system

Abstract

We provide a system that centralizes internal data management and decision-making, improving business efficiency and accuracy. [Solution] The system includes: a data collection means that collects data from multiple data sources and periodically acquires data using an API; a preprocessing means that fills in missing values ​​in the collected data, removes duplicate data, and standardizes the data format; a data integration means that integrates the preprocessed data into a common data model and defines and normalizes data relationships; a data governance means that uses AI to manage access rights, data classification, and privacy; a data visualization and analysis means that, based on user requests, extracts necessary data from the integrated database, analyzes and predicts using AI, and displays the results using a visualization tool; and a feedback reflection means that collects feedback from users, reflects it in the AI ​​model, and improves the accuracy of future analyses.

Description

[Technical Field]

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

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

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

[0004] Currently, there are challenges in sharing and standardizing information in internal data management, and the large amount of data is scattered, making it difficult to make efficient decisions and improve operations.In addition, the process of collecting data from individual data sources and then preprocessing, integrating, governing, visualizing, and analyzing it is time-consuming and labor-intensive.This makes it difficult to utilize accurate and consistent data, and reduces the operational efficiency of the entire organization. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, and a feedback reflection means. Specifically, the data collection means collects data from multiple data sources and periodically retrieves the data using an API. The preprocessing means performs missing value imputation, duplicate data removal, and data format standardization for the collected data. The data integration means integrates the preprocessed data into a common data model, defines data relationships, and normalizes them. The data governance means uses AI to manage access rights, data classification, and privacy. The data visualization and analysis means extracts necessary data from an integrated database based on user requests, analyzes and predicts using AI, and displays the results using a visualization tool. The feedback reflection means collects user feedback and reflects it in the AI ​​model to improve the accuracy of future analyses. In this way, consistency and reliability of data management are ensured, and each department and individual is supported in making quick and accurate decisions.

[0006] "Data collection means" refers to a device or system that collects data from multiple data sources and periodically obtains data using an API.

[0007] "Preprocessing means" refers to a device or system for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0008] A "data integration means" is a device or system that integrates pre-processed data into a common data model, defines data relationships, and performs normalization.

[0009] A "data governance tool" is a device or system that uses AI to manage access rights, data classification, and privacy management.

[0010] A "data visualization and analysis means" is a device or system that extracts necessary data from an integrated database based on a user request, analyzes and predicts it using AI, and displays the results using a visualization tool.

[0011] A "feedback reflection means" is a device or system that collects feedback from users, reflects it in the AI ​​model, and improves the accuracy of analysis from the next time onwards. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] The present invention is a system designed to solve the problem of data management within a company. Details for implementing this system are described below.

[0034] Data collection methods

[0035] The server collects data from multiple data sources within the company (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, it can be configured to collect new sales data from the database every 10 minutes. This allows for timely data collection.

[0036] Pretreatment means

[0037] The server preprocesses the collected data by filling in missing values, removing duplicate data, and standardizing data formats. For example, it standardizes the date and time format and fills in missing sales data. This process maintains the quality of the data and ensures smooth subsequent processing.

[0038] Data Integration Methods

[0039] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs can associate sales data with customer data. This data integration is then stored in a data warehouse, where it serves as the basis for subsequent analysis and visualization.

[0040] Data Governance Measures

[0041] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, highly sensitive data is encrypted and access logs are recorded for traceability.

[0042] Data visualization and analysis tools

[0043] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their own terminal and request specific data analysis or visualization. For example, if a sales representative (user) wants to know sales trends, he or she sends the request from the terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal then displays the resulting analysis results as graphs and dashboards.

[0044] Feedback reflection method

[0045] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. The device then sends that feedback to the server, which then uses the collected feedback to improve the AI ​​model. This process continuously improves the system's analytical accuracy.

[0046] As a concrete example, let us look at the flow of how this system is used by a logistics department to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts logistics data from the integrated database and performs an analysis. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0047] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, and feedback reflection, thereby centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, you can set it to collect new sales data from the database every 10 minutes.

[0051] Step 2:

[0052] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[0053] Step 3:

[0054] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[0055] Step 4:

[0056] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[0057] Step 5:

[0058] Users access the system from their devices and make requests for specific data visualization or analysis. For example, a sales representative requests a sales trend report. The device sends the request to the server.

[0059] Step 6:

[0060] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[0061] Step 7:

[0062] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[0063] Step 8:

[0064] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[0065] Step 9:

[0066] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[0067] Example 1

[0068] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0069] Modern companies are required to efficiently collect and integrate data from multiple sources, then analyze and visualize it. However, many challenges exist, including the handling of missing and duplicate data, the unification of multiple data formats, and the complexity of access rights and privacy management. Furthermore, existing systems lack a means to centrally and efficiently resolve these challenges, which can lead to a decline in data quality and management efficiency. The purpose of this invention is to solve these challenges and improve the accuracy and efficiency of data management and analysis.

[0070] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0071] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, and a feedback reflection means, which makes it possible to comprehensively manage the entire process from data collection to preprocessing, integration, governance, analysis, and feedback.

[0072] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using an API.

[0073] "Preprocessing means" refers to means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0074] A "data integration method" is a method for mapping data from different data sources into a unified schema and storing it in a data warehouse.

[0075] "Data governance measures" are measures that use AI to manage access rights, classify and encrypt data.

[0076] "Data visualization and analysis means" is a means for analyzing data in response to user requests and displaying it as graphs or dashboards.

[0077] "Feedback reflection means" refers to a means of collecting feedback from users and retraining and improving the generative AI model based on that feedback.

[0078] The present invention is a system for managing and analyzing data within a company, and has the following configuration.

[0079] Data collection methods

[0080] The server collects data from multiple data sources (e.g., sales database, logistics system, human resources database). Specifically, it connects to these data sources using APIs and periodically obtains the latest data. For example, the server is configured to collect new sales data from the database every 10 minutes. This collection method allows the latest data to be obtained in real time.

[0081] Pretreatment means

[0082] The server preprocesses the collected data. This includes filling in missing values, removing duplicate data, and standardizing the data format. For example, the date and time format is standardized to "YYYY-MM-DD HH:MM:SS," and missing data is filled in using the previous value or an appropriate default value. This preprocessing maintains the quality of the data and ensures smooth subsequent processing.

[0083] Data Integration Methods

[0084] The server integrates the preprocessed data into a common data model. This involves mapping data collected from different data sources to a unified schema and storing it in a data warehouse. For example, to link sales data and customer data, a customer ID is used as a common key. This integration allows data from different data sources to be managed centrally.

[0085] Data Governance Measures

[0086] The server uses AI to implement data governance, including access rights management, data classification, and encryption. For example, certain business personnel are only allowed to access data related to their department, and highly confidential data is encrypted and access logs are recorded. This ensures data security and privacy.

[0087] Data visualization and analysis tools

[0088] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their terminal and request specific data analysis or visualization. For example, if a sales representative wants to know "sales trends over the past six months," they send the request from their terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using a generative AI model. The resulting analysis results are displayed on the terminal as graphs and dashboards.

[0089] Feedback reflection method

[0090] Users can provide feedback on the displayed analysis results. For example, an accountant can comment on inaccuracies in the income and expenditure analysis results. The device then sends this feedback to the server, which then retrains and improves the generative AI model based on the collected feedback. This allows the system's analytical accuracy to continuously improve.

[0091] Specific examples

[0092] For example, let us look at the process by which a logistics department uses this system to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts and analyzes logistics data from the integrated database. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0093] Prompt Sentence Examples

[0094] Example 1:

[0095] "Using sales data and customer data, please analyze sales trends over the past six months and display them in a graph."

[0096] Example 2:

[0097] "Calculate optimized delivery routes based on logistics data and generate a report that displays the results on a dashboard."

[0098] Example 3:

[0099] "Use your HR data to generate reports on employee attendance, highlighting departments with particularly high absenteeism."

[0100] By using such prompts, the user can give specific instructions to the system and efficiently obtain the required information.

[0101] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0102] Step 1:

[0103] The server connects to multiple data sources and collects data. Specifically, it periodically retrieves the latest data from each data source using APIs. The input is the API endpoint and authentication information of each data source. The output is the collected raw data. For example, the server retrieves new sales data from a sales database every 10 minutes.

[0104] Step 2:

[0105] The server preprocesses the collected raw data. Preprocessing includes filling in missing values, removing duplicate data, and standardizing the data format. The raw data collected in step 1 is used as input. Specific operations include, for example, filling in missing sales data with previous data or average values, removing duplicate customer records, and standardizing the date and time format to "YYYY-MM-DD HH:MM:SS". The output is clean data that has been preprocessed.

[0106] Step 3:

[0107] The server integrates the pre-processed data into a common data model. In this process, data from different data sources is mapped to a unified schema and stored in a data warehouse. The input is the clean data obtained in step 2. Specifically, the server integrates sales data and customer data using customer ID as a key. The output is an integrated dataset stored in the data warehouse.

[0108] Step 4:

[0109] The server uses AI to implement data governance, including managing access rights, classifying and encrypting data. The input is the dataset integrated in step 3. Specific operations include granting access to department-related data to specific business personnel, encrypting confidential data, and recording access logs. The output is a securely managed data ecosystem.

[0110] Step 5:

[0111] A user accesses the system from their device and requests a specific data analysis or visualization. The input is the user's request. For example, the user requests "Show sales trends for the past six months." The output is the request being sent to the server.

[0112] Step 6:

[0113] The server analyzes the data according to the user's request. The input is the request sent in step 5 and the data integrated in step 3. Specifically, it uses a generative AI model to perform the specified analysis. For example, it analyzes sales trends and obtains the results. The output is the analysis results.

[0114] Step 7:

[0115] The terminal visualizes the analysis results sent from the server. The input is the analysis results obtained in step 6. Specifically, the terminal displays the results as graphs or dashboards. The output is visual feedback provided to the user.

[0116] Step 8:

[0117] The user provides feedback on the displayed analysis results. The input is the user providing specific feedback. For example, the user may comment on "inaccuracies in the income and expenditure analysis results." The output is the feedback being sent from the terminal to the server.

[0118] Step 9:

[0119] The server retrains and improves the generative AI model based on the collected feedback. The input is the feedback sent by the user. The specific operation is to retrain the AI ​​model to improve the accuracy of the next analysis. The output is an improved AI model.

[0120] (Application example 1)

[0121] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0122] Modern logistics centers require the management of massive amounts of data and efficient operation. Manually collecting and managing data by staff is inefficient, time-consuming, and carries a high risk of human error. Furthermore, data analysis and efficiency proposals based on the results are often not carried out in a timely manner, making it difficult for on-site managers to make quick decisions. Furthermore, there is a need for real-time situational awareness and continuous system improvement based on feedback.

[0123] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0124] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for proposing efficiency improvements, and a dashboard display means. This enables the logistics center to efficiently carry out a series of processes, including automatic data collection, preprocessing, integration, governance, visualization and analysis, and feedback reflection, thereby realizing real-time situation understanding and rapid decision-making. In addition, efficiency suggestions based on AI analysis support optimal logistics operations.

[0125] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using APIs, updating each logistics process in real time.

[0126] The "preprocessing means" is a means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats, and also for implementing proposals for improving the efficiency of logistics data.

[0127] A "data integration method" is a method for mapping data collected from different data sources to a unified schema, defining the relationships between the data, and integrating them into an integrated data model.

[0128] "Data governance measures" are measures that use AI to manage data access rights, classify data, and protect privacy, encrypting highly sensitive data and recording access logs.

[0129] "Data visualization and analysis means" refers to a means of extracting relevant data from an integrated database based on a user's request, analyzing it using an AI model, and displaying the results to the user as graphs or dashboards.

[0130] "Feedback reflection means" refers to a means of collecting user feedback and using it to improve the AI ​​model and the entire system.

[0131] "Real-time data collection means" refers to a means for collecting data from each system within the logistics center in real time and updating it immediately.

[0132] The "efficiency proposal method" is a method that uses AI models to make logistics optimization proposals based on collected and preprocessed data.

[0133] The "dashboard display means" is a means for visualizing data in real time and visually displaying each process and its status at the logistics center.

[0134] To implement this invention, it is necessary to build a system for use in a logistics center, which includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for suggesting efficiency improvements, and a dashboard display means.

[0135] Hardware and software configuration

[0136] Server: The main computing unit that handles databases, AI model training and prediction, and data integration and preprocessing. Specifically, it uses SQLite for the database and Scikit-learn for AI model training.

[0137] Client terminal: A smartphone or tablet used by logistics center staff to visualize data and input feedback.

[0138] Data collection methods

[0139] The server collects data from each system in the distribution center in real time and updates it periodically. For example, it obtains data from sales databases and personnel databases through APIs. This collected data is then stored in a database.

