tools to perform in-depth analysis on the collected and integrated data. Generative algorithms are employed here, and pattern recognition is performed to detect trends and anomalies within the data. This makes it possible to extract useful insights from the data in real time.

[0038] Furthermore, the server generates intelligent advice based on the analysis results. This intelligent advice generation method allows users to receive practical suggestions to support important business decisions. Examples include inventory optimization based on sales data trends and marketing strategies based on customer data analysis.

[0039] Finally, the server sends the generated data summary to the user's terminal via a user interface. The user can then use the intuitive interface to view the integrated data and explore more detailed data as needed. In particular, if an anomaly is detected, an alert is immediately issued, facilitating rapid response.

[0040] As a concrete example, if a manufacturing company uses this system, the server retrieves product production data, quality control data, and customer feedback data from their respective databases in real time and performs integrated analysis. The user is then provided with suggestions for optimal production plans and specific measures to improve quality, thereby improving the company's production efficiency and quality.

[0041] In this way, the "Smart Data Assistant" according to the present invention will revolutionize how companies utilize data and become a powerful tool for enabling rapid and accurate decision-making.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server begins establishing connections. It uses authentication credentials to establish connections to relational databases, NoSQL databases, and Vector databases for each database. Here, it ensures secure connections by verifying the authentication credentials and confirming access permissions.

[0045] Step 2:

[0046] The server collects the necessary data from multiple databases. It issues appropriate queries to each database to extract information such as sales data, customer information, and product metadata. The collected data is temporarily stored in memory.

[0047] Step 3:

[0048] The server initiates the process of converting collected data into a unified format using data integration means. Different data formats and structures are standardized to facilitate subsequent analysis. This converted data is stored in an integrated data store within a securely managed environment.

[0049] Step 4:

[0050] The server incorporates generation algorithms and begins analyzing the data. Based on the collected and integrated data, analysis is performed using machine learning models. This enables the recognition of data patterns, detection of anomalies, and analysis of trends.

[0051] Step 5:

[0052] The server generates intelligent advice based on the analysis results. This step creates actionable suggestions for the detected trends and anomalies. For example, these may include promotional strategies to increase sales or suggestions for optimizing inventory management.

[0053] Step 6:

[0054] The server organizes the data analysis results and generates a data summary. The summarized data is then visualized in intuitive graphics and text formats, ready to be presented to the user in an easily understandable format.

[0055] Step 7:

[0056] The server sends the generated data summary and intelligent advice to the user's device via the user interface. If a notification or alert is generated, it is immediately sent to the user's device.

[0057] Step 8:

[0058] Users can view the provided data summary through their device and access detailed information as needed. They can also refer to intelligent advice on the interface to aid in decision-making.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] Modern organizations are required to efficiently collect, integrate, and analyze data from multiple different types of databases. However, the introduction of different data formats and analytical tools makes consistent data management and support for rapid decision-making difficult. This reduces the efficiency of data utilization and undermines business competitiveness.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes database access means, heterogeneous data integration means, and data extraction and analysis means. This makes it possible to collect and integrate data from different types of databases in real time. Furthermore, it enables the rapid extraction of useful insights from the data and advanced analysis to support business decision-making.

[0064] "Database access means" refers to the processes and technologies for securely connecting to multiple different databases and collecting data.

[0065] "Heterogeneous data integration means" refers to technologies that collect data of different formats and structures and convert them into a unified format.

[0066] "Data extraction and analysis methods" refer to techniques for extracting necessary information from collected data and analyzing data trends and anomalies.

[0067] "Generative modeling" refers to the process of generating insights from data using AI models and machine learning techniques.

[0068] "Decision-making support advice generation method" refers to technology that generates useful suggestions and guidelines for users based on analysis results.

[0069] "Information visualization and delivery methods" refer to technologies that display data analysis results in a format that users can intuitively understand.

[0070] "User interaction means" refers to the means or interfaces that allow users to interact with a system and access necessary information.

[0071] To implement the invention, the central server of the system is responsible for connecting to multiple databases and collecting data. The server uses database access means to securely connect to different database systems, such as relational databases, NoSQL databases, and Vector databases. In this process, appropriate authentication and connection are performed using SQL, NoSQL APIs, and security software.

[0072] The server integrates collected data using heterogeneous data integration methods and converts it into a unified format. This unifies the data structure and enables efficient data management. ETL tools and data format conversion software are used for data conversion.

[0073] Furthermore, the server mobilizes data extraction and analysis tools and utilizes generative modeling tools to perform data analysis. In this process, AI models and machine learning algorithms are used to detect trends and anomalies from the data and extract insights. Specific software examples include Python's Scikit-learn and TENSORFLOW®.

[0074] Based on the generated analysis results, the server provides suggestions to the user through a decision support advice generation mechanism. This process generates practical advice that the user can immediately use in their work. This enables the user to make important business decisions quickly. To help the user intuitively understand the summary of the collected and analyzed data, the server uses an information visualization mechanism to allow the user to visually view the data on their terminal.

[0075] For example, if a manufacturing company implements this system, the server will collect production data in real time and analyze it in combination with quality control and customer feedback data. Based on this analysis, optimized production schedules and quality improvement measures will be provided.

[0076] An example of a prompt message is: "Analyze trends from manufacturing production data and generate intelligent advice suggesting the optimal production volume for this month."

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server connects to multiple database systems using database access methods. It uses authentication information for each database as input to establish secure connections with relational databases, NoSQL databases, and Vector databases. Specifically, it establishes connections using API keys and authentication tokens and retrieves a list of necessary tables and documents. The output is a list of connected data sources.

[0080] Step 2:

[0081] The server utilizes heterogeneous data integration methods to convert acquired data into a unified format. The input consists of raw data collected from multiple data sources. This data is then integrated using data transformation software to unify its format and data consistency. Specific operations include converting CSV files to JSON and converting data with different schemas to a standard schema. The output is an integrated dataset.

[0082] Step 3:

[0083] The server uses data extraction and analysis tools to perform in-depth analysis of the data. It utilizes an integrated dataset as input. During this process, machine learning models are executed to perform pattern recognition to discover trends and anomalies in the data. Specifically, this involves applying machine learning algorithms using Python's Scikit-learn to analyze trends in time-series data. The output consists of analyzed insights and discovered patterns.

[0084] Step 4:

[0085] The server uses a generative model to generate intelligent advice based on the analysis results. The input is the result of data analysis. Using a generative AI model, it processes suggestions and strategies that users can use for decision-making. Specifically, it uses a natural language generation algorithm to create suggestions based on the analysis results. The output is intelligent advice for the user.

[0086] Step 5:

[0087] The server uses information visualization and delivery means to visualize and deliver the generated intelligent advice and analysis results to the user's terminal. The input consists of the intelligent advice and analysis results. This is then formatted and processed into a format viewable on a web browser. Specific operations include creating graphs and charts using visualization tools and displaying them to the user. The output is a visually easy-to-understand information display.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In today's production environments, there is a need to effectively aggregate diverse data from multiple devices and systems to optimize operations. However, this data generally exists in different formats, making real-time integration and analysis difficult using conventional methods. Furthermore, a lack of real-time intelligent advice to quickly utilize the insights gained is a significant challenge.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes data management means, information integration means, and information analysis means. This enables the collection, integration, and analysis of data from different devices in real time, thereby providing intelligent suggestions for operational optimization in real time.

[0093] "Data management methods" refer to technologies for efficiently organizing data obtained from different sources and storing it in a secure and accessible format.

[0094] "Information integration means" refers to the process and function of converting and integrating data of multiple different forms and structures into a unified format.

[0095] "Information analysis means" refers to computational methods and systems for analyzing collected and integrated data to detect patterns, trends, and anomalies.

[0096] "Generative methods and means" refer to algorithms and processes for generating new insights and proposals from data obtained through information analysis.

[0097] An "intelligent suggestion generation method" is a method for proposing optimal actions and improvement measures to target users or systems based on the results of information analysis.

[0098] An "information aggregation and generation method" is a technique for summarizing analysis results and proposals and providing them in an easily understandable visual or digital format.

[0099] "User interface provision means" refers to technologies and devices that provide an interface that allows users to intuitively receive and manipulate data results and suggestions.

[0100] "Execution means" refers to a method and system for optimizing operations by implementing recommendations generated based on analysis results in a real-world environment.

[0101] This invention is designed as a system to improve factory efficiency. The server acquires data from various devices and sensors and integrates the data using cloud computing technology. Specifically, it accesses the database using Google Cloud Platform and processes the data with programs implemented in Python and Java. Furthermore, it utilizes deep learning libraries such as TensorFlow and PyTorch for data analysis to recognize patterns and optimize productivity.

[0102] The server performs real-time data analysis on aggregated information and generates intelligent suggestions using generation methods based on the results. This allows users to directly check instructions for optimizing operations on their terminals and take appropriate action. The user's terminal implements an intuitive and easy-to-understand user interface, enabling them to quickly find and utilize the necessary information.

[0103] For example, if an anomaly is detected on a production line, that information is immediately sent to the user's terminal. This allows the user to take countermeasures quickly. By inputting a prompt message using the generated AI model, such as "Investigate the cause of the speed reduction observed on a specific production line," it is possible to obtain detailed analysis results to identify the root cause of the problem.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects data from various devices and sensors within the factory. Real-time data from various data points (e.g., temperature, speed, operating time, etc.) is input via the network. This data is temporarily stored using data management systems.

[0107] Step 2:

[0108] The stored data is processed by an information integration mechanism. The server converts data in different formats into a unified format and aggregates it into a database managed on the Google Cloud Platform. Data cleansing and validation are performed during this process, making the data ready for efficient subsequent analysis.

[0109] Step 3:

[0110] After data integration is complete, the server performs in-depth analysis of the data using information analysis tools. The input data is processed by scripts written in Python or Java, and trend analysis and anomaly detection are performed using deep learning models with TensorFlow or PyTorch. As a result, the operational status of the factory is evaluated in detail.

[0111] Step 4:

[0112] Based on the analysis results, the generation method generates intelligent suggestions. The server uses the generation AI model to create recommendations based on the analysis results, which are then formatted by the information aggregation and generation means. Users can use these recommendations to determine operational policies.

[0113] Step 5:

[0114] The user's terminal displays results and suggestions generated through the user interface provisioning means. The terminal provides a concrete operation panel, allowing the user to easily explore information and decide on actions. For example, a prompt message such as "Investigate the cause of the speed reduction observed on a specific production line" may be output, allowing the user to take countermeasures based on detailed analysis results.

[0115] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0116] This invention provides a system that enables more personalized interactions by considering user emotions, in addition to the efficient management and utilization of corporate data. Integrating this emotion recognition function enables more human-like communication and decision-making support.

[0117] This system includes database connection means, data integration means, data analysis means, generation algorithm means, intelligent advice generation means, data summary generation means, and user interface provision means. Furthermore, it is equipped with an emotion engine that recognizes user emotions in real time and provides content and advice accordingly.

[0118] In the initial stage, the server authenticates with various database systems and establishes connections. Next, it retrieves the necessary data, converts different data formats to a unified format, and performs efficient data integration.

[0119] Next, the server performs data analysis. This analysis utilizes generative algorithms to analyze data trends and detect anomalies. Based on the insights gained from the analysis, intelligent advice is then generated for the user.

[0120] In the operation of the emotion engine, the terminal captures the user's voice input and text information, and the server analyzes this information to determine the user's emotional state. The emotion engine uses an emotion analysis algorithm to evaluate the user's emotions in real time.

[0121] To give a concrete example, consider a scenario where a company utilizes this system. The server aggregates and analyzes daily business data. When a user logs into their terminal and views business reports, the emotion engine detects emotions such as excitement or surprise, and displays advice tailored to those emotions. For example, if a user reacts with surprise to the analysis results, the emotion engine might provide additional background information or specific action plans.