[0140] Pretreatment means

[0141] The server performs missing value imputation, duplicate data removal, and data format standardization for the collected data. Pandas is used as a data preprocessing tool to ensure data quality.

[0142] Data Integration Methods

[0143] The server maps the pre-processed data into a unified schema and connects data from different data sources (for example, linking customer IDs with order IDs to associate sales data with customer data). This combined data is then stored in a data warehouse.

[0144] Data Governance Measures

[0145] The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are only given access to relevant data, confidential data is encrypted, and access logs are recorded.

[0146] Data visualization and analysis tools

[0147] The device visualizes data and displays analysis results in response to user requests. The server extracts the relevant data from the integrated database and analyzes it using an AI model. Users can view the resulting dashboards and graphs on their device.

[0148] Feedback reflection method

[0149] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server, and the AI ​​model and the entire system are improved based on the collected feedback.

[0150] Real-time data collection methods

[0151] Data is collected in real time from each system within the logistics center and updated immediately, allowing operations to be managed based on the latest information at all times.

[0152] Efficiency improvement proposal methods

[0153] The server uses AI models to make logistics optimization suggestions based on the collected and pre-processed data, such as displaying optimized delivery routes and inventory management alerts.

[0154] Dashboard display method

[0155] The terminal visualizes data in real time, visually displaying each process and its status in the logistics center.

[0156] Examples and prompts

[0157] For example, if a user enters a prompt such as "Please propose the optimal delivery schedule for next week using the latest logistics information for optimizing delivery routes," the server will extract the necessary data from the integrated database, analyze and optimize it using an AI model, and display the results on the terminal as a dashboard, allowing the logistics center manager to efficiently manage operations.

[0158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0159] Step 1:

[0160] Data collection: The server collects data from each system in the distribution center (e.g., sales database, human resources database) through API. In this collection process, new data is obtained every 10 minutes. The input is raw data from each database, and the output is raw data stored on the server.

[0161] Step 2:

[0162] Data preprocessing: The server completes the collected data by filling in missing values, removing duplicate data, and standardizing the data format. For example, it standardizes the date format and completes missing sales data. The input is the collected raw data, and the output is the preprocessed data.

[0163] Step 3:

[0164] Data Integration: The server maps the pre-processed data to a unified schema and integrates data from different sources. For example, linking customer IDs with order IDs to associate sales data with customer data. The input is the pre-processed data, and the output is the data transformed into a unified data model.

[0165] Step 4:

[0166] Implementing data governance: The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are granted access only to relevant data, confidential data is encrypted, and access logs are recorded. The input is data management policies and database configuration information, and the output is data with access restrictions applied.

[0167] Step 5:

[0168] Data visualization and analysis: The terminal extracts data from the server based on the user's request and performs analysis. The server uses the integrated data to perform analysis using an AI model (Scikit-learn). The results are displayed on the terminal as graphs and dashboards. The input is the user's request and the integrated database, and the output is the analysis results displayed to the user.

[0169] Step 6:

[0170] Feedback reflection: The user provides feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server and used to improve the AI ​​model. The input is the user's feedback, and the output is the parameters of the improved AI model.

[0171] Step 7:

[0172] Real-time data collection: The server collects data from each system in the distribution center in real time and updates it immediately. The input is real-time data from each system, and the output is the latest data stored on the server.

[0173] Step 8:

[0174] Efficiency proposals: The server uses an AI model based on the collected and preprocessed data to make logistics optimization proposals. For example, optimized delivery routes and inventory management alerts are provided to the user. The inputs are the preprocessed data and the AI ​​model, and the output is the optimization proposals.

[0175] Step 9:

[0176] Dashboard display: The terminal visualizes data in real time, visually displaying each process and its status in the distribution center. The input is real-time data and analysis results, and the output is a dashboard that users can access.

[0177] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0178] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and an emotion engine that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system are described below.

[0179] Data collection methods

[0180] The server collects data from multiple internal data sources (e.g., sales database, logistics system, human resources database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, by configuring it to retrieve new sales data from the database every hour, it becomes possible to collect timely data.

[0181] Pretreatment means

[0182] The server preprocesses the collected data. Specifically, it imputes missing values, removes duplicate data, and standardizes data formats. For example, it standardizes the date and time format and imputes missing sales data with the average value. This process maintains the quality of the data and ensures smooth subsequent processing.

[0183] Data Integration Methods

[0184] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs associates sales data with customer data. This data is then stored in a data warehouse and serves as the basis for subsequent analysis and visualization.

[0185] Data Governance Measures

[0186] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, sensitive data is encrypted and access logs are recorded for traceability.

[0187] Data visualization and analysis tools

[0188] The terminal performs data visualization and analysis in response to user requests. Users can access the system from their terminal and request specific data analysis and visualization. For example, if a sales department representative (user) requests a sales trend report, the terminal sends the request to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal displays the resulting analysis results as graphs and dashboards.

[0189] Feedback reflection method

[0190] Users can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the AI ​​model to improve the accuracy of future analyses.

[0191] Emotion Engine

[0192] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the AI ​​model, contributing to improved analysis accuracy and user experience in future analyses.

[0193] As a concrete example, when a sales representative uses this system to check sales trends, they send a request to the system from their device. The server extracts the data and sends the analysis results to their device. The representative then checks the results and expresses their feelings of dissatisfaction or joy. This emotional data is analyzed by the emotion engine, and this feedback and emotional data is reflected in the AI ​​model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[0194] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, emotion recognition, and feedback reflection, centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[0195] The processing flow will be explained below.

[0196] Step 1:

[0197] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, you can set it to retrieve new sales data from the database every hour.

[0198] Step 2:

[0199] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[0200] Step 3:

[0201] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[0202] Step 4:

[0203] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[0204] Step 5:

[0205] Users access the system from their own devices and make requests for specific data visualization or analysis. For example, a sales representative requests a "sales trend report." The device then sends the request to the server.

[0206] Step 6:

[0207] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[0208] Step 7:

[0209] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[0210] Step 8:

[0211] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[0212] Step 9:

[0213] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[0214] Step 10:

[0215] The server uses an emotion engine to recognize the user's emotions. For example, when a user enters feedback, it analyzes text and voice data to identify the user's emotions. This emotion data is collected and reflected in the AI ​​model. This will further improve future analyses and the user experience.

[0216] Example 2

[0217] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0218] In conventional data management systems, data collection from each data source, data preprocessing, data integration, data governance, data visualization and analysis, and user feedback were all performed separately, reducing the efficiency of the entire system. Furthermore, analysis results and feedback provided without considering user sentiment could degrade the quality of the user experience. To address these issues, a system is needed that centralizes in-house data management and decision-making, improving operational efficiency and accuracy.

[0219] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0220] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to efficiently collect data from each data source and execute preprocessing, integration, governance, visualization, and analysis as a series of processes. Furthermore, by recognizing the user's emotions and reflecting them in feedback, it is possible to improve the user experience and improve the accuracy of subsequent analyses.

[0221] "Data collection means" refers to a means for collecting data from multiple data sources within the company and obtaining the data periodically using an API.

[0222] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0223] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[0224] "Data governance measures" are measures for setting data access permissions, classifying data and protecting privacy, and recording data access logs.

[0225] "Data visualization and analysis means" refers to means for visualizing data in response to user requests and performing data analysis using AI models.

[0226] "Feedback reflection means" refers to a means for collecting feedback provided by users and reflecting it in the AI ​​model to improve the accuracy of analysis from the next time onwards.

[0227] An "emotion recognition means" is a means for analyzing a user's input, voice, and facial expressions to identify emotions and provide feedback based on those emotions.

[0228] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and emotion recognition means that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system will be described below.

[0229] Data collection methods

[0230] The server collects data from multiple internal data sources (sales database, logistics system, HR database, etc.). It connects to each data source using APIs and periodically retrieves the latest data. This data collection is automated, and is set to retrieve new sales data from the database every hour, for example.

[0231] Pretreatment means

[0232] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes data formats. For example, standardizing the date and time format and complementing missing sales data with the average value ensures data quality and ensures smooth subsequent processing.

[0233] Data Integration Methods

[0234] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and clarifying data relationships (for example, linking customer IDs to order IDs to associate sales data with customer data). This data is then stored in a data warehouse, forming the basis for subsequent analysis and visualization.

[0235] Data Governance Measures

[0236] The server uses AI to enforce data governance, including access rights management, data classification, and privacy protection. For example, specific personnel are only allowed access to data relevant to their job. Sensitive data is encrypted and all access logs are kept for traceability.

[0237] Data visualization and analysis tools

[0238] The terminal visualizes and analyzes data based on the user's request. The user accesses the system from the terminal and requests specific data analysis or visualization. For example, when a sales representative requests a sales trend report, the terminal sends the request to the server. The server extracts data from the integrated database, performs analysis using a generative AI model, and sends the results to the terminal. The terminal displays the results as graphs and dashboards.

[0239] Feedback reflection method

[0240] The user can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the generative AI model, thereby improving the accuracy of future analyses.

[0241] emotion recognition means

[0242] The server uses emotion recognition means to recognize the user's emotions. The emotion recognition means analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the generative AI model, contributing to improved analysis accuracy and user experience in future analyses.

[0243] Specific examples

[0244] As a concrete example, when a sales representative uses this system to check sales trends, they send a request from their terminal to the system. The server extracts the data and sends the analysis results to the terminal. The representative then checks the results and expresses their feedback and emotions about them. This emotional data is analyzed by the emotion recognition means, and the feedback and emotional data are reflected in the generative AI model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[0245] Prompt Sentence Examples

[0246] "Get sales data, analyze and visualize sales trends over the past six months. Also, collect feedback on the analysis results, analyze user sentiment, and reflect it in your next project."

[0247] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0248] Step 1:

[0249] The server connects to multiple internal data sources (sales database, logistics system, human resources database, etc.) and collects data. API endpoints and authentication information are required as input. The server periodically calls the API to obtain data and saves it in local storage. For example, new sales data is obtained from the sales database every hour. The collected data in JSON format is saved as output. Specific operations include sending API requests and receiving response data.

[0250] Step 2:

[0251] The server performs preprocessing on the collected data. The collected JSON data is required as input. The server performs processes to impute missing values, remove duplicate data, and standardize data formats. For example, it standardizes the date and time format to "YYYY-MM-DD HH:MM:SS" and imputes missing sales data with the average value. A preprocessed data frame is generated as output. Specific operations include data cleansing and format conversion.

[0252] Step 3:

[0253] The server integrates the preprocessed data into a common data model. It requires a preprocessed data frame as input. The server maps data from different data sources into a unified schema and defines data relationships. For example, it associates sales data with customer data by linking customer IDs with order IDs. As output, it generates an integrated dataset and stores it in the data warehouse. Specific actions include write operations to the database.

[0254] Step 4:

[0255] The server uses AI to apply data governance. It requires an integrated dataset and access permission information as input. The server sets data access permissions and performs data classification and privacy protection. For example, it may grant access permission only to data related to a specific department. Sensitive data is encrypted and an access log is recorded. The output is a governed dataset and access log. Specific operations include setting access control lists and encryption.

[0256] Step 5:

[0257] The terminal visualizes and analyzes data based on the user's request. As input, it requires the user's request and a governed dataset. For example, if a user requests a sales trend report, the terminal sends the request to the server. The server performs data analysis using a generative AI model and sends the results to the terminal. As output, visualized graphs and dashboards are generated and displayed to the user. Specific operations include data extraction and rendering of analysis results.

[0258] Step 6:

[0259] The user provides feedback on the displayed analysis results. The analysis results and user feedback are required as input. The device sends the feedback to the server. The server collects the feedback and reflects it in the generative AI model to improve the accuracy of future analyses. An updated AI model is generated as output. Specific operations include collecting feedback data and retraining the model.

[0260] Step 7:

[0261] The server uses emotion recognition means to recognize the user's emotions. The input required is the user's input content, voice, and facial expression data. The server applies an emotion recognition algorithm to identify the user's emotions. For example, when a user enters a rating into the system, the server analyzes the emotion from the content and voice. The output is the user's emotional state, and appropriate feedback is provided based on that. Specific operations include emotion analysis and feedback generation.

[0262] (Application example 2)

[0263] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0264] In conventional factory data management systems, the processes of data collection, preprocessing, integration, governance, visualization, analysis, and feedback reflection are not integrated, making it difficult to analyze data and reflect feedback in real time.In addition, there is no system that analyzes workers' emotions and reflects them in feedback, so there are still challenges in improving the working environment.