[0122] By incorporating an emotion engine in this way, it becomes possible to adapt to the user's emotions and provide more effective and interactive information. This system is expected to dramatically improve not only the company's data utilization but also the user experience.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server attempts to access each database system using authentication credentials, establishing connections to relational databases, NoSQL databases, and Vector databases. At this stage, it verifies the access rights and security of each database to prepare for secure data retrieval.

[0126] Step 2:

[0127] The server retrieves the necessary data from each database. This data includes sales data, customer information, and product-related data. This data is temporarily stored in the server's memory space.

[0128] Step 3:

[0129] The server uses data integration means to convert data in different formats into a single standard format and store it in an integrated data store in order to centralize the integrated data.

[0130] Step 4:

[0131] The server utilizes generation algorithms to analyze integrated data. Here, machine learning is used to detect data trends and anomalies, and future predictions are made to generate information that contributes to corporate decision-making.

[0132] Step 5:

[0133] Based on the information it collects and analyzes, the server uses intelligent advice generation tools to create suggestions. These suggestions include business strategies, inventory management improvement proposals, and marketing campaign optimization.

[0134] Step 6:

[0135] The device captures voice and text input from the user and sends it to the server. The server uses an emotion engine to analyze this input and identify the user's emotional state.

[0136] Step 7:

[0137] The server analyzes the user's emotional information obtained through the emotion engine and adjusts the content and advice presented in the interface based on that analysis. Personalized feedback is provided that is tailored to the user's emotions.

[0138] Step 8:

[0139] Users can view data summaries and intelligent advice sent from the server through their devices. In particular, if a user expresses emotions such as surprise or anxiety, additional information and support are provided to address these concerns, deepening the user's understanding.

[0140] (Example 2)

[0141] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0142] Traditional data management systems have limitations in their ability to integrate and analyze corporate data, making it particularly difficult to improve user experience and provide personalized services. Furthermore, the inability to provide interactive information that takes user emotions into account has made improving user satisfaction a challenge.

[0143] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0144] In this invention, the server includes database connection means, data integration means, and data analysis means. This enables efficient integration and analysis of corporate data, and by utilizing an emotion recognition engine, it becomes possible to provide intelligent advice based on the user's emotions.

[0145] A "database connection means" is a means that provides functions for authenticating and communicating with a database, and for retrieving and writing data.

[0146] A "data integration method" is a means of organizing data obtained from different formats and sources in a unified manner, making it analyzable.

[0147] "Data analysis methods" refer to means of detecting trends and anomalies based on integrated data, using methods such as statistical analysis and machine learning.

[0148] A "generation algorithm means" is a means of executing an algorithm to generate information or predictions that meet specific conditions based on the results of data analysis.

[0149] An "intelligent advice generation method" is a means of automatically generating recommendations and advice to provide to users based on the results of data analysis.

[0150] A "data summary generation method" is a means of summarizing vast amounts of data and providing only the most important information.

[0151] "User interface provision means" refers to means of providing a visual or audio interface for users to interact directly with the system.

[0152] An "emotion recognition engine" is a method that analyzes voice and text information obtained from users to evaluate the user's emotional state in real time.

[0153] A "real-time emotion analysis method" is a means of using an emotion recognition engine to determine a user's emotions in real time and dynamically provide responses and information.

[0154] This system is implemented by combining various technological elements to enhance corporate data management and user interaction. The system's core processing is handled by a server, and it includes database connection, data integration, and data analysis capabilities for efficiently utilizing corporate data.

[0155] The server connects to corporate data using common database management software or open-source database management tools (e.g., MySQL®, PostgreSQL) to integrate with existing database management systems. After retrieving the data, the server uses a data integration engine (e.g., Apache® NiFi) to integrate data in different formats and convert it into an analyzable format.

[0156] In the analysis process, the server executes generation algorithms. The software used for this purpose utilizes data science libraries in Python and R (e.g., Scikit-learn, TensorFlow) to perform trend analysis and anomaly detection. From the resulting insights, intelligent advice is generated and provided to the user.

[0157] Users can view the results of the data analysis and advice provided through the device's user interface. The device also uses an emotion engine to analyze the user's voice input and text data, sending emotional information to the server in real time. Based on this emotional information, the server provides further personalized interactions.

[0158] As a concrete example, when a user views a report related to company travel expenses, the device detects their emotions. If the server detects emotions such as surprise or doubt, it provides additional information and advice on the next course of action based on the results of the emotion engine.

[0159] An example of a prompt using a generative AI model would be: "Please tell me the main trends based on this week's sales data. Please also explain the background and why these trends were surprising."

[0160] In this way, by implementing this system, companies can improve the accuracy of data-driven decision-making and make the user experience more personalized.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The server establishes a connection to the database. This connection involves the server sending authentication information using database client software and receiving a response from the database. User authentication information and database connection information are used as input, and the output is a connection state that allows data retrieval.

[0164] Step 2:

[0165] The server retrieves data through an established connection. The input data retrieved here is often business data from a company, in different formats (e.g., CSV, XML). The server uses a data integration engine to convert this data into a single unified format (e.g., JSON), and the output is an integrated dataset.

[0166] Step 3:

[0167] The server takes the integrated dataset as input and begins data analysis. The server executes generative algorithms to perform data trend analysis and anomaly detection. This analysis utilizes machine learning algorithms to generate data insights and predictive results as output.

[0168] Step 4:

[0169] The server generates intelligent advice based on the analysis results. The analysis results are used as input, and the generating AI model processes them to create output that includes helpful advice and recommendations for the user.

[0170] Step 5:

[0171] The terminal displays advice and analysis results from the server via a user interface. In this process, intelligent advice sent from the server is used as input, and information is provided to the user visually or audibly as output. Specific functions include displaying data in graph format on a dashboard and issuing voice notifications.

[0172] Step 6:

[0173] The device acquires voice input and text information from the user. The user's voice samples and text comments are used as input to evaluate the user's emotions. The device sends this information to a server, where the emotion recognition engine performs real-time emotion analysis.

[0174] Step 7:

[0175] The server dynamically updates content and advice based on the analysis results from the emotion recognition engine. In this step, the output of the emotion analysis is treated as input and output as personalized advice adapted to the user's emotions. Specifically, this includes a function that provides additional information in response to the user's surprise.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0178] Traditional data management systems have the challenge of making it difficult to provide personalized services that take into account the emotional state of users. In particular, in physical stores, there is a need to provide timely information and product recommendations that respond to customers' emotions, but the technology to effectively do this is not yet well established.

[0179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0180] In this invention, the server includes database connection means, data integration means, and emotion recognition means. This makes it possible to analyze customer emotions in real time in physical stores and provide optimized product information and promotions based on that information.

[0181] "Database connection means" refers to technology that has the functionality to connect to various data management systems and retrieve necessary data.

[0182] "Data integration means" refers to technologies for converting data in different formats into a unified format and efficiently aggregating it.

[0183] "Data analysis methods" refer to techniques used to identify trends and detect anomalies using collected data.

[0184] A "generation algorithm" is a technique for generating models that meet specific conditions or objectives in data analysis.

[0185] An "intelligent advice generation method" is a technology that provides appropriate advice to users based on insights gained from data analysis.

[0186] A "data summary generation method" is a technology for providing a summary of data in a format that is easy for users to understand.

[0187] "User interface provisioning means" refers to technologies that provide visual or manipulative means for users to interact with a system.

[0188] "Emotion recognition technology" refers to a technology that analyzes a user's voice and text information to determine their emotional state in real time.

[0189] "Information provision methods based on emotion analysis" refer to technologies that provide users with the most suitable information and content based on the results of emotion recognition.

[0190] In the system that implements this application, a server plays a central role, centrally managing various functions. The system accesses a cloud server via the internet and retrieves data from multiple database systems. User purchase history and sentiment history are collected through the database connection means. Data integration means unify data in different formats and convert it into an analyzable form.

[0191] The data analysis means uses analysis algorithms to perform trend analysis and anomaly detection based on the collected data. The generation algorithm means generates a model based on the analysis results. The intelligent advice generation means creates advice that is appropriate to the user's current emotional state and provides the information in a concise manner.

[0192] On the terminal, emotion recognition means analyze the user's voice input and text data in real time and transmit it to the server. As a result, the server uses emotion analysis-based information provision means to provide appropriate product information and service suggestions that correspond to the user's emotions. The user receives the information through a user interface provision means via a terminal such as a smartphone.

[0193] For example, if a customer shows surprise upon seeing a new product in a store, that information is sent to a server via emotion recognition. The server then quickly provides relevant product information and promotions based on that emotion. As a result, customers can enjoy a personalized shopping experience.

[0194] An example of a prompt using a generative AI model is, "Tell me a new way to tell customers how special this gadget is." This allows the generative AI model to generate effective marketing messages.

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The server uses database connection methods to retrieve customer purchase history and sentiment history from various database systems. Inputs include the necessary databases and query information, and output is integrated customer data. This process involves accessing cloud databases via APIs.

[0198] Step 2:

[0199] The server uses data integration to convert customer data in different formats into a unified format. The input consists of datasets in different formats, and the output is in a unified data format. This conversion process includes data mapping and transformation using scripts.

[0200] Step 3:

[0201] The device uses emotion recognition to capture user voice input and text information and transmit it to the server. The input is real-time voice and text data from the user, and the output is emotion data converted into an analyzable digital format. Voice analysis software is then used to extract the emotional state.

[0202] Step 4:

[0203] The server uses a generation algorithm to perform trend analysis and anomaly detection based on data acquired by the data analysis tool. The input is a unified dataset, and the output is a list of detected trend information and anomalies. This process involves applying statistical algorithms to interpret the data.

[0204] Step 5:

[0205] The server uses emotion analysis-based information delivery methods to generate appropriate advice and product information tailored to the user's emotional state. Input consists of user emotion data and historical trend information, while output is personalized informational content. The process includes the use of AI models for information generation.

[0206] Step 6:

[0207] The user receives and views the generated information on their device via a user interface provisioning mechanism. The input is information content provided by the server, and the output is the application screen displayed to the user's eyes. This process includes UI design that takes usability into consideration.

[0208] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0209] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0210] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0211] [Second Embodiment]

[0212] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0213] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0214] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0215] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0216] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0217] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0218] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0219] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0220] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0221] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0222] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0223] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0224] This invention provides a system for efficiently collecting, integrating, and analyzing information from multiple different database systems in modern enterprises. Specific embodiments for carrying out this invention are described below.

[0225] This system has database connection means to access multiple database systems and easily retrieve necessary data. The server establishes connections with relational databases, NoSQL databases, and Vector databases, and all data is seamlessly integrated. In the initial connection stage, authentication information for each database is verified, providing secure access.

[0226] Next, the server utilizes data integration tools to convert data collected in different formats into a unified format. This allows for centralized management of different data formats, facilitating subsequent data analysis. The integrated data is then temporarily stored in a securely managed environment.

[0227] Next, the server uses data analysis tools to perform in-depth analysis on the collected and integrated data. Generative algorithms are employed here, and pattern recognition is performed to detect trends and anomalies within the data. This makes it possible to extract useful insights from the data in real time.

[0228] Furthermore, the server generates intelligent advice based on the analysis results. This intelligent advice generation method allows users to receive practical suggestions to support important business decisions. Examples include inventory optimization based on sales data trends and marketing strategies based on customer data analysis.

[0229] Finally, the server sends the generated data summary to the user's terminal via a user interface. The user can then use the intuitive interface to view the integrated data and explore more detailed data as needed. In particular, if an anomaly is detected, an alert is immediately issued, facilitating rapid response.

[0230] As a concrete example, if a manufacturing company uses this system, the server retrieves product production data, quality control data, and customer feedback data from their respective databases in real time and performs integrated analysis. The user is then provided with suggestions for optimal production plans and specific measures to improve quality, thereby improving the company's production efficiency and quality.

[0231] In this way, the "Smart Data Assistant" according to the present invention will revolutionize how companies utilize data and become a powerful tool for enabling rapid and accurate decision-making.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The server begins establishing connections. It uses authentication credentials to establish connections to relational databases, NoSQL databases, and Vector databases for each database. Here, it ensures secure connections by verifying the authentication credentials and confirming access permissions.

[0235] Step 2:

[0236] The server collects the necessary data from multiple databases. It issues appropriate queries to each database to extract information such as sales data, customer information, and product metadata. The collected data is temporarily stored in memory.

[0237] Step 3:

[0238] The server initiates the process of converting collected data into a unified format using data integration means. Different data formats and structures are standardized to facilitate subsequent analysis. This converted data is stored in an integrated data store within a securely managed environment.

[0239] Step 4:

[0240] The server incorporates generation algorithms and begins analyzing the data. Based on the collected and integrated data, analysis is performed using machine learning models. This enables the recognition of data patterns, detection of anomalies, and analysis of trends.

[0241] Step 5:

[0242] The server generates intelligent advice based on the analysis results. This step creates actionable suggestions for the detected trends and anomalies. For example, these may include promotional strategies to increase sales or suggestions for optimizing inventory management.

[0243] Step 6:

[0244] The server organizes the data analysis results and generates a data summary. The summarized data is then visualized in intuitive graphics and text formats, ready to be presented to the user in an easily understandable format.

[0245] Step 7:

[0246] The server sends the generated data summary and intelligent advice to the user's device via the user interface. If a notification or alert is generated, it is immediately sent to the user's device.

[0247] Step 8:

[0248] Users can view the provided data summary through their device and access detailed information as needed. They can also refer to intelligent advice on the interface to aid in decision-making.

[0249] (Example 1)

[0250] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0251] Modern organizations are required to efficiently collect, integrate, and analyze data from multiple different types of databases. However, the introduction of different data formats and analytical tools makes consistent data management and support for rapid decision-making difficult. This reduces the efficiency of data utilization and undermines business competitiveness.

[0252] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0253] In this invention, the server includes database access means, heterogeneous data integration means, and data extraction and analysis means. This makes it possible to collect and integrate data from different types of databases in real time. Furthermore, it enables the rapid extraction of useful insights from the data and advanced analysis to support business decision-making.

[0254] "Database access means" refers to the processes and technologies for securely connecting to multiple different databases and collecting data.

[0255] "Heterogeneous data integration means" refers to technologies that collect data of different formats and structures and convert them into a unified format.

[0256] "Data extraction and analysis methods" refer to techniques for extracting necessary information from collected data and analyzing data trends and anomalies.

[0257] "Generative modeling" refers to the process of generating insights from data using AI models and machine learning techniques.

[0258] "Decision-making support advice generation method" refers to technology that generates useful suggestions and guidelines for users based on analysis results.

[0259] "Information visualization and delivery methods" refer to technologies that display data analysis results in a format that users can intuitively understand.

[0260] "User interaction means" refers to the means or interfaces that allow users to interact with a system and access necessary information.

[0261] To implement the invention, the central server of the system is responsible for connecting to multiple databases and collecting data. The server uses database access means to securely connect to different database systems, such as relational databases, NoSQL databases, and Vector databases. In this process, appropriate authentication and connection are performed using SQL, NoSQL APIs, and security software.

[0262] The server integrates collected data using heterogeneous data integration methods and converts it into a unified format. This unifies the data structure and enables efficient data management. ETL tools and data format conversion software are used for data conversion.

[0263] Furthermore, the server mobilizes data extraction and analysis tools and utilizes generative modeling tools to perform data analysis. In this process, AI models and machine learning algorithms are used to detect trends and anomalies from the data and extract insights. Specific software examples include Python's Scikit-learn and TensorFlow.

[0264] Based on the generated analysis results, the server provides suggestions to the user through a decision support advice generation mechanism. This process generates practical advice that the user can immediately use in their work. This enables the user to make important business decisions quickly. To help the user intuitively understand the summary of the collected and analyzed data, the server uses an information visualization mechanism to allow the user to visually view the data on their terminal.

[0265] For example, if a manufacturing company implements this system, the server will collect production data in real time and analyze it in combination with quality control and customer feedback data. Based on this analysis, optimized production schedules and quality improvement measures will be provided.

[0266] An example of a prompt message is: "Analyze trends from manufacturing production data and generate intelligent advice suggesting the optimal production volume for this month."

[0267] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0268] Step 1:

[0269] The server connects to multiple database systems using database access methods. It uses authentication information for each database as input to establish secure connections with relational databases, NoSQL databases, and Vector databases. Specifically, it establishes connections using API keys and authentication tokens and retrieves a list of necessary tables and documents. The output is a list of connected data sources.

[0270] Step 2:

[0271] The server utilizes heterogeneous data integration methods to convert acquired data into a unified format. The input consists of raw data collected from multiple data sources. This data is then integrated using data transformation software to unify its format and data consistency. Specific operations include converting CSV files to JSON and converting data with different schemas to a standard schema. The output is an integrated dataset.

[0272] Step 3:

[0273] The server uses data extraction and analysis tools to perform in-depth analysis of the data. It utilizes an integrated dataset as input. During this process, machine learning models are executed to perform pattern recognition to discover trends and anomalies in the data. Specifically, this involves applying machine learning algorithms using Python's Scikit-learn to analyze trends in time-series data. The output consists of analyzed insights and discovered patterns.

[0274] Step 4:

[0275] The server uses a generative model to generate intelligent advice based on the analysis results. The input is the result of data analysis. Using a generative AI model, it processes suggestions and strategies that users can use for decision-making. Specifically, it uses a natural language generation algorithm to create suggestions based on the analysis results. The output is intelligent advice for the user.

[0276] Step 5:

[0277] The server uses information visualization and delivery means to visualize and deliver the generated intelligent advice and analysis results to the user's terminal. The input consists of the intelligent advice and analysis results. This is then formatted and processed into a format viewable on a web browser. Specific operations include creating graphs and charts using visualization tools and displaying them to the user. The output is a visually easy-to-understand information display.

[0278] (Application Example 1)

[0279] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0280] In today's production environments, there is a need to effectively aggregate diverse data from multiple devices and systems to optimize operations. However, this data generally exists in different formats, making real-time integration and analysis difficult using conventional methods. Furthermore, a lack of real-time intelligent advice to quickly utilize the insights gained is a significant challenge.

[0281] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0282] In this invention, the server includes data management means, information integration means, and information analysis means. By collecting data from different devices in real time, integrating and analyzing it, intelligent proposals for operation optimization can be provided in real time.

[0283] The "data management means" is a technology for efficiently organizing data obtained from different information sources and storing it in a secure and accessible form.

[0284] The "information integration means" is a process and function for converting data of multiple different formats and structures into a unified format and integrating it.

[0285] The "information analysis means" is a calculation method and system for analyzing the collected and integrated data to detect patterns, trends, and anomalies.

[0286] The "generation method means" is an algorithm and process for generating new insights and proposals from the data obtained by information analysis.

[0287] The "intelligent proposal generation means" is a method for proposing optimal actions and improvement measures for the target user or system based on the results of information analysis.

[0288] The "information aggregation generation means" is a method for summarizing analysis results and proposals and providing them in a visually or digitally easy-to-understand form.

[0289] The "user interface providing means" is a technology and device for providing an interface through which users can intuitively receive and operate on data results and proposals.

[0290] The "execution means" is a method and system for executing the recommendations generated based on the analysis results in a real environment to optimize operation.

[0291] This invention is designed as a system to improve factory efficiency. The server acquires data from various devices and sensors and integrates the data using cloud computing technology. Specifically, it accesses the database using Google Cloud Platform and processes the data with programs implemented in Python and Java. Furthermore, it utilizes deep learning libraries such as TensorFlow and PyTorch for data analysis to recognize patterns and optimize productivity.

[0292] The server performs real-time data analysis on aggregated information and generates intelligent suggestions using generation methods based on the results. This allows users to directly check instructions for optimizing operations on their terminals and take appropriate action. The user's terminal implements an intuitive and easy-to-understand user interface, enabling them to quickly find and utilize the necessary information.

[0293] For example, if an anomaly is detected on a production line, that information is immediately sent to the user's terminal. This allows the user to take countermeasures quickly. By inputting a prompt message using the generated AI model, such as "Investigate the cause of the speed reduction observed on a specific production line," it is possible to obtain detailed analysis results to identify the root cause of the problem.

[0294] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0295] Step 1:

[0296] The server collects data from various devices and sensors within the factory. Real-time data from various data points (e.g., temperature, speed, operating time, etc.) is input via the network. This data is temporarily stored using data management systems.

[0297] Step 2:

[0298] The stored data is processed by an information integration mechanism. The server converts data in different formats into a unified format and aggregates it into a database managed on the Google Cloud Platform. Data cleansing and validation are performed during this process, making the data ready for efficient subsequent analysis.

[0299] Step 3:

[0300] After data integration is complete, the server performs in-depth analysis of the data using information analysis tools. The input data is processed by scripts written in Python or Java, and trend analysis and anomaly detection are performed using deep learning models with TensorFlow or PyTorch. As a result, the operational status of the factory is evaluated in detail.

[0301] Step 4:

[0302] Based on the analysis results, the generation method generates intelligent suggestions. The server uses the generation AI model to create recommendations based on the analysis results, which are then formatted by the information aggregation and generation means. Users can use these recommendations to determine operational policies.

[0303] Step 5:

[0304] The user's terminal displays results and suggestions generated through the user interface provisioning means. The terminal provides a concrete operation panel, allowing the user to easily explore information and decide on actions. For example, a prompt message such as "Investigate the cause of the speed reduction observed on a specific production line" may be output, allowing the user to take countermeasures based on detailed analysis results.

[0305] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0306] In addition to the efficient management and utilization of corporate data, the present invention provides a system that realizes more personalized interactions by considering the emotions of users. By integrating this emotion recognition function, more human-like communication and decision-making support become possible.

[0307] This system is equipped with database connection means, data integration means, data analysis means, generation algorithm means, intelligent advice generation means, data summary generation means, and user interface provision means. Furthermore, it is equipped with an emotion engine for recognizing the emotions of users in real time and providing corresponding content and advice.

[0308] In the initial stage, the server authenticates various database systems and establishes connections. Next, it acquires the necessary data, converts different data formats into a unified format, and performs efficient data integration.

[0309] Next, the server conducts data analysis. For the analysis, generation algorithms are utilized to perform trend analysis and anomaly detection of the data. Intelligent advice based on the findings obtained from the analysis is generated for the user.

[0310] In the operation of the emotion engine, the terminal captures the user's voice input and text information, and the server analyzes this information to determine the user's emotional state. The emotion engine evaluates the user's emotions in real time by using emotion analysis algorithms.

[0311] Taking a specific example, consider the case where a certain company utilizes this system. The server aggregates and analyzes daily business data. When the user logs in to the terminal to view a business report and the emotion engine detects emotions such as excitement or surprise of the user, advice corresponding to that emotion is displayed. For example, if the user shows a surprised reaction to the analysis results, the emotion engine may provide additional background information or a specific action plan.

[0312] By incorporating an emotion engine in this way, it becomes possible to adapt to the user's emotions and provide more effective and interactive information. This system is expected to dramatically improve not only the company's data utilization but also the user experience.

[0313] The following describes the processing flow.

[0314] Step 1:

[0315] The server attempts to access each database system using authentication credentials, establishing connections to relational databases, NoSQL databases, and Vector databases. At this stage, it verifies the access rights and security of each database to prepare for secure data retrieval.

[0316] Step 2:

[0317] The server retrieves the necessary data from each database. This data includes sales data, customer information, and product-related data. This data is temporarily stored in the server's memory space.

[0318] Step 3:

[0319] The server uses data integration means to convert data in different formats into a single standard format and store it in an integrated data store in order to centralize the integrated data.

[0320] Step 4:

[0321] The server utilizes generation algorithms to analyze integrated data. Here, machine learning is used to detect data trends and anomalies, and future predictions are made to generate information that contributes to corporate decision-making.

[0322] Step 5:

[0323] Based on the information it collects and analyzes, the server uses intelligent advice generation tools to create suggestions. These suggestions include business strategies, inventory management improvement proposals, and marketing campaign optimization.