[0265] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to collect, preprocess, and integrate data in real time from multiple data sources within the factory. In addition, data visualization and analysis can be performed based on the integrated data, and feedback can be reflected immediately. Furthermore, by using the emotion recognition means, it is possible to analyze the emotions of workers and use this information to improve the work environment.

[0266] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining the latest data using an API.

[0267] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0268] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[0269] "Data governance measures" are measures that use AI to manage access rights, classify data, and protect privacy.

[0270] "Data visualization and analysis means" refers to a means of visualizing data in response to user requests and analyzing it using an AI model.

[0271] The "feedback reflection means" is a means for collecting feedback from users on the displayed analysis results and reflecting that feedback in the AI ​​model.

[0272] An "emotion recognition means" is a means of analyzing a user's input, voice, and facial expressions to identify emotions and reflect them in the system.

[0273] This invention relates to a data management system for industrial robots, and provides a system that efficiently performs a series of processes from data collection to preprocessing, integration, governance, visualization, analysis, feedback reflection, and emotion recognition.

[0274] System Program

[0275] Specific program processing to realize each means is carried out separately for the server, terminal, and user.

[0276] Natural language explanations

[0277] 1. Data collection methods:

[0278] The server collects data from multiple data sources (such as each manufacturing process and machine in the factory). It connects to these data sources using APIs and periodically obtains the latest data. For example, operation data and quality data from each manufacturing line are collected every hour and sent to the server.

[0279] 2. Pretreatment methods:

[0280] The server processes the collected data by removing noise, formatting, and filling in missing values. It uses Python to standardize data formats and remove duplicate data. For example, it standardizes data in different formats for each production line and fills in missing quality data with the average value.

[0281] 3. Data integration methods:

[0282] The server integrates the preprocessed data into the AWS® data warehouse. Data from different data sources is mapped to a unified schema and data relationships are defined. For example, by linking manufacturing process IDs and machine IDs, operation data and quality data for each process can be associated.

[0283] 4. Data Governance Measures:

[0284] The server uses AI to manage access rights, classify data, and protect privacy. For example, quality control personnel can be granted access only to quality data and not to other data. Confidential data is also encrypted and access logs are recorded for traceability.

[0285] 5. Data visualization and analysis tools:

[0286] The device visualizes data in response to user requests and performs analysis using AI models. Power BI is used to display real-time factory operation status and anomaly detection on a dashboard. For example, when a manufacturing department employee requests a production line operation trend report, the device sends it to the server and displays the analysis results on the dashboard.

[0287] 6. Feedback methods:

[0288] Users can provide feedback on the displayed analysis results. The feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model to improve the accuracy of future analyses. For example, if a quality control officer comments on areas for improvement in anomaly detection results, these comments will be reflected in the next analysis.

[0289] 7. Emotion recognition means:

[0290] The server uses Azure® Cognitive Services to analyze the user's emotions. It identifies emotions from the user's input, voice, and facial expressions and reflects them as feedback. For example, when a worker enters an evaluation into the system, it recognizes emotions such as joy or stress from the input and voice and provides appropriate feedback.

[0291] Examples of specific examples and prompts

[0292] Robots in the factory collect operational data and send it to a server. The server uses Python scripts to preprocess the data, fill in missing values, and standardize the format. The preprocessed data is integrated in an AWS data warehouse, and various data sources are mapped. Azure Cognitive Services is used to create an emotion engine that analyzes feedback from workers and recognizes emotions such as joy and stress. Power BI is used to display real-time factory operation status on a dashboard, and workers are notified if an abnormality is detected.

[0293] Example prompt sentence:

[0294] "Devout a system that handles data collection, preprocessing, data integration, data governance, data visualization, feedback, and emotion recognition within the factory, and program it using Python, AWS, and Azure Cognitive Services. This will enable real-time monitoring of factory operation status, anomaly detection, and worker emotion analysis."

[0295] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0296] Step 1:

[0297] (Data Collection)

[0298] The server connects to each data source using an API to collect the requested data from multiple data sources. The input is operation data, quality data, and production progress data for each manufacturing process and machine in the factory. The output is the transfer of this data to the server. Specifically, the data collection program periodically sends requests to the API endpoint and stores the latest collected data on the server.

[0299] Step 2:

[0300] (Data preprocessing)

[0301] The server processes the collected raw data to improve its quality. The input is the raw data stored on the server. The output is preprocessed, cleaned data. Specifically, it performs operations such as imputing missing values ​​in the data with the mean value, removing duplicate data, and standardizing date formats. These data cleaning operations are performed using Python scripts.

[0302] Step 3:

[0303] (Data Integration)

[0304] The server integrates and centralizes the preprocessed data into a common data model. The input is the preprocessed data. The output is an integrated dataset. Specifically, using an AWS data warehouse or similar, the data provided from different data sources is mapped to a unified schema and linked based on keys such as manufacturing process IDs and machine IDs.

[0305] Step 4:

[0306] (Data Governance)

[0307] The server applies data governance to the integrated data using AI. The input is the integrated data set. The output is governance data that includes properly classified and encrypted data and access control information. Specifically, it sets data access rights, encrypts sensitive data, and records access logs. This is achieved using an access rights management system and encryption software.

[0308] Step 5:

[0309] (Data Visualization and Analysis)

[0310] The terminal visualizes data in response to user requests and performs analysis using an AI model. The input is the integrated dataset and the user request. The output is the analysis results and visualized data. Specifically, Power BI is used to display factory operation status and anomaly detection in real time on a dashboard. When a user requests analysis of specific data, it is sent to the server, which then analyzes it and sends the results to the terminal.

[0311] Step 6:

[0312] (Reflecting feedback)

[0313] The user provides feedback on the displayed analysis results. The input is the user's feedback. The output is the feedback results and data that will be reflected in the next analysis. Specifically, the feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model. This improves the accuracy of data analysis from the next time onwards.

[0314] Step 7:

[0315] (emotion recognition)

[0316] The server uses Azure Cognitive Services to analyze the user's emotions. The inputs are the user's input, voice, and facial expression data. The output is the analyzed emotional data. Specifically, when the user enters an evaluation or feedback to the system, the system analyzes the text and voice data to identify the user's emotional state (for example, joy or stress), and feeds the results back to the system.

[0317] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0318] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0319] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0320] [Second embodiment]

[0321] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0322] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0323] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0324] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0325] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0326] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0327] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0328] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0329] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0330] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0331] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0332] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0333] The present invention is a system designed to solve the problem of data management within a company. Details for implementing this system are described below.

[0334] Data collection methods

[0335] The server collects data from multiple data sources within the company (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, it can be configured to collect new sales data from the database every 10 minutes. This allows for timely data collection.

[0336] Pretreatment means

[0337] The server preprocesses the collected data by filling in missing values, removing duplicate data, and standardizing data formats. For example, it standardizes the date and time format and fills in missing sales data. This process maintains the quality of the data and ensures smooth subsequent processing.

[0338] Data Integration Methods

[0339] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs can associate sales data with customer data. This data integration is then stored in a data warehouse, where it serves as the basis for subsequent analysis and visualization.

[0340] Data Governance Measures

[0341] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, highly sensitive data is encrypted and access logs are recorded for traceability.

[0342] Data visualization and analysis tools

[0343] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their own terminal and request specific data analysis or visualization. For example, if a sales representative (user) wants to know sales trends, he or she sends the request from the terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal then displays the resulting analysis results as graphs and dashboards.

[0344] Feedback reflection method

[0345] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. The device then sends that feedback to the server, which then uses the collected feedback to improve the AI ​​model. This process continuously improves the system's analytical accuracy.

[0346] As a concrete example, let us look at the flow of how this system is used by a logistics department to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts logistics data from the integrated database and performs an analysis. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0347] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, and feedback reflection, thereby centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[0348] The processing flow will be explained below.

[0349] Step 1:

[0350] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, you can set it to collect new sales data from the database every 10 minutes.

[0351] Step 2:

[0352] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[0353] Step 3:

[0354] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[0355] Step 4:

[0356] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[0357] Step 5:

[0358] Users access the system from their devices and make requests for specific data visualization or analysis. For example, a sales representative requests a sales trend report. The device sends the request to the server.

[0359] Step 6:

[0360] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[0361] Step 7:

[0362] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[0363] Step 8:

[0364] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[0365] Step 9:

[0366] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[0367] Example 1

[0368] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0369] Modern companies are required to efficiently collect and integrate data from multiple sources, then analyze and visualize it. However, many challenges exist, including the handling of missing and duplicate data, the unification of multiple data formats, and the complexity of access rights and privacy management. Furthermore, existing systems lack a means to centrally and efficiently resolve these challenges, which can lead to a decline in data quality and management efficiency. The purpose of this invention is to solve these challenges and improve the accuracy and efficiency of data management and analysis.

[0370] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0371] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, and a feedback reflection means, which makes it possible to comprehensively manage the entire process from data collection to preprocessing, integration, governance, analysis, and feedback.

[0372] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using an API.

[0373] "Preprocessing means" refers to means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0374] A "data integration method" is a method for mapping data from different data sources into a unified schema and storing it in a data warehouse.

[0375] "Data governance measures" are measures that use AI to manage access rights, classify and encrypt data.

[0376] "Data visualization and analysis means" is a means for analyzing data in response to user requests and displaying it as graphs or dashboards.

[0377] "Feedback reflection means" refers to a means of collecting feedback from users and retraining and improving the generative AI model based on that feedback.

[0378] The present invention is a system for managing and analyzing data within a company, and has the following configuration.

[0379] Data collection methods

[0380] The server collects data from multiple data sources (e.g., sales database, logistics system, human resources database). Specifically, it connects to these data sources using APIs and periodically obtains the latest data. For example, the server is configured to collect new sales data from the database every 10 minutes. This collection method allows the latest data to be obtained in real time.

[0381] Pretreatment means

[0382] The server preprocesses the collected data. This includes filling in missing values, removing duplicate data, and standardizing the data format. For example, the date and time format is standardized to "YYYY-MM-DD HH:MM:SS," and missing data is filled in using the previous value or an appropriate default value. This preprocessing maintains the quality of the data and ensures smooth subsequent processing.

[0383] Data Integration Methods

[0384] The server integrates the preprocessed data into a common data model. This involves mapping data collected from different data sources to a unified schema and storing it in a data warehouse. For example, to link sales data and customer data, a customer ID is used as a common key. This integration allows data from different data sources to be managed centrally.

[0385] Data Governance Measures

[0386] The server uses AI to implement data governance, including access rights management, data classification, and encryption. For example, certain business personnel are only allowed to access data related to their department, and highly confidential data is encrypted and access logs are recorded. This ensures data security and privacy.

[0387] Data visualization and analysis tools

[0388] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their terminal and request specific data analysis or visualization. For example, if a sales representative wants to know "sales trends over the past six months," they send the request from their terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using a generative AI model. The resulting analysis results are displayed on the terminal as graphs and dashboards.

[0389] Feedback reflection method

[0390] Users can provide feedback on the displayed analysis results. For example, an accountant can comment on inaccuracies in the income and expenditure analysis results. The device then sends this feedback to the server, which then retrains and improves the generative AI model based on the collected feedback. This allows the system's analytical accuracy to continuously improve.

[0391] Specific examples

[0392] For example, let us look at the process by which a logistics department uses this system to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts and analyzes logistics data from the integrated database. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0393] Prompt Sentence Examples

[0394] Example 1:

[0395] "Using sales data and customer data, please analyze sales trends over the past six months and display them in a graph."

[0396] Example 2:

[0397] "Calculate optimized delivery routes based on logistics data and generate a report that displays the results on a dashboard."

[0398] Example 3:

[0399] "Use your HR data to generate reports on employee attendance, highlighting departments with particularly high absenteeism."

[0400] By using such prompts, the user can give specific instructions to the system and efficiently obtain the required information.

[0401] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0402] Step 1:

[0403] The server connects to multiple data sources and collects data. Specifically, it periodically retrieves the latest data from each data source using APIs. The input is the API endpoint and authentication information of each data source. The output is the collected raw data. For example, the server retrieves new sales data from a sales database every 10 minutes.

[0404] Step 2:

[0405] The server preprocesses the collected raw data. Preprocessing includes filling in missing values, removing duplicate data, and standardizing the data format. The raw data collected in step 1 is used as input. Specific operations include, for example, filling in missing sales data with previous data or average values, removing duplicate customer records, and standardizing the date and time format to "YYYY-MM-DD HH:MM:SS". The output is clean data that has been preprocessed.

[0406] Step 3:

[0407] The server integrates the pre-processed data into a common data model. In this process, data from different data sources is mapped to a unified schema and stored in a data warehouse. The input is the clean data obtained in step 2. Specifically, the server integrates sales data and customer data using customer ID as a key. The output is an integrated dataset stored in the data warehouse.

[0408] Step 4:

[0409] The server uses AI to implement data governance, including managing access rights, classifying and encrypting data. The input is the dataset integrated in step 3. Specific operations include granting access to department-related data to specific business personnel, encrypting confidential data, and recording access logs. The output is a securely managed data ecosystem.

[0410] Step 5:

[0411] A user accesses the system from their device and requests a specific data analysis or visualization. The input is the user's request. For example, the user requests "Show sales trends for the past six months." The output is the request being sent to the server.

[0412] Step 6:

[0413] The server analyzes the data according to the user's request. The input is the request sent in step 5 and the data integrated in step 3. Specifically, it uses a generative AI model to perform the specified analysis. For example, it analyzes sales trends and obtains the results. The output is the analysis results.

[0414] Step 7:

[0415] The terminal visualizes the analysis results sent from the server. The input is the analysis results obtained in step 6. Specifically, the terminal displays the results as graphs or dashboards. The output is visual feedback provided to the user.

[0416] Step 8:

[0417] The user provides feedback on the displayed analysis results. The input is the user providing specific feedback. For example, the user may comment on "inaccuracies in the income and expenditure analysis results." The output is the feedback being sent from the terminal to the server.

[0418] Step 9:

[0419] The server retrains and improves the generative AI model based on the collected feedback. The input is the feedback sent by the user. The specific operation is to retrain the AI ​​model to improve the accuracy of the next analysis. The output is an improved AI model.

[0420] (Application example 1)

[0421] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0422] Modern logistics centers require the management of massive amounts of data and efficient operation. Manually collecting and managing data by staff is inefficient, time-consuming, and carries a high risk of human error. Furthermore, data analysis and efficiency proposals based on the results are often not carried out in a timely manner, making it difficult for on-site managers to make quick decisions. Furthermore, there is a need for real-time situational awareness and continuous system improvement based on feedback.

[0423] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0424] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for proposing efficiency improvements, and a dashboard display means. This enables the logistics center to efficiently carry out a series of processes, including automatic data collection, preprocessing, integration, governance, visualization and analysis, and feedback reflection, thereby realizing real-time situation understanding and rapid decision-making. In addition, efficiency suggestions based on AI analysis support optimal logistics operations.

[0425] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using APIs, updating each logistics process in real time.

[0426] The "preprocessing means" is a means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats, and also for implementing proposals for improving the efficiency of logistics data.

[0427] A "data integration method" is a method for mapping data collected from different data sources to a unified schema, defining the relationships between the data, and integrating them into an integrated data model.

[0428] "Data governance measures" are measures that use AI to manage data access rights, classify data, and protect privacy, encrypting highly sensitive data and recording access logs.

[0429] "Data visualization and analysis means" refers to a means of extracting relevant data from an integrated database based on a user's request, analyzing it using an AI model, and displaying the results to the user as graphs or dashboards.

[0430] "Feedback reflection means" refers to a means of collecting user feedback and using it to improve the AI ​​model and the entire system.

[0431] "Real-time data collection means" refers to a means for collecting data from each system within the logistics center in real time and updating it immediately.

[0432] The "efficiency proposal method" is a method that uses AI models to make logistics optimization proposals based on collected and preprocessed data.

[0433] The "dashboard display means" is a means for visualizing data in real time and visually displaying each process and its status at the logistics center.

[0434] To implement this invention, it is necessary to build a system for use in a logistics center, which includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for suggesting efficiency improvements, and a dashboard display means.

[0435] Hardware and software configuration

[0436] Server: The main computing unit that handles databases, AI model training and prediction, and data integration and preprocessing. Specifically, it uses SQLite for the database and Scikit-learn for AI model training.

[0437] Client terminal: A smartphone or tablet used by logistics center staff to visualize data and input feedback.

[0438] Data collection methods

[0439] The server collects data from each system in the distribution center in real time and updates it periodically. For example, it obtains data from sales databases and personnel databases through APIs. This collected data is then stored in a database.

[0440] Pretreatment means

[0441] The server performs missing value imputation, duplicate data removal, and data format standardization for the collected data. Pandas is used as a data preprocessing tool to ensure data quality.

[0442] Data Integration Methods

[0443] The server maps the pre-processed data into a unified schema and connects data from different data sources (for example, linking customer IDs with order IDs to associate sales data with customer data). This combined data is then stored in a data warehouse.

[0444] Data Governance Measures

[0445] The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are only given access to relevant data, confidential data is encrypted, and access logs are recorded.

[0446] Data visualization and analysis tools

[0447] The device visualizes data and displays analysis results in response to user requests. The server extracts the relevant data from the integrated database and analyzes it using an AI model. Users can view the resulting dashboards and graphs on their device.

[0448] Feedback reflection method

[0449] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server, and the AI ​​model and the entire system are improved based on the collected feedback.

[0450] Real-time data collection methods

[0451] Data is collected in real time from each system within the logistics center and updated immediately, allowing operations to be managed based on the latest information at all times.

[0452] Efficiency improvement proposal methods

[0453] The server uses AI models to make logistics optimization suggestions based on the collected and pre-processed data, such as displaying optimized delivery routes and inventory management alerts.

[0454] Dashboard display method

[0455] The terminal visualizes data in real time, visually displaying each process and its status in the logistics center.

[0456] Examples and prompts

[0457] For example, if a user enters a prompt such as "Please propose the optimal delivery schedule for next week using the latest logistics information for optimizing delivery routes," the server will extract the necessary data from the integrated database, analyze and optimize it using an AI model, and display the results on the terminal as a dashboard, allowing the logistics center manager to efficiently manage operations.

[0458] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0459] Step 1:

[0460] Data collection: The server collects data from each system in the distribution center (e.g., sales database, human resources database) through API. In this collection process, new data is obtained every 10 minutes. The input is raw data from each database, and the output is raw data stored on the server.

[0461] Step 2:

[0462] Data preprocessing: The server completes the collected data by filling in missing values, removing duplicate data, and standardizing the data format. For example, it standardizes the date format and completes missing sales data. The input is the collected raw data, and the output is the preprocessed data.

[0463] Step 3:

[0464] Data Integration: The server maps the pre-processed data to a unified schema and integrates data from different sources. For example, linking customer IDs with order IDs to associate sales data with customer data. The input is the pre-processed data, and the output is the data transformed into a unified data model.

[0465] Step 4:

[0466] Implementing data governance: The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are granted access only to relevant data, confidential data is encrypted, and access logs are recorded. The input is data management policies and database configuration information, and the output is data with access restrictions applied.

[0467] Step 5:

[0468] Data visualization and analysis: The terminal extracts data from the server based on the user's request and performs analysis. The server uses the integrated data to perform analysis using an AI model (Scikit-learn). The results are displayed on the terminal as graphs and dashboards. The input is the user's request and the integrated database, and the output is the analysis results displayed to the user.

[0469] Step 6:

[0470] Feedback reflection: The user provides feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server and used to improve the AI ​​model. The input is the user's feedback, and the output is the parameters of the improved AI model.

[0471] Step 7:

[0472] Real-time data collection: The server collects data from each system in the distribution center in real time and updates it immediately. The input is real-time data from each system, and the output is the latest data stored on the server.

[0473] Step 8:

[0474] Efficiency proposals: The server uses an AI model based on the collected and preprocessed data to make logistics optimization proposals. For example, optimized delivery routes and inventory management alerts are provided to the user. The inputs are the preprocessed data and the AI ​​model, and the output is the optimization proposals.

[0475] Step 9:

[0476] Dashboard display: The terminal visualizes data in real time, visually displaying each process and its status in the distribution center. The input is real-time data and analysis results, and the output is a dashboard that users can access.

[0477] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0478] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and an emotion engine that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system are described below.

[0479] Data collection methods

[0480] The server collects data from multiple internal data sources (e.g., sales database, logistics system, human resources database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, by configuring it to retrieve new sales data from the database every hour, it becomes possible to collect timely data.

[0481] Pretreatment means

[0482] The server preprocesses the collected data. Specifically, it imputes missing values, removes duplicate data, and standardizes data formats. For example, it standardizes the date and time format and imputes missing sales data with the average value. This process maintains the quality of the data and ensures smooth subsequent processing.

[0483] Data Integration Methods

[0484] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs associates sales data with customer data. This data is then stored in a data warehouse and serves as the basis for subsequent analysis and visualization.

[0485] Data Governance Measures

[0486] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, sensitive data is encrypted and access logs are recorded for traceability.

[0487] Data visualization and analysis tools

[0488] The terminal performs data visualization and analysis in response to user requests. Users can access the system from their terminal and request specific data analysis and visualization. For example, if a sales department representative (user) requests a sales trend report, the terminal sends the request to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal displays the resulting analysis results as graphs and dashboards.

[0489] Feedback reflection method

[0490] Users can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the AI ​​model to improve the accuracy of future analyses.

[0491] Emotion Engine

[0492] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the AI ​​model, contributing to improved analysis accuracy and user experience in future analyses.

[0493] As a concrete example, when a sales representative uses this system to check sales trends, they send a request to the system from their device. The server extracts the data and sends the analysis results to their device. The representative then checks the results and expresses their feelings of dissatisfaction or joy. This emotional data is analyzed by the emotion engine, and this feedback and emotional data is reflected in the AI ​​model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[0494] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, emotion recognition, and feedback reflection, centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[0495] The processing flow will be explained below.

[0496] Step 1:

[0497] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, you can set it to retrieve new sales data from the database every hour.

[0498] Step 2:

[0499] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[0500] Step 3:

[0501] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[0502] Step 4:

[0503] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[0504] Step 5:

[0505] Users access the system from their own devices and make requests for specific data visualization or analysis. For example, a sales representative requests a "sales trend report." The device then sends the request to the server.

[0506] Step 6:

[0507] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[0508] Step 7:

[0509] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[0510] Step 8:

[0511] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[0512] Step 9:

[0513] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[0514] Step 10:

[0515] The server uses an emotion engine to recognize the user's emotions. For example, when a user enters feedback, it analyzes text and voice data to identify the user's emotions. This emotion data is collected and reflected in the AI ​​model. This will further improve future analyses and the user experience.

[0516] Example 2

[0517] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0518] In conventional data management systems, data collection from each data source, data preprocessing, data integration, data governance, data visualization and analysis, and user feedback were all performed separately, reducing the efficiency of the entire system. Furthermore, analysis results and feedback provided without considering user sentiment could degrade the quality of the user experience. To address these issues, a system is needed that centralizes in-house data management and decision-making, improving operational efficiency and accuracy.

[0519] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0520] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to efficiently collect data from each data source and execute preprocessing, integration, governance, visualization, and analysis as a series of processes. Furthermore, by recognizing the user's emotions and reflecting them in feedback, it is possible to improve the user experience and improve the accuracy of subsequent analyses.

[0521] "Data collection means" refers to a means for collecting data from multiple data sources within the company and obtaining the data periodically using an API.

[0522] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0523] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[0524] "Data governance measures" are measures for setting data access permissions, classifying data and protecting privacy, and recording data access logs.

[0525] "Data visualization and analysis means" refers to means for visualizing data in response to user requests and performing data analysis using AI models.

[0526] "Feedback reflection means" refers to a means for collecting feedback provided by users and reflecting it in the AI ​​model to improve the accuracy of analysis from the next time onwards.

[0527] An "emotion recognition means" is a means for analyzing a user's input, voice, and facial expressions to identify emotions and provide feedback based on those emotions.

[0528] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and emotion recognition means that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system will be described below.

[0529] Data collection methods

[0530] The server collects data from multiple internal data sources (sales database, logistics system, HR database, etc.). It connects to each data source using APIs and periodically retrieves the latest data. This data collection is automated, and is set to retrieve new sales data from the database every hour, for example.

[0531] Pretreatment means

[0532] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes data formats. For example, standardizing the date and time format and complementing missing sales data with the average value ensures data quality and ensures smooth subsequent processing.

[0533] Data Integration Methods

[0534] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and clarifying data relationships (for example, linking customer IDs to order IDs to associate sales data with customer data). This data is then stored in a data warehouse, forming the basis for subsequent analysis and visualization.

[0535] Data Governance Measures

[0536] The server uses AI to enforce data governance, including access rights management, data classification, and privacy protection. For example, specific personnel are only allowed access to data relevant to their job. Sensitive data is encrypted and all access logs are kept for traceability.

[0537] Data visualization and analysis tools

[0538] The terminal visualizes and analyzes data based on the user's request. The user accesses the system from the terminal and requests specific data analysis or visualization. For example, when a sales representative requests a sales trend report, the terminal sends the request to the server. The server extracts data from the integrated database, performs analysis using a generative AI model, and sends the results to the terminal. The terminal displays the results as graphs and dashboards.