[0324] Step 6:

[0325] The device captures voice and text input from the user and sends it to the server. The server uses an emotion engine to analyze this input and identify the user's emotional state.

[0326] Step 7:

[0327] The server analyzes the user's emotional information obtained through the emotion engine and adjusts the content and advice presented in the interface based on that analysis. Personalized feedback is provided that is tailored to the user's emotions.

[0328] Step 8:

[0329] Users can view data summaries and intelligent advice sent from the server through their devices. In particular, if a user expresses emotions such as surprise or anxiety, additional information and support are provided to address these concerns, deepening the user's understanding.

[0330] (Example 2)

[0331] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0332] Traditional data management systems have limitations in their ability to integrate and analyze corporate data, making it particularly difficult to improve user experience and provide personalized services. Furthermore, the inability to provide interactive information that takes user emotions into account has made improving user satisfaction a challenge.

[0333] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0334] In this invention, the server includes database connection means, data integration means, and data analysis means. This enables efficient integration and analysis of corporate data, and by utilizing an emotion recognition engine, it becomes possible to provide intelligent advice based on the user's emotions.

[0335] A "database connection means" is a means that provides functions for authenticating and communicating with a database, and for retrieving and writing data.

[0336] A "data integration method" is a means of organizing data obtained from different formats and sources in a unified manner, making it analyzable.

[0337] "Data analysis methods" refer to means of detecting trends and anomalies based on integrated data, using methods such as statistical analysis and machine learning.

[0338] A "generation algorithm means" is a means of executing an algorithm to generate information or predictions that meet specific conditions based on the results of data analysis.

[0339] An "intelligent advice generation method" is a means of automatically generating recommendations and advice to provide to users based on the results of data analysis.

[0340] A "data summary generation method" is a means of summarizing vast amounts of data and providing only the most important information.

[0341] "User interface provision means" refers to means of providing a visual or audio interface for users to interact directly with the system.

[0342] An "emotion recognition engine" is a method that analyzes voice and text information obtained from users to evaluate the user's emotional state in real time.

[0343] A "real-time emotion analysis method" is a means of using an emotion recognition engine to determine a user's emotions in real time and dynamically provide responses and information.

[0344] This system is implemented by combining various technological elements to enhance corporate data management and user interaction. The system's core processing is handled by a server, and it includes database connection, data integration, and data analysis capabilities for efficiently utilizing corporate data.

[0345] The server connects to enterprise data using common database management software or open-source database management tools (e.g., MySQL, PostgreSQL) to integrate with existing database management systems. After retrieving the data, the server uses a data integration engine (e.g., Apache NiFi) to consolidate the data from different formats and convert it into an analyzable format.

[0346] In the analysis process, the server executes generation algorithms. The software used for this purpose utilizes data science libraries in Python and R (e.g., Scikit-learn, TensorFlow) to perform trend analysis and anomaly detection. From the resulting insights, intelligent advice is generated and provided to the user.

[0347] Users can view the results of the data analysis and advice provided through the device's user interface. The device also uses an emotion engine to analyze the user's voice input and text data, sending emotional information to the server in real time. Based on this emotional information, the server provides further personalized interactions.

[0348] As a concrete example, when a user views a report related to company travel expenses, the device detects their emotions. If the server detects emotions such as surprise or doubt, it provides additional information and advice on the next course of action based on the results of the emotion engine.

[0349] An example of a prompt using a generative AI model would be: "Please tell me the main trends based on this week's sales data. Please also explain the background and why these trends were surprising."

[0350] In this way, by implementing this system, companies can improve the accuracy of data-driven decision-making and make the user experience more personalized.

[0351] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0352] Step 1:

[0353] The server establishes a connection to the database. This connection involves the server sending authentication information using database client software and receiving a response from the database. User authentication information and database connection information are used as input, and the output is a connection state that allows data retrieval.

[0354] Step 2:

[0355] The server retrieves data through an established connection. The input data retrieved here is often business data from a company, in different formats (e.g., CSV, XML). The server uses a data integration engine to convert this data into a single unified format (e.g., JSON), and the output is an integrated dataset.

[0356] Step 3:

[0357] The server takes the integrated dataset as input and begins data analysis. The server executes generative algorithms to perform data trend analysis and anomaly detection. This analysis utilizes machine learning algorithms to generate data insights and predictive results as output.

[0358] Step 4:

[0359] The server generates intelligent advice based on the analysis results. The analysis results are used as input, and the generating AI model processes them to create output that includes helpful advice and recommendations for the user.

[0360] Step 5:

[0361] The terminal displays advice and analysis results from the server via a user interface. In this process, intelligent advice sent from the server is used as input, and information is provided to the user visually or audibly as output. Specific functions include displaying data in graph format on a dashboard and issuing voice notifications.

[0362] Step 6:

[0363] The device acquires voice input and text information from the user. The user's voice samples and text comments are used as input to evaluate the user's emotions. The device sends this information to a server, where the emotion recognition engine performs real-time emotion analysis.

[0364] Step 7:

[0365] The server dynamically updates content and advice based on the analysis results from the emotion recognition engine. In this step, the output of the emotion analysis is treated as input and output as personalized advice adapted to the user's emotions. Specifically, this includes a function that provides additional information in response to the user's surprise.

[0366] (Application Example 2)

[0367] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0368] Traditional data management systems have the challenge of making it difficult to provide personalized services that take into account the emotional state of users. In particular, in physical stores, there is a need to provide timely information and product recommendations that respond to customers' emotions, but the technology to effectively do this is not yet well established.

[0369] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0370] In this invention, the server includes database connection means, data integration means, and emotion recognition means. This makes it possible to analyze customer emotions in real time in physical stores and provide optimized product information and promotions based on that information.

[0371] "Database connection means" refers to technology that has the functionality to connect to various data management systems and retrieve necessary data.

[0372] "Data integration means" refers to technologies for converting data in different formats into a unified format and efficiently aggregating it.

[0373] "Data analysis methods" refer to techniques used to identify trends and detect anomalies using collected data.

[0374] A "generation algorithm" is a technique for generating models that meet specific conditions or objectives in data analysis.

[0375] An "intelligent advice generation method" is a technology that provides appropriate advice to users based on insights gained from data analysis.

[0376] A "data summary generation method" is a technology for providing a summary of data in a format that is easy for users to understand.

[0377] "User interface provisioning means" refers to technologies that provide visual or manipulative means for users to interact with a system.

[0378] "Emotion recognition technology" refers to a technology that analyzes a user's voice and text information to determine their emotional state in real time.

[0379] "Information provision methods based on emotion analysis" refer to technologies that provide users with the most suitable information and content based on the results of emotion recognition.

[0380] In the system that implements this application, a server plays a central role, centrally managing various functions. The system accesses a cloud server via the internet and retrieves data from multiple database systems. User purchase history and sentiment history are collected through the database connection means. Data integration means unify data in different formats and convert it into an analyzable form.

[0381] The data analysis means uses analysis algorithms to perform trend analysis and anomaly detection based on the collected data. The generation algorithm means generates a model based on the analysis results. The intelligent advice generation means creates advice that is appropriate to the user's current emotional state and provides the information in a concise manner.

[0382] On the terminal, emotion recognition means analyze the user's voice input and text data in real time and transmit it to the server. As a result, the server uses emotion analysis-based information provision means to provide appropriate product information and service suggestions that correspond to the user's emotions. The user receives the information through a user interface provision means via a terminal such as a smartphone.

[0383] For example, if a customer shows surprise upon seeing a new product in a store, that information is sent to a server via emotion recognition. The server then quickly provides relevant product information and promotions based on that emotion. As a result, customers can enjoy a personalized shopping experience.

[0384] An example of a prompt using a generative AI model is, "Tell me a new way to tell customers how special this gadget is." This allows the generative AI model to generate effective marketing messages.

[0385] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0386] Step 1:

[0387] The server uses database connection methods to retrieve customer purchase history and sentiment history from various database systems. Inputs include the necessary databases and query information, and output is integrated customer data. This process involves accessing cloud databases via APIs.

[0388] Step 2:

[0389] The server uses data integration to convert customer data in different formats into a unified format. The input consists of datasets in different formats, and the output is in a unified data format. This conversion process includes data mapping and transformation using scripts.

[0390] Step 3:

[0391] The device uses emotion recognition to capture user voice input and text information and transmit it to the server. The input is real-time voice and text data from the user, and the output is emotion data converted into an analyzable digital format. Voice analysis software is then used to extract the emotional state.

[0392] Step 4:

[0393] The server uses a generation algorithm to perform trend analysis and anomaly detection based on data acquired by the data analysis tool. The input is a unified dataset, and the output is a list of detected trend information and anomalies. This process involves applying statistical algorithms to interpret the data.

[0394] Step 5:

[0395] The server uses emotion analysis-based information delivery methods to generate appropriate advice and product information tailored to the user's emotional state. Input consists of user emotion data and historical trend information, while output is personalized informational content. The process includes the use of AI models for information generation.

[0396] Step 6:

[0397] The user receives and views the generated information on their device via a user interface provisioning mechanism. The input is information content provided by the server, and the output is the application screen displayed to the user's eyes. This process includes UI design that takes usability into consideration.

[0398] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0399] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0400] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0401] [Third Embodiment]

[0402] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0403] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0404] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0405] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0406] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0407] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0408] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0409] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0410] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0411] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0412] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0413] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0414] This invention provides a system for efficiently collecting, integrating, and analyzing information from multiple different database systems in modern enterprises. Specific embodiments for carrying out this invention are described below.

[0415] This system has database connection means to access multiple database systems and easily retrieve necessary data. The server establishes connections with relational databases, NoSQL databases, and Vector databases, and all data is seamlessly integrated. In the initial connection stage, authentication information for each database is verified, providing secure access.

[0416] Next, the server utilizes data integration tools to convert data collected in different formats into a unified format. This allows for centralized management of different data formats, facilitating subsequent data analysis. The integrated data is then temporarily stored in a securely managed environment.

[0417] Next, the server uses data analysis tools to perform in-depth analysis on the collected and integrated data. Generative algorithms are employed here, and pattern recognition is performed to detect trends and anomalies within the data. This makes it possible to extract useful insights from the data in real time.

[0418] Furthermore, the server generates intelligent advice based on the analysis results. This intelligent advice generation method allows users to receive practical suggestions to support important business decisions. Examples include inventory optimization based on sales data trends and marketing strategies based on customer data analysis.

[0419] Finally, the server sends the generated data summary to the user's terminal via a user interface. The user can then use the intuitive interface to view the integrated data and explore more detailed data as needed. In particular, if an anomaly is detected, an alert is immediately issued, facilitating rapid response.

[0420] As a concrete example, if a manufacturing company uses this system, the server retrieves product production data, quality control data, and customer feedback data from their respective databases in real time and performs integrated analysis. The user is then provided with suggestions for optimal production plans and specific measures to improve quality, thereby improving the company's production efficiency and quality.

[0421] In this way, the "Smart Data Assistant" according to the present invention will revolutionize how companies utilize data and become a powerful tool for enabling rapid and accurate decision-making.

[0422] The following describes the processing flow.

[0423] Step 1:

[0424] The server begins establishing connections. It uses authentication credentials to establish connections to relational databases, NoSQL databases, and Vector databases for each database. Here, it ensures secure connections by verifying the authentication credentials and confirming access permissions.

[0425] Step 2:

[0426] The server collects the necessary data from multiple databases. It issues appropriate queries to each database to extract information such as sales data, customer information, and product metadata. The collected data is temporarily stored in memory.

[0427] Step 3:

[0428] The server initiates the process of converting collected data into a unified format using data integration means. Different data formats and structures are standardized to facilitate subsequent analysis. This converted data is stored in an integrated data store within a securely managed environment.

[0429] Step 4:

[0430] The server incorporates generation algorithms and begins analyzing the data. Based on the collected and integrated data, analysis is performed using machine learning models. This enables the recognition of data patterns, detection of anomalies, and analysis of trends.