[0539] Feedback reflection method

[0540] The user can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the generative AI model, thereby improving the accuracy of future analyses.

[0541] emotion recognition means

[0542] The server uses emotion recognition means to recognize the user's emotions. The emotion recognition means analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the generative AI model, contributing to improved analysis accuracy and user experience in future analyses.

[0543] Specific examples

[0544] As a concrete example, when a sales representative uses this system to check sales trends, they send a request from their terminal to the system. The server extracts the data and sends the analysis results to the terminal. The representative then checks the results and expresses their feedback and emotions about them. This emotional data is analyzed by the emotion recognition means, and the feedback and emotional data are reflected in the generative AI model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[0545] Prompt Sentence Examples

[0546] "Get sales data, analyze and visualize sales trends over the past six months. Also, collect feedback on the analysis results, analyze user sentiment, and reflect it in your next project."

[0547] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0548] Step 1:

[0549] The server connects to multiple internal data sources (sales database, logistics system, human resources database, etc.) and collects data. API endpoints and authentication information are required as input. The server periodically calls the API to obtain data and saves it in local storage. For example, new sales data is obtained from the sales database every hour. The collected data in JSON format is saved as output. Specific operations include sending API requests and receiving response data.

[0550] Step 2:

[0551] The server performs preprocessing on the collected data. The collected JSON data is required as input. The server performs processes to impute missing values, remove duplicate data, and standardize data formats. For example, it standardizes the date and time format to "YYYY-MM-DD HH:MM:SS" and imputes missing sales data with the average value. A preprocessed data frame is generated as output. Specific operations include data cleansing and format conversion.

[0552] Step 3:

[0553] The server integrates the preprocessed data into a common data model. It requires a preprocessed data frame as input. The server maps data from different data sources into a unified schema and defines data relationships. For example, it associates sales data with customer data by linking customer IDs with order IDs. As output, it generates an integrated dataset and stores it in the data warehouse. Specific actions include write operations to the database.

[0554] Step 4:

[0555] The server uses AI to apply data governance. It requires an integrated dataset and access permission information as input. The server sets data access permissions and performs data classification and privacy protection. For example, it may grant access permission only to data related to a specific department. Sensitive data is encrypted and an access log is recorded. The output is a governed dataset and access log. Specific operations include setting access control lists and encryption.

[0556] Step 5:

[0557] The terminal visualizes and analyzes data based on the user's request. As input, it requires the user's request and a governed dataset. For example, if a user requests a sales trend report, the terminal sends the request to the server. The server performs data analysis using a generative AI model and sends the results to the terminal. As output, visualized graphs and dashboards are generated and displayed to the user. Specific operations include data extraction and rendering of analysis results.

[0558] Step 6:

[0559] The user provides feedback on the displayed analysis results. The analysis results and user feedback are required as input. The device sends the feedback to the server. The server collects the feedback and reflects it in the generative AI model to improve the accuracy of future analyses. An updated AI model is generated as output. Specific operations include collecting feedback data and retraining the model.

[0560] Step 7:

[0561] The server uses emotion recognition means to recognize the user's emotions. The input required is the user's input content, voice, and facial expression data. The server applies an emotion recognition algorithm to identify the user's emotions. For example, when a user enters a rating into the system, the server analyzes the emotion from the content and voice. The output is the user's emotional state, and appropriate feedback is provided based on that. Specific operations include emotion analysis and feedback generation.

[0562] (Application example 2)

[0563] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0564] In conventional factory data management systems, the processes of data collection, preprocessing, integration, governance, visualization, analysis, and feedback reflection are not integrated, making it difficult to analyze data and reflect feedback in real time.In addition, there is no system that analyzes workers' emotions and reflects them in feedback, so there are still challenges in improving the working environment.

[0565] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to collect, preprocess, and integrate data in real time from multiple data sources within the factory. In addition, data visualization and analysis can be performed based on the integrated data, and feedback can be reflected immediately. Furthermore, by using the emotion recognition means, it is possible to analyze the emotions of workers and use this information to improve the work environment.

[0566] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining the latest data using an API.

[0567] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0568] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[0569] "Data governance measures" are measures that use AI to manage access rights, classify data, and protect privacy.

[0570] "Data visualization and analysis means" refers to a means of visualizing data in response to user requests and analyzing it using an AI model.

[0571] The "feedback reflection means" is a means for collecting feedback from users on the displayed analysis results and reflecting that feedback in the AI ​​model.

[0572] An "emotion recognition means" is a means of analyzing a user's input, voice, and facial expressions to identify emotions and reflect them in the system.

[0573] This invention relates to a data management system for industrial robots, and provides a system that efficiently performs a series of processes from data collection to preprocessing, integration, governance, visualization, analysis, feedback reflection, and emotion recognition.

[0574] System Program

[0575] Specific program processing to realize each means is carried out separately for the server, terminal, and user.

[0576] Natural language explanations

[0577] 1. Data collection methods:

[0578] The server collects data from multiple data sources (such as each manufacturing process and machine in the factory). It connects to these data sources using APIs and periodically obtains the latest data. For example, operation data and quality data from each manufacturing line are collected every hour and sent to the server.

[0579] 2. Pretreatment methods:

[0580] The server processes the collected data by removing noise, formatting, and filling in missing values. It uses Python to standardize data formats and remove duplicate data. For example, it standardizes data in different formats for each production line and fills in missing quality data with the average value.

[0581] 3. Data integration methods:

[0582] The server integrates the preprocessed data into the AWS data warehouse, mapping data from different data sources to a unified schema and defining data relationships. For example, by linking manufacturing process IDs and machine IDs, the operation data and quality data for each process can be associated.

[0583] 4. Data Governance Measures:

[0584] The server uses AI to manage access rights, classify data, and protect privacy. For example, quality control personnel can be granted access only to quality data and not to other data. Confidential data is also encrypted and access logs are recorded for traceability.

[0585] 5. Data visualization and analysis tools:

[0586] The device visualizes data in response to user requests and performs analysis using AI models. Power BI is used to display real-time factory operation status and anomaly detection on a dashboard. For example, when a manufacturing department employee requests a production line operation trend report, the device sends it to the server and displays the analysis results on the dashboard.

[0587] 6. Feedback methods:

[0588] Users can provide feedback on the displayed analysis results. The feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model to improve the accuracy of future analyses. For example, if a quality control officer comments on areas for improvement in anomaly detection results, these comments will be reflected in the next analysis.

[0589] 7. Emotion recognition means:

[0590] The server uses Azure Cognitive Services to analyze the user's emotions. It identifies emotions from the user's input, voice, and facial expressions and reflects them as feedback. For example, when a worker enters an evaluation into the system, it recognizes emotions such as joy or stress from the input and voice and provides appropriate feedback.

[0591] Examples of specific examples and prompts

[0592] Robots in the factory collect operational data and send it to a server. The server uses Python scripts to preprocess the data, fill in missing values, and standardize the format. The preprocessed data is integrated in an AWS data warehouse, and various data sources are mapped. Azure Cognitive Services is used to create an emotion engine that analyzes feedback from workers and recognizes emotions such as joy and stress. Power BI is used to display real-time factory operation status on a dashboard, and workers are notified if an abnormality is detected.

[0593] Example prompt sentence:

[0594] "Devout a system that handles data collection, preprocessing, data integration, data governance, data visualization, feedback, and emotion recognition within the factory, and program it using Python, AWS, and Azure Cognitive Services. This will enable real-time monitoring of factory operation status, anomaly detection, and worker emotion analysis."

[0595] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0596] Step 1:

[0597] (Data Collection)

[0598] The server connects to each data source using an API to collect the requested data from multiple data sources. The input is operation data, quality data, and production progress data for each manufacturing process and machine in the factory. The output is the transfer of this data to the server. Specifically, the data collection program periodically sends requests to the API endpoint and stores the latest collected data on the server.

[0599] Step 2:

[0600] (Data preprocessing)

[0601] The server processes the collected raw data to improve its quality. The input is the raw data stored on the server. The output is preprocessed, cleaned data. Specifically, it performs operations such as imputing missing values ​​in the data with the mean value, removing duplicate data, and standardizing date formats. These data cleaning operations are performed using Python scripts.

[0602] Step 3:

[0603] (Data Integration)

[0604] The server integrates and centralizes the preprocessed data into a common data model. The input is the preprocessed data. The output is an integrated dataset. Specifically, using an AWS data warehouse or similar, the data provided from different data sources is mapped to a unified schema and linked based on keys such as manufacturing process IDs and machine IDs.

[0605] Step 4:

[0606] (Data Governance)

[0607] The server applies data governance to the integrated data using AI. The input is the integrated data set. The output is governance data that includes properly classified and encrypted data and access control information. Specifically, it sets data access rights, encrypts sensitive data, and records access logs. This is achieved using an access rights management system and encryption software.

[0608] Step 5:

[0609] (Data Visualization and Analysis)

[0610] The terminal visualizes data in response to user requests and performs analysis using an AI model. The input is the integrated dataset and the user request. The output is the analysis results and visualized data. Specifically, Power BI is used to display factory operation status and anomaly detection in real time on a dashboard. When a user requests analysis of specific data, it is sent to the server, which then analyzes it and sends the results to the terminal.

[0611] Step 6:

[0612] (Reflecting feedback)

[0613] The user provides feedback on the displayed analysis results. The input is the user's feedback. The output is the feedback results and data that will be reflected in the next analysis. Specifically, the feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model. This improves the accuracy of data analysis from the next time onwards.

[0614] Step 7:

[0615] (emotion recognition)

[0616] The server uses Azure Cognitive Services to analyze the user's emotions. The inputs are the user's input, voice, and facial expression data. The output is the analyzed emotional data. Specifically, when the user enters an evaluation or feedback to the system, the system analyzes the text and voice data to identify the user's emotional state (for example, joy or stress), and feeds the results back to the system.

[0617] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0618] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0620] [Third embodiment]

[0621] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0622] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0623] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0624] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0625] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0626] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0627] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0628] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0629] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0630] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0631] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0632] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0633] The present invention is a system designed to solve the problem of data management within a company. Details for implementing this system are described below.

[0634] Data collection methods

[0635] The server collects data from multiple data sources within the company (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, it can be configured to collect new sales data from the database every 10 minutes. This allows for timely data collection.

[0636] Pretreatment means

[0637] The server preprocesses the collected data by filling in missing values, removing duplicate data, and standardizing data formats. For example, it standardizes the date and time format and fills in missing sales data. This process maintains the quality of the data and ensures smooth subsequent processing.

[0638] Data Integration Methods

[0639] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs can associate sales data with customer data. This data integration is then stored in a data warehouse, where it serves as the basis for subsequent analysis and visualization.

[0640] Data Governance Measures

[0641] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, highly sensitive data is encrypted and access logs are recorded for traceability.

[0642] Data visualization and analysis tools

[0643] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their own terminal and request specific data analysis or visualization. For example, if a sales representative (user) wants to know sales trends, he or she sends the request from the terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal then displays the resulting analysis results as graphs and dashboards.

[0644] Feedback reflection method

[0645] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. The device then sends that feedback to the server, which then uses the collected feedback to improve the AI ​​model. This process continuously improves the system's analytical accuracy.

[0646] As a concrete example, let us look at the flow of how this system is used by a logistics department to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts logistics data from the integrated database and performs an analysis. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0647] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, and feedback reflection, thereby centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[0648] The processing flow will be explained below.

[0649] Step 1:

[0650] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, you can set it to collect new sales data from the database every 10 minutes.

[0651] Step 2:

[0652] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[0653] Step 3:

[0654] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[0655] Step 4:

[0656] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[0657] Step 5:

[0658] Users access the system from their devices and make requests for specific data visualization or analysis. For example, a sales representative requests a sales trend report. The device sends the request to the server.

[0659] Step 6:

[0660] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[0661] Step 7:

[0662] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[0663] Step 8:

[0664] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[0665] Step 9:

[0666] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[0667] Example 1

[0668] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0669] Modern companies are required to efficiently collect and integrate data from multiple sources, then analyze and visualize it. However, many challenges exist, including the handling of missing and duplicate data, the unification of multiple data formats, and the complexity of access rights and privacy management. Furthermore, existing systems lack a means to centrally and efficiently resolve these challenges, which can lead to a decline in data quality and management efficiency. The purpose of this invention is to solve these challenges and improve the accuracy and efficiency of data management and analysis.

[0670] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0671] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, and a feedback reflection means, which makes it possible to comprehensively manage the entire process from data collection to preprocessing, integration, governance, analysis, and feedback.