[0431] Step 5:

[0432] The server generates intelligent advice based on the analysis results. This step creates actionable suggestions for the detected trends and anomalies. For example, these may include promotional strategies to increase sales or suggestions for optimizing inventory management.

[0433] Step 6:

[0434] The server organizes the data analysis results and generates a data summary. The summarized data is then visualized in intuitive graphics and text formats, ready to be presented to the user in an easily understandable format.

[0435] Step 7:

[0436] The server sends the generated data summary and intelligent advice to the user's device via the user interface. If a notification or alert is generated, it is immediately sent to the user's device.

[0437] Step 8:

[0438] Users can view the provided data summary through their device and access detailed information as needed. They can also refer to intelligent advice on the interface to aid in decision-making.

[0439] (Example 1)

[0440] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0441] Modern organizations are required to efficiently collect, integrate, and analyze data from multiple different types of databases. However, the introduction of different data formats and analytical tools makes consistent data management and support for rapid decision-making difficult. This reduces the efficiency of data utilization and undermines business competitiveness.

[0442] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0443] In this invention, the server includes database access means, heterogeneous data integration means, and data extraction and analysis means. This makes it possible to collect and integrate data from different types of databases in real time. Furthermore, it enables the rapid extraction of useful insights from the data and advanced analysis to support business decision-making.

[0444] "Database access means" refers to the processes and technologies for securely connecting to multiple different databases and collecting data.

[0445] "Heterogeneous data integration means" refers to technologies that collect data of different formats and structures and convert them into a unified format.

[0446] "Data extraction and analysis methods" refer to techniques for extracting necessary information from collected data and analyzing data trends and anomalies.

[0447] "Generative modeling" refers to the process of generating insights from data using AI models and machine learning techniques.

[0448] "Decision-making support advice generation method" refers to technology that generates useful suggestions and guidelines for users based on analysis results.

[0449] "Information visualization and delivery methods" refer to technologies that display data analysis results in a format that users can intuitively understand.

[0450] "User interaction means" refers to the means or interfaces that allow users to interact with a system and access necessary information.

[0451] To implement the invention, the central server of the system is responsible for connecting to multiple databases and collecting data. The server uses database access means to securely connect to different database systems, such as relational databases, NoSQL databases, and Vector databases. In this process, appropriate authentication and connection are performed using SQL, NoSQL APIs, and security software.

[0452] The server integrates collected data using heterogeneous data integration methods and converts it into a unified format. This unifies the data structure and enables efficient data management. ETL tools and data format conversion software are used for data conversion.

[0453] Furthermore, the server mobilizes data extraction and analysis tools and utilizes generative modeling tools to perform data analysis. In this process, AI models and machine learning algorithms are used to detect trends and anomalies from the data and extract insights. Specific software examples include Python's Scikit-learn and TensorFlow.

[0454] Based on the generated analysis results, the server provides suggestions to the user through a decision support advice generation mechanism. This process generates practical advice that the user can immediately use in their work. This enables the user to make important business decisions quickly. To help the user intuitively understand the summary of the collected and analyzed data, the server uses an information visualization mechanism to allow the user to visually view the data on their terminal.

[0455] For example, if a manufacturing company implements this system, the server will collect production data in real time and analyze it in combination with quality control and customer feedback data. Based on this analysis, optimized production schedules and quality improvement measures will be provided.

[0456] An example of a prompt message is: "Analyze trends from manufacturing production data and generate intelligent advice suggesting the optimal production volume for this month."

[0457] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0458] Step 1:

[0459] The server connects to multiple database systems using database access methods. It uses authentication information for each database as input to establish secure connections with relational databases, NoSQL databases, and Vector databases. Specifically, it establishes connections using API keys and authentication tokens and retrieves a list of necessary tables and documents. The output is a list of connected data sources.

[0460] Step 2:

[0461] The server utilizes heterogeneous data integration methods to convert acquired data into a unified format. The input consists of raw data collected from multiple data sources. This data is then integrated using data transformation software to unify its format and data consistency. Specific operations include converting CSV files to JSON and converting data with different schemas to a standard schema. The output is an integrated dataset.

[0462] Step 3:

[0463] The server uses data extraction and analysis tools to perform in-depth analysis of the data. It utilizes an integrated dataset as input. During this process, machine learning models are executed to perform pattern recognition to discover trends and anomalies in the data. Specifically, this involves applying machine learning algorithms using Python's Scikit-learn to analyze trends in time-series data. The output consists of analyzed insights and discovered patterns.

[0464] Step 4:

[0465] The server uses a generative model to generate intelligent advice based on the analysis results. The input is the result of data analysis. Using a generative AI model, it processes suggestions and strategies that users can use for decision-making. Specifically, it uses a natural language generation algorithm to create suggestions based on the analysis results. The output is intelligent advice for the user.

[0466] Step 5:

[0467] The server uses information visualization and delivery means to visualize and deliver the generated intelligent advice and analysis results to the user's terminal. The input consists of the intelligent advice and analysis results. This is then formatted and processed into a format viewable on a web browser. Specific operations include creating graphs and charts using visualization tools and displaying them to the user. The output is a visually easy-to-understand information display.

[0468] (Application Example 1)

[0469] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0470] In today's production environments, there is a need to effectively aggregate diverse data from multiple devices and systems to optimize operations. However, this data generally exists in different formats, making real-time integration and analysis difficult using conventional methods. Furthermore, a lack of real-time intelligent advice to quickly utilize the insights gained is a significant challenge.

[0471] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0472] In this invention, the server includes data management means, information integration means, and information analysis means. This enables the collection, integration, and analysis of data from different devices in real time, thereby providing intelligent suggestions for operational optimization in real time.

[0473] "Data management methods" refer to technologies for efficiently organizing data obtained from different sources and storing it in a secure and accessible format.

[0474] "Information integration means" refers to the process and function of converting and integrating data of multiple different forms and structures into a unified format.

[0475] "Information analysis means" refers to computational methods and systems for analyzing collected and integrated data to detect patterns, trends, and anomalies.

[0476] "Generative methods and means" refer to algorithms and processes for generating new insights and proposals from data obtained through information analysis.

[0477] An "intelligent suggestion generation method" is a method for proposing optimal actions and improvement measures to target users or systems based on the results of information analysis.

[0478] An "information aggregation and generation method" is a technique for summarizing analysis results and proposals and providing them in an easily understandable visual or digital format.

[0479] "User interface provision means" refers to technologies and devices that provide an interface that allows users to intuitively receive and manipulate data results and suggestions.

[0480] "Execution means" refers to a method and system for optimizing operations by implementing recommendations generated based on analysis results in a real-world environment.

[0481] This invention is designed as a system to improve factory efficiency. The server acquires data from various devices and sensors and integrates the data using cloud computing technology. Specifically, it accesses the database using Google Cloud Platform and processes the data with programs implemented in Python and Java. Furthermore, it utilizes deep learning libraries such as TensorFlow and PyTorch for data analysis to recognize patterns and optimize productivity.

[0482] The server performs real-time data analysis on aggregated information and generates intelligent suggestions using generation methods based on the results. This allows users to directly check instructions for optimizing operations on their terminals and take appropriate action. The user's terminal implements an intuitive and easy-to-understand user interface, enabling them to quickly find and utilize the necessary information.

[0483] For example, if an anomaly is detected on a production line, that information is immediately sent to the user's terminal. This allows the user to take countermeasures quickly. By inputting a prompt message using the generated AI model, such as "Investigate the cause of the speed reduction observed on a specific production line," it is possible to obtain detailed analysis results to identify the root cause of the problem.

[0484] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0485] Step 1:

[0486] The server collects data from various devices and sensors within the factory. Real-time data from various data points (e.g., temperature, speed, operating time, etc.) is input via the network. This data is temporarily stored using data management systems.

[0487] Step 2:

[0488] The stored data is processed by an information integration mechanism. The server converts data in different formats into a unified format and aggregates it into a database managed on the Google Cloud Platform. Data cleansing and validation are performed during this process, making the data ready for efficient subsequent analysis.

[0489] Step 3:

[0490] After data integration is complete, the server performs in-depth analysis of the data using information analysis tools. The input data is processed by scripts written in Python or Java, and trend analysis and anomaly detection are performed using deep learning models with TensorFlow or PyTorch. As a result, the operational status of the factory is evaluated in detail.

[0491] Step 4:

[0492] Based on the analysis results, the generation method generates intelligent suggestions. The server uses the generation AI model to create recommendations based on the analysis results, which are then formatted by the information aggregation and generation means. Users can use these recommendations to determine operational policies.

[0493] Step 5:

[0494] The user's terminal displays results and suggestions generated through the user interface provisioning means. The terminal provides a concrete operation panel, allowing the user to easily explore information and decide on actions. For example, a prompt message such as "Investigate the cause of the speed reduction observed on a specific production line" may be output, allowing the user to take countermeasures based on detailed analysis results.

[0495] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0496] This invention provides a system that enables more personalized interactions by considering user emotions, in addition to the efficient management and utilization of corporate data. Integrating this emotion recognition function enables more human-like communication and decision-making support.

[0497] This system includes database connection means, data integration means, data analysis means, generation algorithm means, intelligent advice generation means, data summary generation means, and user interface provision means. Furthermore, it is equipped with an emotion engine that recognizes user emotions in real time and provides content and advice accordingly.

[0498] In the initial stage, the server authenticates with various database systems and establishes connections. Next, it retrieves the necessary data, converts different data formats to a unified format, and performs efficient data integration.

[0499] Next, the server performs data analysis. This analysis utilizes generative algorithms to analyze data trends and detect anomalies. Based on the insights gained from the analysis, intelligent advice is then generated for the user.

[0500] In the operation of the emotion engine, the terminal captures the user's voice input and text information, and the server analyzes this information to determine the user's emotional state. The emotion engine uses an emotion analysis algorithm to evaluate the user's emotions in real time.

[0501] To give a concrete example, consider a scenario where a company utilizes this system. The server aggregates and analyzes daily business data. When a user logs into their terminal and views business reports, the emotion engine detects emotions such as excitement or surprise, and displays advice tailored to those emotions. For example, if a user reacts with surprise to the analysis results, the emotion engine might provide additional background information or specific action plans.

[0502] By incorporating an emotion engine in this way, it becomes possible to adapt to the user's emotions and provide more effective and interactive information. This system is expected to dramatically improve not only the company's data utilization but also the user experience.

[0503] The following describes the processing flow.

[0504] Step 1:

[0505] The server attempts to access each database system using authentication credentials, establishing connections to relational databases, NoSQL databases, and Vector databases. At this stage, it verifies the access rights and security of each database to prepare for secure data retrieval.

[0506] Step 2:

[0507] The server retrieves the necessary data from each database. This data includes sales data, customer information, and product-related data. This data is temporarily stored in the server's memory space.

[0508] Step 3:

[0509] The server uses data integration means to convert data in different formats into a single standard format and store it in an integrated data store in order to centralize the integrated data.

[0510] Step 4:

[0511] The server utilizes generation algorithms to analyze integrated data. Here, machine learning is used to detect data trends and anomalies, and future predictions are made to generate information that contributes to corporate decision-making.

[0512] Step 5:

[0513] Based on the information it collects and analyzes, the server uses intelligent advice generation tools to create suggestions. These suggestions include business strategies, inventory management improvement proposals, and marketing campaign optimization.

[0514] Step 6:

[0515] The device captures voice and text input from the user and sends it to the server. The server uses an emotion engine to analyze this input and identify the user's emotional state.

[0516] Step 7:

[0517] The server analyzes the user's emotional information obtained through the emotion engine and adjusts the content and advice presented in the interface based on that analysis. Personalized feedback is provided that is tailored to the user's emotions.

[0518] Step 8:

[0519] Users can view data summaries and intelligent advice sent from the server through their devices. In particular, if a user expresses emotions such as surprise or anxiety, additional information and support are provided to address these concerns, deepening the user's understanding.

[0520] (Example 2)

[0521] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0522] Traditional data management systems have limitations in their ability to integrate and analyze corporate data, making it particularly difficult to improve user experience and provide personalized services. Furthermore, the inability to provide interactive information that takes user emotions into account has made improving user satisfaction a challenge.

[0523] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0524] In this invention, the server includes database connection means, data integration means, and data analysis means. This enables efficient integration and analysis of corporate data, and by utilizing an emotion recognition engine, it becomes possible to provide intelligent advice based on the user's emotions.

[0525] A "database connection means" is a means that provides functions for authenticating and communicating with a database, and for retrieving and writing data.

[0526] A "data integration method" is a means of organizing data obtained from different formats and sources in a unified manner, making it analyzable.

[0527] "Data analysis methods" refer to means of detecting trends and anomalies based on integrated data, using methods such as statistical analysis and machine learning.

[0528] A "generation algorithm means" is a means of executing an algorithm to generate information or predictions that meet specific conditions based on the results of data analysis.

[0529] An "intelligent advice generation method" is a means of automatically generating recommendations and advice to provide to users based on the results of data analysis.

[0530] A "data summary generation method" is a means of summarizing vast amounts of data and providing only the most important information.

[0531] "User interface provision means" refers to means of providing a visual or audio interface for users to interact directly with the system.

[0532] An "emotion recognition engine" is a method that analyzes voice and text information obtained from users to evaluate the user's emotional state in real time.

[0533] A "real-time emotion analysis method" is a means of using an emotion recognition engine to determine a user's emotions in real time and dynamically provide responses and information.

[0534] This system is implemented by combining various technological elements to enhance corporate data management and user interaction. The system's core processing is handled by a server, and it includes database connection, data integration, and data analysis capabilities for efficiently utilizing corporate data.

[0535] The server connects to enterprise data using common database management software or open-source database management tools (e.g., MySQL, PostgreSQL) to integrate with existing database management systems. After retrieving the data, the server uses a data integration engine (e.g., Apache NiFi) to consolidate the data from different formats and convert it into an analyzable format.

[0536] In the analysis process, the server executes generation algorithms. The software used for this purpose utilizes data science libraries in Python and R (e.g., Scikit-learn, TensorFlow) to perform trend analysis and anomaly detection. From the resulting insights, intelligent advice is generated and provided to the user.

[0537] Users can view the results of the data analysis and advice provided through the device's user interface. The device also uses an emotion engine to analyze the user's voice input and text data, sending emotional information to the server in real time. Based on this emotional information, the server provides further personalized interactions.

[0538] As a concrete example, when a user views a report related to company travel expenses, the device detects their emotions. If the server detects emotions such as surprise or doubt, it provides additional information and advice on the next course of action based on the results of the emotion engine.

[0539] An example of a prompt using a generative AI model would be: "Please tell me the main trends based on this week's sales data. Please also explain the background and why these trends were surprising."

[0540] In this way, by implementing this system, companies can improve the accuracy of data-driven decision-making and make the user experience more personalized.

[0541] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0542] Step 1:

[0543] The server establishes a connection to the database. This connection involves the server sending authentication information using database client software and receiving a response from the database. User authentication information and database connection information are used as input, and the output is a connection state that allows data retrieval.

[0544] Step 2:

[0545] The server retrieves data through an established connection. The input data retrieved here is often business data from a company, in different formats (e.g., CSV, XML). The server uses a data integration engine to convert this data into a single unified format (e.g., JSON), and the output is an integrated dataset.

[0546] Step 3:

[0547] The server takes the integrated dataset as input and begins data analysis. The server executes generative algorithms to perform data trend analysis and anomaly detection. This analysis utilizes machine learning algorithms to generate data insights and predictive results as output.

[0548] Step 4:

[0549] The server generates intelligent advice based on the analysis results. The analysis results are used as input, and the generating AI model processes them to create output that includes helpful advice and recommendations for the user.

[0550] Step 5:

[0551] The terminal displays advice and analysis results from the server via a user interface. In this process, intelligent advice sent from the server is used as input, and information is provided to the user visually or audibly as output. Specific functions include displaying data in graph format on a dashboard and issuing voice notifications.

[0552] Step 6:

[0553] The device acquires voice input and text information from the user. The user's voice samples and text comments are used as input to evaluate the user's emotions. The device sends this information to a server, where the emotion recognition engine performs real-time emotion analysis.

[0554] Step 7:

[0555] The server dynamically updates content and advice based on the analysis results from the emotion recognition engine. In this step, the output of the emotion analysis is treated as input and output as personalized advice adapted to the user's emotions. Specifically, this includes a function that provides additional information in response to the user's surprise.

[0556] (Application Example 2)

[0557] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0558] Traditional data management systems have the challenge of making it difficult to provide personalized services that take into account the emotional state of users. In particular, in physical stores, there is a need to provide timely information and product recommendations that respond to customers' emotions, but the technology to effectively do this is not yet well established.

[0559] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0560] In this invention, the server includes database connection means, data integration means, and emotion recognition means. This makes it possible to analyze customer emotions in real time in physical stores and provide optimized product information and promotions based on that information.

[0561] "Database connection means" refers to technology that has the functionality to connect to various data management systems and retrieve necessary data.

[0562] "Data integration means" refers to technologies for converting data in different formats into a unified format and efficiently aggregating it.

[0563] "Data analysis methods" refer to techniques used to identify trends and detect anomalies using collected data.

[0564] A "generation algorithm" is a technique for generating models that meet specific conditions or objectives in data analysis.

[0565] An "intelligent advice generation method" is a technology that provides appropriate advice to users based on insights gained from data analysis.

[0566] A "data summary generation method" is a technology for providing a summary of data in a format that is easy for users to understand.

[0567] "User interface provisioning means" refers to technologies that provide visual or manipulative means for users to interact with a system.

[0568] "Emotion recognition technology" refers to a technology that analyzes a user's voice and text information to determine their emotional state in real time.

[0569] "Information provision methods based on emotion analysis" refer to technologies that provide users with the most suitable information and content based on the results of emotion recognition.

[0570] In the system that implements this application, a server plays a central role, centrally managing various functions. The system accesses a cloud server via the internet and retrieves data from multiple database systems. User purchase history and sentiment history are collected through the database connection means. Data integration means unify data in different formats and convert it into an analyzable form.

[0571] The data analysis means uses analysis algorithms to perform trend analysis and anomaly detection based on the collected data. The generation algorithm means generates a model based on the analysis results. The intelligent advice generation means creates advice that is appropriate to the user's current emotional state and provides the information in a concise manner.

[0572] On the terminal, emotion recognition means analyze the user's voice input and text data in real time and transmit it to the server. As a result, the server uses emotion analysis-based information provision means to provide appropriate product information and service suggestions that correspond to the user's emotions. The user receives the information through a user interface provision means via a terminal such as a smartphone.

[0573] For example, if a customer shows surprise upon seeing a new product in a store, that information is sent to a server via emotion recognition. The server then quickly provides relevant product information and promotions based on that emotion. As a result, customers can enjoy a personalized shopping experience.

[0574] An example of a prompt using a generative AI model is, "Tell me a new way to tell customers how special this gadget is." This allows the generative AI model to generate effective marketing messages.

[0575] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0576] Step 1:

[0577] The server uses database connection methods to retrieve customer purchase history and sentiment history from various database systems. Inputs include the necessary databases and query information, and output is integrated customer data. This process involves accessing cloud databases via APIs.

[0578] Step 2:

[0579] The server uses data integration to convert customer data in different formats into a unified format. The input consists of datasets in different formats, and the output is in a unified data format. This conversion process includes data mapping and transformation using scripts.

[0580] Step 3:

[0581] The device uses emotion recognition to capture user voice input and text information and transmit it to the server. The input is real-time voice and text data from the user, and the output is emotion data converted into an analyzable digital format. Voice analysis software is then used to extract the emotional state.

[0582] Step 4:

[0583] The server uses a generation algorithm to perform trend analysis and anomaly detection based on data acquired by the data analysis tool. The input is a unified dataset, and the output is a list of detected trend information and anomalies. This process involves applying statistical algorithms to interpret the data.

[0584] Step 5:

[0585] The server uses emotion analysis-based information delivery methods to generate appropriate advice and product information tailored to the user's emotional state. Input consists of user emotion data and historical trend information, while output is personalized informational content. The process includes the use of AI models for information generation.

[0586] Step 6:

[0587] The user receives and views the generated information on their device via a user interface provisioning mechanism. The input is information content provided by the server, and the output is the application screen displayed to the user's eyes. This process includes UI design that takes usability into consideration.

[0588] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0589] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0590] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0591] [Fourth Embodiment]

[0592] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0593] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0594] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0595] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0596] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0597] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0598] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0599] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0600] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0601] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0602] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0603] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0604] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0605] This invention provides a system for efficiently collecting, integrating, and analyzing information from multiple different database systems in modern enterprises. Specific embodiments for carrying out this invention are described below.

[0606] This system has database connection means to access multiple database systems and easily retrieve necessary data. The server establishes connections with relational databases, NoSQL databases, and Vector databases, and all data is seamlessly integrated. In the initial connection stage, authentication information for each database is verified, providing secure access.

[0607] Next, the server utilizes data integration tools to convert data collected in different formats into a unified format. This allows for centralized management of different data formats, facilitating subsequent data analysis. The integrated data is then temporarily stored in a securely managed environment.

[0608] Next, the server uses data analysis tools to perform in-depth analysis on the collected and integrated data. Generative algorithms are employed here, and pattern recognition is performed to detect trends and anomalies within the data. This makes it possible to extract useful insights from the data in real time.

[0609] Furthermore, the server generates intelligent advice based on the analysis results. This intelligent advice generation method allows users to receive practical suggestions to support important business decisions. Examples include inventory optimization based on sales data trends and marketing strategies based on customer data analysis.

[0610] Finally, the server sends the generated data summary to the user's terminal via a user interface. The user can then use the intuitive interface to view the integrated data and explore more detailed data as needed. In particular, if an anomaly is detected, an alert is immediately issued, facilitating rapid response.

[0611] As a concrete example, if a manufacturing company uses this system, the server retrieves product production data, quality control data, and customer feedback data from their respective databases in real time and performs integrated analysis. The user is then provided with suggestions for optimal production plans and specific measures to improve quality, thereby improving the company's production efficiency and quality.

[0612] In this way, the "Smart Data Assistant" according to the present invention will revolutionize how companies utilize data and become a powerful tool for enabling rapid and accurate decision-making.

[0613] The following describes the processing flow.

[0614] Step 1:

[0615] The server begins establishing connections. It uses authentication credentials to establish connections to relational databases, NoSQL databases, and Vector databases for each database. Here, it ensures secure connections by verifying the authentication credentials and confirming access permissions.

[0616] Step 2:

[0617] The server collects the necessary data from multiple databases. It issues appropriate queries to each database to extract information such as sales data, customer information, and product metadata. The collected data is temporarily stored in memory.

[0618] Step 3:

[0619] The server initiates the process of converting collected data into a unified format using data integration means. Different data formats and structures are standardized to facilitate subsequent analysis. This converted data is stored in an integrated data store within a securely managed environment.

[0620] Step 4:

[0621] The server incorporates generation algorithms and begins analyzing the data. Based on the collected and integrated data, analysis is performed using machine learning models. This enables the recognition of data patterns, detection of anomalies, and analysis of trends.

[0622] Step 5:

[0623] The server generates intelligent advice based on the analysis results. This step creates actionable suggestions for the detected trends and anomalies. For example, these may include promotional strategies to increase sales or suggestions for optimizing inventory management.

[0624] Step 6:

[0625] The server organizes the data analysis results and generates a data summary. The summarized data is then visualized in intuitive graphics and text formats, ready to be presented to the user in an easily understandable format.

[0626] Step 7:

[0627] The server sends the generated data summary and intelligent advice to the user's device via the user interface. If a notification or alert is generated, it is immediately sent to the user's device.

[0628] Step 8:

[0629] Users can view the provided data summary through their device and access detailed information as needed. They can also refer to intelligent advice on the interface to aid in decision-making.