[0672] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using an API.

[0673] "Preprocessing means" refers to means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0674] A "data integration method" is a method for mapping data from different data sources into a unified schema and storing it in a data warehouse.

[0675] "Data governance measures" are measures that use AI to manage access rights, classify and encrypt data.

[0676] "Data visualization and analysis means" is a means for analyzing data in response to user requests and displaying it as graphs or dashboards.

[0677] "Feedback reflection means" refers to a means of collecting feedback from users and retraining and improving the generative AI model based on that feedback.

[0678] The present invention is a system for managing and analyzing data within a company, and has the following configuration.

[0679] Data collection methods

[0680] The server collects data from multiple data sources (e.g., sales database, logistics system, human resources database). Specifically, it connects to these data sources using APIs and periodically obtains the latest data. For example, the server is configured to collect new sales data from the database every 10 minutes. This collection method allows the latest data to be obtained in real time.

[0681] Pretreatment means

[0682] The server preprocesses the collected data. This includes filling in missing values, removing duplicate data, and standardizing the data format. For example, the date and time format is standardized to "YYYY-MM-DD HH:MM:SS," and missing data is filled in using the previous value or an appropriate default value. This preprocessing maintains the quality of the data and ensures smooth subsequent processing.

[0683] Data Integration Methods

[0684] The server integrates the preprocessed data into a common data model. This involves mapping data collected from different data sources to a unified schema and storing it in a data warehouse. For example, to link sales data and customer data, a customer ID is used as a common key. This integration allows data from different data sources to be managed centrally.

[0685] Data Governance Measures

[0686] The server uses AI to implement data governance, including access rights management, data classification, and encryption. For example, certain business personnel are only allowed to access data related to their department, and highly confidential data is encrypted and access logs are recorded. This ensures data security and privacy.

[0687] Data visualization and analysis tools

[0688] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their terminal and request specific data analysis or visualization. For example, if a sales representative wants to know "sales trends over the past six months," they send the request from their terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using a generative AI model. The resulting analysis results are displayed on the terminal as graphs and dashboards.

[0689] Feedback reflection method

[0690] Users can provide feedback on the displayed analysis results. For example, an accountant can comment on inaccuracies in the income and expenditure analysis results. The device then sends this feedback to the server, which then retrains and improves the generative AI model based on the collected feedback. This allows the system's analytical accuracy to continuously improve.

[0691] Specific examples

[0692] For example, let us look at the process by which a logistics department uses this system to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts and analyzes logistics data from the integrated database. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0693] Prompt Sentence Examples

[0694] Example 1:

[0695] "Using sales data and customer data, please analyze sales trends over the past six months and display them in a graph."

[0696] Example 2:

[0697] "Calculate optimized delivery routes based on logistics data and generate a report that displays the results on a dashboard."

[0698] Example 3:

[0699] "Use your HR data to generate reports on employee attendance, highlighting departments with particularly high absenteeism."

[0700] By using such prompts, the user can give specific instructions to the system and efficiently obtain the required information.

[0701] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0702] Step 1:

[0703] The server connects to multiple data sources and collects data. Specifically, it periodically retrieves the latest data from each data source using APIs. The input is the API endpoint and authentication information of each data source. The output is the collected raw data. For example, the server retrieves new sales data from a sales database every 10 minutes.

[0704] Step 2:

[0705] The server preprocesses the collected raw data. Preprocessing includes filling in missing values, removing duplicate data, and standardizing the data format. The raw data collected in step 1 is used as input. Specific operations include, for example, filling in missing sales data with previous data or average values, removing duplicate customer records, and standardizing the date and time format to "YYYY-MM-DD HH:MM:SS". The output is clean data that has been preprocessed.

[0706] Step 3:

[0707] The server integrates the pre-processed data into a common data model. In this process, data from different data sources is mapped to a unified schema and stored in a data warehouse. The input is the clean data obtained in step 2. Specifically, the server integrates sales data and customer data using customer ID as a key. The output is an integrated dataset stored in the data warehouse.

[0708] Step 4:

[0709] The server uses AI to implement data governance, including managing access rights, classifying and encrypting data. The input is the dataset integrated in step 3. Specific operations include granting access to department-related data to specific business personnel, encrypting confidential data, and recording access logs. The output is a securely managed data ecosystem.

[0710] Step 5:

[0711] A user accesses the system from their device and requests a specific data analysis or visualization. The input is the user's request. For example, the user requests "Show sales trends for the past six months." The output is the request being sent to the server.

[0712] Step 6:

[0713] The server analyzes the data according to the user's request. The input is the request sent in step 5 and the data integrated in step 3. Specifically, it uses a generative AI model to perform the specified analysis. For example, it analyzes sales trends and obtains the results. The output is the analysis results.

[0714] Step 7:

[0715] The terminal visualizes the analysis results sent from the server. The input is the analysis results obtained in step 6. Specifically, the terminal displays the results as graphs or dashboards. The output is visual feedback provided to the user.

[0716] Step 8:

[0717] The user provides feedback on the displayed analysis results. The input is the user providing specific feedback. For example, the user may comment on "inaccuracies in the income and expenditure analysis results." The output is the feedback being sent from the terminal to the server.

[0718] Step 9:

[0719] The server retrains and improves the generative AI model based on the collected feedback. The input is the feedback sent by the user. The specific operation is to retrain the AI ​​model to improve the accuracy of the next analysis. The output is an improved AI model.

[0720] (Application example 1)

[0721] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0722] Modern logistics centers require the management of massive amounts of data and efficient operation. Manually collecting and managing data by staff is inefficient, time-consuming, and carries a high risk of human error. Furthermore, data analysis and efficiency proposals based on the results are often not carried out in a timely manner, making it difficult for on-site managers to make quick decisions. Furthermore, there is a need for real-time situational awareness and continuous system improvement based on feedback.

[0723] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0724] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for proposing efficiency improvements, and a dashboard display means. This enables the logistics center to efficiently carry out a series of processes, including automatic data collection, preprocessing, integration, governance, visualization and analysis, and feedback reflection, thereby realizing real-time situation understanding and rapid decision-making. In addition, efficiency suggestions based on AI analysis support optimal logistics operations.

[0725] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using APIs, updating each logistics process in real time.

[0726] The "preprocessing means" is a means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats, and also for implementing proposals for improving the efficiency of logistics data.

[0727] A "data integration method" is a method for mapping data collected from different data sources to a unified schema, defining the relationships between the data, and integrating them into an integrated data model.

[0728] "Data governance measures" are measures that use AI to manage data access rights, classify data, and protect privacy, encrypting highly sensitive data and recording access logs.

[0729] "Data visualization and analysis means" refers to a means of extracting relevant data from an integrated database based on a user's request, analyzing it using an AI model, and displaying the results to the user as graphs or dashboards.

[0730] "Feedback reflection means" refers to a means of collecting user feedback and using it to improve the AI ​​model and the entire system.

[0731] "Real-time data collection means" refers to a means for collecting data from each system within the logistics center in real time and updating it immediately.

[0732] The "efficiency proposal method" is a method that uses AI models to make logistics optimization proposals based on collected and preprocessed data.

[0733] The "dashboard display means" is a means for visualizing data in real time and visually displaying each process and its status at the logistics center.

[0734] To implement this invention, it is necessary to build a system for use in a logistics center, which includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for suggesting efficiency improvements, and a dashboard display means.

[0735] Hardware and software configuration

[0736] Server: The main computing unit that handles databases, AI model training and prediction, and data integration and preprocessing. Specifically, it uses SQLite for the database and Scikit-learn for AI model training.

[0737] Client terminal: A smartphone or tablet used by logistics center staff to visualize data and input feedback.

[0738] Data collection methods

[0739] The server collects data from each system in the distribution center in real time and updates it periodically. For example, it obtains data from sales databases and personnel databases through APIs. This collected data is then stored in a database.

[0740] Pretreatment means

[0741] The server performs missing value imputation, duplicate data removal, and data format standardization for the collected data. Pandas is used as a data preprocessing tool to ensure data quality.

[0742] Data Integration Methods

[0743] The server maps the pre-processed data into a unified schema and connects data from different data sources (for example, linking customer IDs with order IDs to associate sales data with customer data). This combined data is then stored in a data warehouse.

[0744] Data Governance Measures

[0745] The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are only given access to relevant data, confidential data is encrypted, and access logs are recorded.

[0746] Data visualization and analysis tools

[0747] The device visualizes data and displays analysis results in response to user requests. The server extracts the relevant data from the integrated database and analyzes it using an AI model. Users can view the resulting dashboards and graphs on their device.

[0748] Feedback reflection method

[0749] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server, and the AI ​​model and the entire system are improved based on the collected feedback.

[0750] Real-time data collection methods

[0751] Data is collected in real time from each system within the logistics center and updated immediately, allowing operations to be managed based on the latest information at all times.

[0752] Efficiency improvement proposal methods

[0753] The server uses AI models to make logistics optimization suggestions based on the collected and pre-processed data, such as displaying optimized delivery routes and inventory management alerts.

[0754] Dashboard display method

[0755] The terminal visualizes data in real time, visually displaying each process and its status in the logistics center.

[0756] Examples and prompts

[0757] For example, if a user enters a prompt such as "Please propose the optimal delivery schedule for next week using the latest logistics information for optimizing delivery routes," the server will extract the necessary data from the integrated database, analyze and optimize it using an AI model, and display the results on the terminal as a dashboard, allowing the logistics center manager to efficiently manage operations.

[0758] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0759] Step 1:

[0760] Data collection: The server collects data from each system in the distribution center (e.g., sales database, human resources database) through API. In this collection process, new data is obtained every 10 minutes. The input is raw data from each database, and the output is raw data stored on the server.

[0761] Step 2:

[0762] Data preprocessing: The server completes the collected data by filling in missing values, removing duplicate data, and standardizing the data format. For example, it standardizes the date format and completes missing sales data. The input is the collected raw data, and the output is the preprocessed data.

[0763] Step 3:

[0764] Data Integration: The server maps the pre-processed data to a unified schema and integrates data from different sources. For example, linking customer IDs with order IDs to associate sales data with customer data. The input is the pre-processed data, and the output is the data transformed into a unified data model.

[0765] Step 4:

[0766] Implementing data governance: The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are granted access only to relevant data, confidential data is encrypted, and access logs are recorded. The input is data management policies and database configuration information, and the output is data with access restrictions applied.

[0767] Step 5:

[0768] Data visualization and analysis: The terminal extracts data from the server based on the user's request and performs analysis. The server uses the integrated data to perform analysis using an AI model (Scikit-learn). The results are displayed on the terminal as graphs and dashboards. The input is the user's request and the integrated database, and the output is the analysis results displayed to the user.

[0769] Step 6:

[0770] Feedback reflection: The user provides feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server and used to improve the AI ​​model. The input is the user's feedback, and the output is the parameters of the improved AI model.

[0771] Step 7:

[0772] Real-time data collection: The server collects data from each system in the distribution center in real time and updates it immediately. The input is real-time data from each system, and the output is the latest data stored on the server.

[0773] Step 8:

[0774] Efficiency proposals: The server uses an AI model based on the collected and preprocessed data to make logistics optimization proposals. For example, optimized delivery routes and inventory management alerts are provided to the user. The inputs are the preprocessed data and the AI ​​model, and the output is the optimization proposals.

[0775] Step 9:

[0776] Dashboard display: The terminal visualizes data in real time, visually displaying each process and its status in the distribution center. The input is real-time data and analysis results, and the output is a dashboard that users can access.

[0777] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0778] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and an emotion engine that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system are described below.

[0779] Data collection methods

[0780] The server collects data from multiple internal data sources (e.g., sales database, logistics system, human resources database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, by configuring it to retrieve new sales data from the database every hour, it becomes possible to collect timely data.

[0781] Pretreatment means

[0782] The server preprocesses the collected data. Specifically, it imputes missing values, removes duplicate data, and standardizes data formats. For example, it standardizes the date and time format and imputes missing sales data with the average value. This process maintains the quality of the data and ensures smooth subsequent processing.

[0783] Data Integration Methods

[0784] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs associates sales data with customer data. This data is then stored in a data warehouse and serves as the basis for subsequent analysis and visualization.

[0785] Data Governance Measures

[0786] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, sensitive data is encrypted and access logs are recorded for traceability.

[0787] Data visualization and analysis tools

[0788] The terminal performs data visualization and analysis in response to user requests. Users can access the system from their terminal and request specific data analysis and visualization. For example, if a sales department representative (user) requests a sales trend report, the terminal sends the request to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal displays the resulting analysis results as graphs and dashboards.

[0789] Feedback reflection method

[0790] Users can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the AI ​​model to improve the accuracy of future analyses.