[0630] (Example 1)

[0631] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0632] Modern organizations are required to efficiently collect, integrate, and analyze data from multiple different types of databases. However, the introduction of different data formats and analytical tools makes consistent data management and support for rapid decision-making difficult. This reduces the efficiency of data utilization and undermines business competitiveness.

[0633] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0634] In this invention, the server includes database access means, heterogeneous data integration means, and data extraction and analysis means. This makes it possible to collect and integrate data from different types of databases in real time. Furthermore, it enables the rapid extraction of useful insights from the data and advanced analysis to support business decision-making.

[0635] "Database access means" refers to the processes and technologies for securely connecting to multiple different databases and collecting data.

[0636] "Heterogeneous data integration means" refers to technologies that collect data of different formats and structures and convert them into a unified format.

[0637] "Data extraction and analysis methods" refer to techniques for extracting necessary information from collected data and analyzing data trends and anomalies.

[0638] "Generative modeling" refers to the process of generating insights from data using AI models and machine learning techniques.

[0639] "Decision-making support advice generation method" refers to technology that generates useful suggestions and guidelines for users based on analysis results.

[0640] "Information visualization and delivery methods" refer to technologies that display data analysis results in a format that users can intuitively understand.

[0641] "User interaction means" refers to the means or interfaces that allow users to interact with a system and access necessary information.

[0642] To implement the invention, the central server of the system is responsible for connecting to multiple databases and collecting data. The server uses database access means to securely connect to different database systems, such as relational databases, NoSQL databases, and Vector databases. In this process, appropriate authentication and connection are performed using SQL, NoSQL APIs, and security software.

[0643] The server integrates collected data using heterogeneous data integration methods and converts it into a unified format. This unifies the data structure and enables efficient data management. ETL tools and data format conversion software are used for data conversion.

[0644] Furthermore, the server mobilizes data extraction and analysis tools and utilizes generative modeling tools to perform data analysis. In this process, AI models and machine learning algorithms are used to detect trends and anomalies from the data and extract insights. Specific software examples include Python's Scikit-learn and TensorFlow.

[0645] Based on the generated analysis results, the server provides suggestions to the user through a decision support advice generation mechanism. This process generates practical advice that the user can immediately use in their work. This enables the user to make important business decisions quickly. To help the user intuitively understand the summary of the collected and analyzed data, the server uses an information visualization mechanism to allow the user to visually view the data on their terminal.

[0646] For example, if a manufacturing company implements this system, the server will collect production data in real time and analyze it in combination with quality control and customer feedback data. Based on this analysis, optimized production schedules and quality improvement measures will be provided.

[0647] An example of a prompt message is: "Analyze trends from manufacturing production data and generate intelligent advice suggesting the optimal production volume for this month."

[0648] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0649] Step 1:

[0650] The server connects to multiple database systems using database access methods. It uses authentication information for each database as input to establish secure connections with relational databases, NoSQL databases, and Vector databases. Specifically, it establishes connections using API keys and authentication tokens and retrieves a list of necessary tables and documents. The output is a list of connected data sources.

[0651] Step 2:

[0652] The server utilizes heterogeneous data integration methods to convert acquired data into a unified format. The input consists of raw data collected from multiple data sources. This data is then integrated using data transformation software to unify its format and data consistency. Specific operations include converting CSV files to JSON and converting data with different schemas to a standard schema. The output is an integrated dataset.

[0653] Step 3:

[0654] The server uses data extraction and analysis tools to perform in-depth analysis of the data. It utilizes an integrated dataset as input. During this process, machine learning models are executed to perform pattern recognition to discover trends and anomalies in the data. Specifically, this involves applying machine learning algorithms using Python's Scikit-learn to analyze trends in time-series data. The output consists of analyzed insights and discovered patterns.

[0655] Step 4:

[0656] The server uses a generative model to generate intelligent advice based on the analysis results. The input is the result of data analysis. Using a generative AI model, it processes suggestions and strategies that users can use for decision-making. Specifically, it uses a natural language generation algorithm to create suggestions based on the analysis results. The output is intelligent advice for the user.

[0657] Step 5:

[0658] The server uses information visualization and delivery means to visualize and deliver the generated intelligent advice and analysis results to the user's terminal. The input consists of the intelligent advice and analysis results. This is then formatted and processed into a format viewable on a web browser. Specific operations include creating graphs and charts using visualization tools and displaying them to the user. The output is a visually easy-to-understand information display.

[0659] (Application Example 1)

[0660] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0661] In today's production environments, there is a need to effectively aggregate diverse data from multiple devices and systems to optimize operations. However, this data generally exists in different formats, making real-time integration and analysis difficult using conventional methods. Furthermore, a lack of real-time intelligent advice to quickly utilize the insights gained is a significant challenge.

[0662] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0663] In this invention, the server includes data management means, information integration means, and information analysis means. This enables the collection, integration, and analysis of data from different devices in real time, thereby providing intelligent suggestions for operational optimization in real time.

[0664] "Data management methods" refer to technologies for efficiently organizing data obtained from different sources and storing it in a secure and accessible format.

[0665] "Information integration means" refers to the process and function of converting and integrating data of multiple different forms and structures into a unified format.

[0666] "Information analysis means" refers to computational methods and systems for analyzing collected and integrated data to detect patterns, trends, and anomalies.

[0667] "Generative methods and means" refer to algorithms and processes for generating new insights and proposals from data obtained through information analysis.

[0668] An "intelligent suggestion generation method" is a method for proposing optimal actions and improvement measures to target users or systems based on the results of information analysis.

[0669] An "information aggregation and generation method" is a technique for summarizing analysis results and proposals and providing them in an easily understandable visual or digital format.

[0670] "User interface provision means" refers to technologies and devices that provide an interface that allows users to intuitively receive and manipulate data results and suggestions.

[0671] "Execution means" refers to a method and system for optimizing operations by implementing recommendations generated based on analysis results in a real-world environment.

[0672] This invention is designed as a system to improve factory efficiency. The server acquires data from various devices and sensors and integrates the data using cloud computing technology. Specifically, it accesses the database using Google Cloud Platform and processes the data with programs implemented in Python and Java. Furthermore, it utilizes deep learning libraries such as TensorFlow and PyTorch for data analysis to recognize patterns and optimize productivity.

[0673] The server performs real-time data analysis on aggregated information and generates intelligent suggestions using generation methods based on the results. This allows users to directly check instructions for optimizing operations on their terminals and take appropriate action. The user's terminal implements an intuitive and easy-to-understand user interface, enabling them to quickly find and utilize the necessary information.

[0674] For example, if an anomaly is detected on a production line, that information is immediately sent to the user's terminal. This allows the user to take countermeasures quickly. By inputting a prompt message using the generated AI model, such as "Investigate the cause of the speed reduction observed on a specific production line," it is possible to obtain detailed analysis results to identify the root cause of the problem.

[0675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0676] Step 1:

[0677] The server collects data from various devices and sensors within the factory. Real-time data from various data points (e.g., temperature, speed, operating time, etc.) is input via the network. This data is temporarily stored using data management systems.

[0678] Step 2:

[0679] The stored data is processed by an information integration mechanism. The server converts data in different formats into a unified format and aggregates it into a database managed on the Google Cloud Platform. Data cleansing and validation are performed during this process, making the data ready for efficient subsequent analysis.

[0680] Step 3:

[0681] After data integration is complete, the server performs in-depth analysis of the data using information analysis tools. The input data is processed by scripts written in Python or Java, and trend analysis and anomaly detection are performed using deep learning models with TensorFlow or PyTorch. As a result, the operational status of the factory is evaluated in detail.

[0682] Step 4:

[0683] Based on the analysis results, the generation method generates intelligent suggestions. The server uses the generation AI model to create recommendations based on the analysis results, which are then formatted by the information aggregation and generation means. Users can use these recommendations to determine operational policies.

[0684] Step 5:

[0685] The user's terminal displays results and suggestions generated through the user interface provisioning means. The terminal provides a concrete operation panel, allowing the user to easily explore information and decide on actions. For example, a prompt message such as "Investigate the cause of the speed reduction observed on a specific production line" may be output, allowing the user to take countermeasures based on detailed analysis results.

[0686] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0687] This invention provides a system that enables more personalized interactions by considering user emotions, in addition to the efficient management and utilization of corporate data. Integrating this emotion recognition function enables more human-like communication and decision-making support.

[0688] This system includes database connection means, data integration means, data analysis means, generation algorithm means, intelligent advice generation means, data summary generation means, and user interface provision means. Furthermore, it is equipped with an emotion engine that recognizes user emotions in real time and provides content and advice accordingly.

[0689] In the initial stage, the server authenticates with various database systems and establishes connections. Next, it retrieves the necessary data, converts different data formats to a unified format, and performs efficient data integration.

[0690] Next, the server performs data analysis. This analysis utilizes generative algorithms to analyze data trends and detect anomalies. Based on the insights gained from the analysis, intelligent advice is then generated for the user.

[0691] In the operation of the emotion engine, the terminal captures the user's voice input and text information, and the server analyzes this information to determine the user's emotional state. The emotion engine uses an emotion analysis algorithm to evaluate the user's emotions in real time.

[0692] To give a concrete example, consider a scenario where a company utilizes this system. The server aggregates and analyzes daily business data. When a user logs into their terminal and views business reports, the emotion engine detects emotions such as excitement or surprise, and displays advice tailored to those emotions. For example, if a user reacts with surprise to the analysis results, the emotion engine might provide additional background information or specific action plans.

[0693] By incorporating an emotion engine in this way, it becomes possible to adapt to the user's emotions and provide more effective and interactive information. This system is expected to dramatically improve not only the company's data utilization but also the user experience.

[0694] The following describes the processing flow.

[0695] Step 1:

[0696] The server attempts to access each database system using authentication credentials, establishing connections to relational databases, NoSQL databases, and Vector databases. At this stage, it verifies the access rights and security of each database to prepare for secure data retrieval.

[0697] Step 2:

[0698] The server retrieves the necessary data from each database. This data includes sales data, customer information, and product-related data. This data is temporarily stored in the server's memory space.

[0699] Step 3:

[0700] The server uses data integration means to convert data in different formats into a single standard format and store it in an integrated data store in order to centralize the integrated data.

[0701] Step 4:

[0702] The server utilizes generation algorithms to analyze integrated data. Here, machine learning is used to detect data trends and anomalies, and future predictions are made to generate information that contributes to corporate decision-making.

[0703] Step 5:

[0704] Based on the information it collects and analyzes, the server uses intelligent advice generation tools to create suggestions. These suggestions include business strategies, inventory management improvement proposals, and marketing campaign optimization.

[0705] Step 6:

[0706] The device captures voice and text input from the user and sends it to the server. The server uses an emotion engine to analyze this input and identify the user's emotional state.

[0707] Step 7:

[0708] The server analyzes the user's emotional information obtained through the emotion engine and adjusts the content and advice presented in the interface based on that analysis. Personalized feedback is provided that is tailored to the user's emotions.

[0709] Step 8:

[0710] Users can view data summaries and intelligent advice sent from the server through their devices. In particular, if a user expresses emotions such as surprise or anxiety, additional information and support are provided to address these concerns, deepening the user's understanding.

[0711] (Example 2)

[0712] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0713] Traditional data management systems have limitations in their ability to integrate and analyze corporate data, making it particularly difficult to improve user experience and provide personalized services. Furthermore, the inability to provide interactive information that takes user emotions into account has made improving user satisfaction a challenge.

[0714] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0715] In this invention, the server includes database connection means, data integration means, and data analysis means. This enables efficient integration and analysis of corporate data, and by utilizing an emotion recognition engine, it becomes possible to provide intelligent advice based on the user's emotions.

[0716] A "database connection means" is a means that provides functions for authenticating and communicating with a database, and for retrieving and writing data.

[0717] A "data integration method" is a means of organizing data obtained from different formats and sources in a unified manner, making it analyzable.

[0718] "Data analysis methods" refer to means of detecting trends and anomalies based on integrated data, using methods such as statistical analysis and machine learning.

[0719] A "generation algorithm means" is a means of executing an algorithm to generate information or predictions that meet specific conditions based on the results of data analysis.

[0720] An "intelligent advice generation method" is a means of automatically generating recommendations and advice to provide to users based on the results of data analysis.

[0721] A "data summary generation method" is a means of summarizing vast amounts of data and providing only the most important information.

[0722] "User interface provision means" refers to means of providing a visual or audio interface for users to interact directly with the system.

[0723] An "emotion recognition engine" is a method that analyzes voice and text information obtained from users to evaluate the user's emotional state in real time.

[0724] A "real-time emotion analysis method" is a means of using an emotion recognition engine to determine a user's emotions in real time and dynamically provide responses and information.

[0725] This system is implemented by combining various technological elements to enhance corporate data management and user interaction. The system's core processing is handled by a server, and it includes database connection, data integration, and data analysis capabilities for efficiently utilizing corporate data.

[0726] The server connects to enterprise data using common database management software or open-source database management tools (e.g., MySQL, PostgreSQL) to integrate with existing database management systems. After retrieving the data, the server uses a data integration engine (e.g., Apache NiFi) to consolidate the data from different formats and convert it into an analyzable format.

[0727] In the analysis process, the server executes generation algorithms. The software used for this purpose utilizes data science libraries in Python and R (e.g., Scikit-learn, TensorFlow) to perform trend analysis and anomaly detection. From the resulting insights, intelligent advice is generated and provided to the user.

[0728] Users can view the results of the data analysis and advice provided through the device's user interface. The device also uses an emotion engine to analyze the user's voice input and text data, sending emotional information to the server in real time. Based on this emotional information, the server provides further personalized interactions.

[0729] As a concrete example, when a user views a report related to company travel expenses, the device detects their emotions. If the server detects emotions such as surprise or doubt, it provides additional information and advice on the next course of action based on the results of the emotion engine.

[0730] An example of a prompt using a generative AI model would be: "Please tell me the main trends based on this week's sales data. Please also explain the background and why these trends were surprising."

[0731] In this way, by implementing this system, companies can improve the accuracy of data-driven decision-making and make the user experience more personalized.

[0732] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0733] Step 1:

[0734] The server establishes a connection to the database. This connection involves the server sending authentication information using database client software and receiving a response from the database. User authentication information and database connection information are used as input, and the output is a connection state that allows data retrieval.

[0735] Step 2:

[0736] The server retrieves data through an established connection. The input data retrieved here is often business data from a company, in different formats (e.g., CSV, XML). The server uses a data integration engine to convert this data into a single unified format (e.g., JSON), and the output is an integrated dataset.

[0737] Step 3:

[0738] The server takes the integrated dataset as input and begins data analysis. The server executes generative algorithms to perform data trend analysis and anomaly detection. This analysis utilizes machine learning algorithms to generate data insights and predictive results as output.

[0739] Step 4:

[0740] The server generates intelligent advice based on the analysis results. The analysis results are used as input, and the generating AI model processes them to create output that includes helpful advice and recommendations for the user.

[0741] Step 5:

[0742] The terminal displays advice and analysis results from the server via a user interface. In this process, intelligent advice sent from the server is used as input, and information is provided to the user visually or audibly as output. Specific functions include displaying data in graph format on a dashboard and issuing voice notifications.

[0743] Step 6:

[0744] The device acquires voice input and text information from the user. The user's voice samples and text comments are used as input to evaluate the user's emotions. The device sends this information to a server, where the emotion recognition engine performs real-time emotion analysis.

[0745] Step 7:

[0746] The server dynamically updates content and advice based on the analysis results from the emotion recognition engine. In this step, the output of the emotion analysis is treated as input and output as personalized advice adapted to the user's emotions. Specifically, this includes a function that provides additional information in response to the user's surprise.

[0747] (Application Example 2)

[0748] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0749] Traditional data management systems have the challenge of making it difficult to provide personalized services that take into account the emotional state of users. In particular, in physical stores, there is a need to provide timely information and product recommendations that respond to customers' emotions, but the technology to effectively do this is not yet well established.

[0750] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0751] In this invention, the server includes database connection means, data integration means, and emotion recognition means. This makes it possible to analyze customer emotions in real time in physical stores and provide optimized product information and promotions based on that information.

[0752] "Database connection means" refers to technology that has the functionality to connect to various data management systems and retrieve necessary data.

[0753] "Data integration means" refers to technologies for converting data in different formats into a unified format and efficiently aggregating it.

[0754] "Data analysis methods" refer to techniques used to identify trends and detect anomalies using collected data.

[0755] A "generation algorithm" is a technique for generating models that meet specific conditions or objectives in data analysis.

[0756] An "intelligent advice generation method" is a technology that provides appropriate advice to users based on insights gained from data analysis.

[0757] A "data summary generation method" is a technology for providing a summary of data in a format that is easy for users to understand.

[0758] "User interface provisioning means" refers to technologies that provide visual or manipulative means for users to interact with a system.

[0759] "Emotion recognition technology" refers to a technology that analyzes a user's voice and text information to determine their emotional state in real time.

[0760] "Information provision methods based on emotion analysis" refer to technologies that provide users with the most suitable information and content based on the results of emotion recognition.

[0761] In the system that implements this application, a server plays a central role, centrally managing various functions. The system accesses a cloud server via the internet and retrieves data from multiple database systems. User purchase history and sentiment history are collected through the database connection means. Data integration means unify data in different formats and convert it into an analyzable form.

[0762] The data analysis means uses analysis algorithms to perform trend analysis and anomaly detection based on the collected data. The generation algorithm means generates a model based on the analysis results. The intelligent advice generation means creates advice that is appropriate to the user's current emotional state and provides the information in a concise manner.

[0763] On the terminal, emotion recognition means analyze the user's voice input and text data in real time and transmit it to the server. As a result, the server uses emotion analysis-based information provision means to provide appropriate product information and service suggestions that correspond to the user's emotions. The user receives the information through a user interface provision means via a terminal such as a smartphone.

[0764] For example, if a customer shows surprise upon seeing a new product in a store, that information is sent to a server via emotion recognition. The server then quickly provides relevant product information and promotions based on that emotion. As a result, customers can enjoy a personalized shopping experience.

[0765] An example of a prompt using a generative AI model is, "Tell me a new way to tell customers how special this gadget is." This allows the generative AI model to generate effective marketing messages.

[0766] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0767] Step 1:

[0768] The server uses database connection methods to retrieve customer purchase history and sentiment history from various database systems. Inputs include the necessary databases and query information, and output is integrated customer data. This process involves accessing cloud databases via APIs.

[0769] Step 2:

[0770] The server uses data integration to convert customer data in different formats into a unified format. The input consists of datasets in different formats, and the output is in a unified data format. This conversion process includes data mapping and transformation using scripts.

[0771] Step 3:

[0772] The device uses emotion recognition to capture user voice input and text information and transmit it to the server. The input is real-time voice and text data from the user, and the output is emotion data converted into an analyzable digital format. Voice analysis software is then used to extract the emotional state.

[0773] Step 4:

[0774] The server uses a generation algorithm to perform trend analysis and anomaly detection based on data acquired by the data analysis tool. The input is a unified dataset, and the output is a list of detected trend information and anomalies. This process involves applying statistical algorithms to interpret the data.

[0775] Step 5:

[0776] The server uses emotion analysis-based information delivery methods to generate appropriate advice and product information tailored to the user's emotional state. Input consists of user emotion data and historical trend information, while output is personalized informational content. The process includes the use of AI models for information generation.

[0777] Step 6:

[0778] The user receives and views the generated information on their device via a user interface provisioning mechanism. The input is information content provided by the server, and the output is the application screen displayed to the user's eyes. This process includes UI design that takes usability into consideration.

[0779] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0780] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0781] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0782] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0783] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0784] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0785] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0786] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0787] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0788] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0789] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0790] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0791] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0792] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0793] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0794] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0795] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0796] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0797] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0798] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0799] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0800] The following is further disclosed regarding the embodiments described above.

[0801] (Claim 1)

[0802] Database connection means,

[0803] Data integration means,

[0804] Data analysis methods,

[0805] Generation algorithm means,

[0806] Intelligent advice generation means,

[0807] Data summary generation means,

[0808] Means for providing a user interface,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, comprising data integration means for collecting information from data sources and integrating it in real time.

[0812] (Claim 3)

[0813] The system according to claim 1, comprising a data analysis means for performing anomaly detection and trend analysis using a generation algorithm means.

[0814] "Example 1"

[0815] (Claim 1)

[0816] Database access means,

[0817] Means for integrating heterogeneous data,

[0818] Data extraction and analysis means,

[0819] Generative model means,

[0820] A means for generating decision support advice,

[0821] Information visualization and provision means,

[0822] User interaction means,

[0823] A system that includes this.

[0824] (Claim 2)

[0825] The system according to claim 1, comprising heterogeneous data integration means for extracting information from information sources and integrating it in real time.

[0826] (Claim 3)

[0827] The system according to claim 1, comprising a data extraction and analysis means for performing anomaly detection and pattern analysis using a generative model means.

[0828] "Application Example 1"

[0829] (Claim 1)

[0830] Data management means,

[0831] Information integration means,

[0832] Information analysis means,

[0833] Generation method and means,

[0834] Intelligent proposal generation means,

[0835] Information aggregation and generation means,

[0836] Means for providing a user interface,

[0837] An execution means that acquires information from equipment and supports operational optimization based on the analysis results,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, comprising data collection means and information integration means for aggregating information in real time to optimize equipment operation.

[0841] (Claim 3)

[0842] The system according to claim 1, comprising an information analysis means that performs anomaly detection and trend analysis using a generation method means, and supports process adjustment with the generated recommendations.

[0843] "Example 2 of combining an emotion engine"

[0844] (Claim 1)

[0845] Database connection means,

[0846] Data integration means,

[0847] Data analysis methods,

[0848] Generation algorithm means,

[0849] Intelligent advice generation means,

[0850] Data summary generation means,

[0851] Means for providing a user interface,

[0852] Emotion recognition engine,

[0853] Real-time emotion analysis method,

[0854] A system that includes this.

[0855] (Claim 2)

[0856] The system according to claim 1, comprising data integration means for collecting information from data sources and integrating it in real time.

[0857] (Claim 3)

[0858] The system according to claim 1, comprising a data analysis means for performing anomaly detection and trend analysis using a generation algorithm means, and further performing real-time sentiment analysis to evaluate the user's emotional state.

[0859] "Application example 2 when combining with an emotional engine"

[0860] (Claim 1)

[0861] Database connection means,

[0862] Data integration means,

[0863] Data analysis methods,

[0864] Generation algorithm means,

[0865] Intelligent advice generation means,

[0866] Data summary generation means,

[0867] Means for providing a user interface,

[0868] Means of recognizing emotions,

[0869] Information provision methods based on emotion analysis,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, comprising the function of collecting information from data sources, integrating it in real time, and evaluating the user's emotions using emotion recognition technology.

[0873] (Claim 3)

[0874] The system according to claim 1, comprising a generation algorithm that performs anomaly detection and trend analysis, and further provides optimized advice to the user based on the sentiment analysis results. [Explanation of symbols]

[0875] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A database connection means for accessing multiple database systems and retrieving necessary data, A data integration means that converts data of different formats and structures into a single unified format, A data analysis method that extracts useful information by performing statistical analysis and pattern recognition based on collected data, A generative algorithm that uses artificial intelligence technology to generate new knowledge and proposals from the results of data analysis, An intelligent advice generation method that provides appropriate and practical suggestions to the user based on the analysis results, A data summary generation means that summarizes the analyzed data and provides it to the user as a visual or overview, A means of providing a user interface that enables users to access, operate, and view information on the system, A system that includes this.

2. The system according to claim 1, comprising data integration means for collecting information from data sources and integrating it in real time.

3. The system according to claim 1, comprising a data analysis means for performing anomaly detection and trend analysis using a generation algorithm means.

Images