[0791] Emotion Engine

[0792] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the AI ​​model, contributing to improved analysis accuracy and user experience in future analyses.

[0793] As a concrete example, when a sales representative uses this system to check sales trends, they send a request to the system from their device. The server extracts the data and sends the analysis results to their device. The representative then checks the results and expresses their feelings of dissatisfaction or joy. This emotional data is analyzed by the emotion engine, and this feedback and emotional data is reflected in the AI ​​model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[0794] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, emotion recognition, and feedback reflection, centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[0795] The processing flow will be explained below.

[0796] Step 1:

[0797] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, you can set it to retrieve new sales data from the database every hour.

[0798] Step 2:

[0799] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[0800] Step 3:

[0801] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[0802] Step 4:

[0803] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[0804] Step 5:

[0805] Users access the system from their own devices and make requests for specific data visualization or analysis. For example, a sales representative requests a "sales trend report." The device then sends the request to the server.

[0806] Step 6:

[0807] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[0808] Step 7:

[0809] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[0810] Step 8:

[0811] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[0812] Step 9:

[0813] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[0814] Step 10:

[0815] The server uses an emotion engine to recognize the user's emotions. For example, when a user enters feedback, it analyzes text and voice data to identify the user's emotions. This emotion data is collected and reflected in the AI ​​model. This will further improve future analyses and the user experience.

[0816] Example 2

[0817] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0818] In conventional data management systems, data collection from each data source, data preprocessing, data integration, data governance, data visualization and analysis, and user feedback were all performed separately, reducing the efficiency of the entire system. Furthermore, analysis results and feedback provided without considering user sentiment could degrade the quality of the user experience. To address these issues, a system is needed that centralizes in-house data management and decision-making, improving operational efficiency and accuracy.

[0819] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0820] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to efficiently collect data from each data source and execute preprocessing, integration, governance, visualization, and analysis as a series of processes. Furthermore, by recognizing the user's emotions and reflecting them in feedback, it is possible to improve the user experience and improve the accuracy of subsequent analyses.

[0821] "Data collection means" refers to a means for collecting data from multiple data sources within the company and obtaining the data periodically using an API.

[0822] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0823] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[0824] "Data governance measures" are measures for setting data access permissions, classifying data and protecting privacy, and recording data access logs.

[0825] "Data visualization and analysis means" refers to means for visualizing data in response to user requests and performing data analysis using AI models.

[0826] "Feedback reflection means" refers to a means for collecting feedback provided by users and reflecting it in the AI ​​model to improve the accuracy of analysis from the next time onwards.

[0827] An "emotion recognition means" is a means for analyzing a user's input, voice, and facial expressions to identify emotions and provide feedback based on those emotions.

[0828] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and emotion recognition means that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system will be described below.

[0829] Data collection methods

[0830] The server collects data from multiple internal data sources (sales database, logistics system, HR database, etc.). It connects to each data source using APIs and periodically retrieves the latest data. This data collection is automated, and is set to retrieve new sales data from the database every hour, for example.

[0831] Pretreatment means

[0832] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes data formats. For example, standardizing the date and time format and complementing missing sales data with the average value ensures data quality and ensures smooth subsequent processing.

[0833] Data Integration Methods

[0834] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and clarifying data relationships (for example, linking customer IDs to order IDs to associate sales data with customer data). This data is then stored in a data warehouse, forming the basis for subsequent analysis and visualization.

[0835] Data Governance Measures

[0836] The server uses AI to enforce data governance, including access rights management, data classification, and privacy protection. For example, specific personnel are only allowed access to data relevant to their job. Sensitive data is encrypted and all access logs are kept for traceability.

[0837] Data visualization and analysis tools

[0838] The terminal visualizes and analyzes data based on the user's request. The user accesses the system from the terminal and requests specific data analysis or visualization. For example, when a sales representative requests a sales trend report, the terminal sends the request to the server. The server extracts data from the integrated database, performs analysis using a generative AI model, and sends the results to the terminal. The terminal displays the results as graphs and dashboards.

[0839] Feedback reflection method

[0840] The user can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the generative AI model, thereby improving the accuracy of future analyses.

[0841] emotion recognition means

[0842] The server uses emotion recognition means to recognize the user's emotions. The emotion recognition means analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the generative AI model, contributing to improved analysis accuracy and user experience in future analyses.

[0843] Specific examples

[0844] As a concrete example, when a sales representative uses this system to check sales trends, they send a request from their terminal to the system. The server extracts the data and sends the analysis results to the terminal. The representative then checks the results and expresses their feedback and emotions about them. This emotional data is analyzed by the emotion recognition means, and the feedback and emotional data are reflected in the generative AI model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[0845] Prompt Sentence Examples

[0846] "Get sales data, analyze and visualize sales trends over the past six months. Also, collect feedback on the analysis results, analyze user sentiment, and reflect it in your next project."

[0847] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0848] Step 1:

[0849] The server connects to multiple internal data sources (sales database, logistics system, human resources database, etc.) and collects data. API endpoints and authentication information are required as input. The server periodically calls the API to obtain data and saves it in local storage. For example, new sales data is obtained from the sales database every hour. The collected data in JSON format is saved as output. Specific operations include sending API requests and receiving response data.

[0850] Step 2:

[0851] The server performs preprocessing on the collected data. The collected JSON data is required as input. The server performs processes to impute missing values, remove duplicate data, and standardize data formats. For example, it standardizes the date and time format to "YYYY-MM-DD HH:MM:SS" and imputes missing sales data with the average value. A preprocessed data frame is generated as output. Specific operations include data cleansing and format conversion.

[0852] Step 3:

[0853] The server integrates the preprocessed data into a common data model. It requires a preprocessed data frame as input. The server maps data from different data sources into a unified schema and defines data relationships. For example, it associates sales data with customer data by linking customer IDs with order IDs. As output, it generates an integrated dataset and stores it in the data warehouse. Specific actions include write operations to the database.

[0854] Step 4:

[0855] The server uses AI to apply data governance. It requires an integrated dataset and access permission information as input. The server sets data access permissions and performs data classification and privacy protection. For example, it may grant access permission only to data related to a specific department. Sensitive data is encrypted and an access log is recorded. The output is a governed dataset and access log. Specific operations include setting access control lists and encryption.

[0856] Step 5:

[0857] The terminal visualizes and analyzes data based on the user's request. As input, it requires the user's request and a governed dataset. For example, if a user requests a sales trend report, the terminal sends the request to the server. The server performs data analysis using a generative AI model and sends the results to the terminal. As output, visualized graphs and dashboards are generated and displayed to the user. Specific operations include data extraction and rendering of analysis results.

[0858] Step 6:

[0859] The user provides feedback on the displayed analysis results. The analysis results and user feedback are required as input. The device sends the feedback to the server. The server collects the feedback and reflects it in the generative AI model to improve the accuracy of future analyses. An updated AI model is generated as output. Specific operations include collecting feedback data and retraining the model.

[0860] Step 7:

[0861] The server uses emotion recognition means to recognize the user's emotions. The input required is the user's input content, voice, and facial expression data. The server applies an emotion recognition algorithm to identify the user's emotions. For example, when a user enters a rating into the system, the server analyzes the emotion from the content and voice. The output is the user's emotional state, and appropriate feedback is provided based on that. Specific operations include emotion analysis and feedback generation.

[0862] (Application example 2)

[0863] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0864] In conventional factory data management systems, the processes of data collection, preprocessing, integration, governance, visualization, analysis, and feedback reflection are not integrated, making it difficult to analyze data and reflect feedback in real time.In addition, there is no system that analyzes workers' emotions and reflects them in feedback, so there are still challenges in improving the working environment.

[0865] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to collect, preprocess, and integrate data in real time from multiple data sources within the factory. In addition, data visualization and analysis can be performed based on the integrated data, and feedback can be reflected immediately. Furthermore, by using the emotion recognition means, it is possible to analyze the emotions of workers and use this information to improve the work environment.

[0866] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining the latest data using an API.

[0867] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0868] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[0869] "Data governance measures" are measures that use AI to manage access rights, classify data, and protect privacy.

[0870] "Data visualization and analysis means" refers to a means of visualizing data in response to user requests and analyzing it using an AI model.

[0871] The "feedback reflection means" is a means for collecting feedback from users on the displayed analysis results and reflecting that feedback in the AI ​​model.

[0872] An "emotion recognition means" is a means of analyzing a user's input, voice, and facial expressions to identify emotions and reflect them in the system.

[0873] This invention relates to a data management system for industrial robots, and provides a system that efficiently performs a series of processes from data collection to preprocessing, integration, governance, visualization, analysis, feedback reflection, and emotion recognition.

[0874] System Program

[0875] Specific program processing to realize each means is carried out separately for the server, terminal, and user.

[0876] Natural language explanations

[0877] 1. Data collection methods:

[0878] The server collects data from multiple data sources (such as each manufacturing process and machine in the factory). It connects to these data sources using APIs and periodically obtains the latest data. For example, operation data and quality data from each manufacturing line are collected every hour and sent to the server.

[0879] 2. Pretreatment methods:

[0880] The server processes the collected data by removing noise, formatting, and filling in missing values. It uses Python to standardize data formats and remove duplicate data. For example, it standardizes data in different formats for each production line and fills in missing quality data with the average value.

[0881] 3. Data integration methods:

[0882] The server integrates the preprocessed data into the AWS data warehouse, mapping data from different data sources to a unified schema and defining data relationships. For example, by linking manufacturing process IDs and machine IDs, the operation data and quality data for each process can be associated.

[0883] 4. Data Governance Measures:

[0884] The server uses AI to manage access rights, classify data, and protect privacy. For example, quality control personnel can be granted access only to quality data and not to other data. Confidential data is also encrypted and access logs are recorded for traceability.

[0885] 5. Data visualization and analysis tools:

[0886] The device visualizes data in response to user requests and performs analysis using AI models. Power BI is used to display real-time factory operation status and anomaly detection on a dashboard. For example, when a manufacturing department employee requests a production line operation trend report, the device sends it to the server and displays the analysis results on the dashboard.

[0887] 6. Feedback methods:

[0888] Users can provide feedback on the displayed analysis results. The feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model to improve the accuracy of future analyses. For example, if a quality control officer comments on areas for improvement in anomaly detection results, these comments will be reflected in the next analysis.

[0889] 7. Emotion recognition means:

[0890] The server uses Azure Cognitive Services to analyze the user's emotions. It identifies emotions from the user's input, voice, and facial expressions and reflects them as feedback. For example, when a worker enters an evaluation into the system, it recognizes emotions such as joy or stress from the input and voice and provides appropriate feedback.

[0891] Examples of specific examples and prompts

[0892] Robots in the factory collect operational data and send it to a server. The server uses Python scripts to preprocess the data, fill in missing values, and standardize the format. The preprocessed data is integrated in an AWS data warehouse, and various data sources are mapped. Azure Cognitive Services is used to create an emotion engine that analyzes feedback from workers and recognizes emotions such as joy and stress. Power BI is used to display real-time factory operation status on a dashboard, and workers are notified if an abnormality is detected.

[0893] Example prompt sentence:

[0894] "Devout a system that handles data collection, preprocessing, data integration, data governance, data visualization, feedback, and emotion recognition within the factory, and program it using Python, AWS, and Azure Cognitive Services. This will enable real-time monitoring of factory operation status, anomaly detection, and worker emotion analysis."

[0895] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0896] Step 1:

[0897] (Data Collection)

[0898] The server connects to each data source using an API to collect the requested data from multiple data sources. The input is operation data, quality data, and production progress data for each manufacturing process and machine in the factory. The output is the transfer of this data to the server. Specifically, the data collection program periodically sends requests to the API endpoint and stores the latest collected data on the server.

[0899] Step 2:

[0900] (Data preprocessing)

[0901] The server processes the collected raw data to improve its quality. The input is the raw data stored on the server. The output is preprocessed, cleaned data. Specifically, it performs operations such as imputing missing values ​​in the data with the mean value, removing duplicate data, and standardizing date formats. These data cleaning operations are performed using Python scripts.

[0902] Step 3:

[0903] (Data Integration)

[0904] The server integrates and centralizes the preprocessed data into a common data model. The input is the preprocessed data. The output is an integrated dataset. Specifically, using an AWS data warehouse or similar, the data provided from different data sources is mapped to a unified schema and linked based on keys such as manufacturing process IDs and machine IDs.

[0905] Step 4:

[0906] (Data Governance)

[0907] The server applies data governance to the integrated data using AI. The input is the integrated data set. The output is governance data that includes properly classified and encrypted data and access control information. Specifically, it sets data access rights, encrypts sensitive data, and records access logs. This is achieved using an access rights management system and encryption software.

[0908] Step 5:

[0909] (Data Visualization and Analysis)

[0910] The terminal visualizes data in response to user requests and performs analysis using an AI model. The input is the integrated dataset and the user request. The output is the analysis results and visualized data. Specifically, Power BI is used to display factory operation status and anomaly detection in real time on a dashboard. When a user requests analysis of specific data, it is sent to the server, which then analyzes it and sends the results to the terminal.

[0911] Step 6:

[0912] (Reflecting feedback)

[0913] The user provides feedback on the displayed analysis results. The input is the user's feedback. The output is the feedback results and data that will be reflected in the next analysis. Specifically, the feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model. This improves the accuracy of data analysis from the next time onwards.

[0914] Step 7:

[0915] (emotion recognition)

[0916] The server uses Azure Cognitive Services to analyze the user's emotions. The inputs are the user's input, voice, and facial expression data. The output is the analyzed emotional data. Specifically, when the user enters an evaluation or feedback to the system, the system analyzes the text and voice data to identify the user's emotional state (for example, joy or stress), and feeds the results back to the system.

[0917] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0918] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0919] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0920] [Fourth embodiment]

[0921] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0922] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0923] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0924] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0925] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0926] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0927] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0928] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0929] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0930] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0931] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0932] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0933] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0934] The present invention is a system designed to solve the problem of data management within a company. Details for implementing this system are described below.

[0935] Data collection methods

[0936] The server collects data from multiple data sources within the company (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, it can be configured to collect new sales data from the database every 10 minutes. This allows for timely data collection.

[0937] Pretreatment means

[0938] The server preprocesses the collected data by filling in missing values, removing duplicate data, and standardizing data formats. For example, it standardizes the date and time format and fills in missing sales data. This process maintains the quality of the data and ensures smooth subsequent processing.

[0939] Data Integration Methods

[0940] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs can associate sales data with customer data. This data integration is then stored in a data warehouse, where it serves as the basis for subsequent analysis and visualization.

[0941] Data Governance Measures

[0942] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, highly sensitive data is encrypted and access logs are recorded for traceability.

[0943] Data visualization and analysis tools

[0944] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their own terminal and request specific data analysis or visualization. For example, if a sales representative (user) wants to know sales trends, he or she sends the request from the terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal then displays the resulting analysis results as graphs and dashboards.

[0945] Feedback reflection method

[0946] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. The device then sends that feedback to the server, which then uses the collected feedback to improve the AI ​​model. This process continuously improves the system's analytical accuracy.

[0947] As a concrete example, let us look at the flow of how this system is used by a logistics department to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts logistics data from the integrated database and performs an analysis. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0948] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, and feedback reflection, thereby centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[0949] The processing flow will be explained below.

[0950] Step 1:

[0951] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It uses an API to connect to each data source and periodically retrieves the latest data. For example, you can set it to collect new sales data from the database every 10 minutes.

[0952] Step 2:

[0953] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[0954] Step 3:

[0955] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[0956] Step 4:

[0957] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[0958] Step 5:

[0959] Users access the system from their devices and make requests for specific data visualization or analysis. For example, a sales representative requests a sales trend report. The device sends the request to the server.

[0960] Step 6:

[0961] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[0962] Step 7:

[0963] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[0964] Step 8:

[0965] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[0966] Step 9:

[0967] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[0968] Example 1

[0969] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0970] Modern companies are required to efficiently collect and integrate data from multiple sources, then analyze and visualize it. However, many challenges exist, including the handling of missing and duplicate data, the unification of multiple data formats, and the complexity of access rights and privacy management. Furthermore, existing systems lack a means to centrally and efficiently resolve these challenges, which can lead to a decline in data quality and management efficiency. The purpose of this invention is to solve these challenges and improve the accuracy and efficiency of data management and analysis.

[0971] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0972] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, and a feedback reflection means, which makes it possible to comprehensively manage the entire process from data collection to preprocessing, integration, governance, analysis, and feedback.

[0973] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using an API.

[0974] "Preprocessing means" refers to means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[0975] A "data integration method" is a method for mapping data from different data sources into a unified schema and storing it in a data warehouse.

[0976] "Data governance measures" are measures that use AI to manage access rights, classify and encrypt data.

[0977] "Data visualization and analysis means" is a means for analyzing data in response to user requests and displaying it as graphs or dashboards.

[0978] "Feedback reflection means" refers to a means of collecting feedback from users and retraining and improving the generative AI model based on that feedback.

[0979] The present invention is a system for managing and analyzing data within a company, and has the following configuration.

[0980] Data collection methods

[0981] The server collects data from multiple data sources (e.g., sales database, logistics system, human resources database). Specifically, it connects to these data sources using APIs and periodically obtains the latest data. For example, the server is configured to collect new sales data from the database every 10 minutes. This collection method allows the latest data to be obtained in real time.

[0982] Pretreatment means

[0983] The server preprocesses the collected data. This includes filling in missing values, removing duplicate data, and standardizing the data format. For example, the date and time format is standardized to "YYYY-MM-DD HH:MM:SS," and missing data is filled in using the previous value or an appropriate default value. This preprocessing maintains the quality of the data and ensures smooth subsequent processing.

[0984] Data Integration Methods

[0985] The server integrates the preprocessed data into a common data model. This involves mapping data collected from different data sources to a unified schema and storing it in a data warehouse. For example, to link sales data and customer data, a customer ID is used as a common key. This integration allows data from different data sources to be managed centrally.

[0986] Data Governance Measures

[0987] The server uses AI to implement data governance, including access rights management, data classification, and encryption. For example, certain business personnel are only allowed to access data related to their department, and highly confidential data is encrypted and access logs are recorded. This ensures data security and privacy.

[0988] Data visualization and analysis tools

[0989] The terminal visualizes and analyzes data in response to user requests. Users can access the system from their terminal and request specific data analysis or visualization. For example, if a sales representative wants to know "sales trends over the past six months," they send the request from their terminal to the server. The server extracts the relevant data from the integrated database and analyzes it using a generative AI model. The resulting analysis results are displayed on the terminal as graphs and dashboards.

[0990] Feedback reflection method

[0991] Users can provide feedback on the displayed analysis results. For example, an accountant can comment on inaccuracies in the income and expenditure analysis results. The device then sends this feedback to the server, which then retrains and improves the generative AI model based on the collected feedback. This allows the system's analytical accuracy to continuously improve.

[0992] Specific examples

[0993] For example, let us look at the process by which a logistics department uses this system to improve delivery efficiency. The logistics department manager (user) accesses the system and requests a "logistics efficiency report." The terminal sends the request to the server, which extracts and analyzes logistics data from the integrated database. As a result of the analysis, a dashboard containing optimized delivery routes and bottleneck information is generated and displayed on the terminal. The manager (user) then uses this information to create and implement a specific action plan.

[0994] Prompt Sentence Examples

[0995] Example 1:

[0996] "Using sales data and customer data, please analyze sales trends over the past six months and display them in a graph."

[0997] Example 2:

[0998] "Calculate optimized delivery routes based on logistics data and generate a report that displays the results on a dashboard."

[0999] Example 3:

[1000] "Use your HR data to generate reports on employee attendance, highlighting departments with particularly high absenteeism."

[1001] By using such prompts, the user can give specific instructions to the system and efficiently obtain the required information.

[1002] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1003] Step 1:

[1004] The server connects to multiple data sources and collects data. Specifically, it periodically retrieves the latest data from each data source using APIs. The input is the API endpoint and authentication information of each data source. The output is the collected raw data. For example, the server retrieves new sales data from a sales database every 10 minutes.

[1005] Step 2:

[1006] The server preprocesses the collected raw data. Preprocessing includes filling in missing values, removing duplicate data, and standardizing the data format. The raw data collected in step 1 is used as input. Specific operations include, for example, filling in missing sales data with previous data or average values, removing duplicate customer records, and standardizing the date and time format to "YYYY-MM-DD HH:MM:SS". The output is clean data that has been preprocessed.

[1007] Step 3:

[1008] The server integrates the pre-processed data into a common data model. In this process, data from different data sources is mapped to a unified schema and stored in a data warehouse. The input is the clean data obtained in step 2. Specifically, the server integrates sales data and customer data using customer ID as a key. The output is an integrated dataset stored in the data warehouse.

[1009] Step 4:

[1010] The server uses AI to implement data governance, including managing access rights, classifying and encrypting data. The input is the dataset integrated in step 3. Specific operations include granting access to department-related data to specific business personnel, encrypting confidential data, and recording access logs. The output is a securely managed data ecosystem.

[1011] Step 5:

[1012] A user accesses the system from their device and requests a specific data analysis or visualization. The input is the user's request. For example, the user requests "Show sales trends for the past six months." The output is the request being sent to the server.

[1013] Step 6:

[1014] The server analyzes the data according to the user's request. The input is the request sent in step 5 and the data integrated in step 3. Specifically, it uses a generative AI model to perform the specified analysis. For example, it analyzes sales trends and obtains the results. The output is the analysis results.

[1015] Step 7:

[1016] The terminal visualizes the analysis results sent from the server. The input is the analysis results obtained in step 6. Specifically, the terminal displays the results as graphs or dashboards. The output is visual feedback provided to the user.

[1017] Step 8:

[1018] The user provides feedback on the displayed analysis results. The input is the user providing specific feedback. For example, the user may comment on "inaccuracies in the income and expenditure analysis results." The output is the feedback being sent from the terminal to the server.

[1019] Step 9:

[1020] The server retrains and improves the generative AI model based on the collected feedback. The input is the feedback sent by the user. The specific operation is to retrain the AI ​​model to improve the accuracy of the next analysis. The output is an improved AI model.

[1021] (Application example 1)

[1022] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1023] Modern logistics centers require the management of massive amounts of data and efficient operation. Manually collecting and managing data by staff is inefficient, time-consuming, and carries a high risk of human error. Furthermore, data analysis and efficiency proposals based on the results are often not carried out in a timely manner, making it difficult for on-site managers to make quick decisions. Furthermore, there is a need for real-time situational awareness and continuous system improvement based on feedback.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1025] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for proposing efficiency improvements, and a dashboard display means. This enables the logistics center to efficiently carry out a series of processes, including automatic data collection, preprocessing, integration, governance, visualization and analysis, and feedback reflection, thereby realizing real-time situation understanding and rapid decision-making. In addition, efficiency suggestions based on AI analysis support optimal logistics operations.

[1026] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining data using APIs, updating each logistics process in real time.

[1027] The "preprocessing means" is a means for completing missing values ​​in collected data, deleting duplicate data, and standardizing data formats, and also for implementing proposals for improving the efficiency of logistics data.

[1028] A "data integration method" is a method for mapping data collected from different data sources to a unified schema, defining the relationships between the data, and integrating them into an integrated data model.

[1029] "Data governance measures" are measures that use AI to manage data access rights, classify data, and protect privacy, encrypting highly sensitive data and recording access logs.

[1030] "Data visualization and analysis means" refers to a means of extracting relevant data from an integrated database based on a user's request, analyzing it using an AI model, and displaying the results to the user as graphs or dashboards.

[1031] "Feedback reflection means" refers to a means of collecting user feedback and using it to improve the AI ​​model and the entire system.

[1032] "Real-time data collection means" refers to a means for collecting data from each system within the logistics center in real time and updating it immediately.

[1033] The "efficiency proposal method" is a method that uses AI models to make logistics optimization proposals based on collected and preprocessed data.

[1034] The "dashboard display means" is a means for visualizing data in real time and visually displaying each process and its status at the logistics center.

[1035] To implement this invention, it is necessary to build a system for use in a logistics center, which includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, a real-time data collection means, a means for suggesting efficiency improvements, and a dashboard display means.

[1036] Hardware and software configuration

[1037] Server: The main computing unit that handles databases, AI model training and prediction, and data integration and preprocessing. Specifically, it uses SQLite for the database and Scikit-learn for AI model training.

[1038] Client terminal: A smartphone or tablet used by logistics center staff to visualize data and input feedback.

[1039] Data collection methods

[1040] The server collects data from each system in the distribution center in real time and updates it periodically. For example, it obtains data from sales databases and personnel databases through APIs. This collected data is then stored in a database.

[1041] Pretreatment means

[1042] The server performs missing value imputation, duplicate data removal, and data format standardization for the collected data. Pandas is used as a data preprocessing tool to ensure data quality.

[1043] Data Integration Methods

[1044] The server maps the pre-processed data into a unified schema and connects data from different data sources (for example, linking customer IDs with order IDs to associate sales data with customer data). This combined data is then stored in a data warehouse.

[1045] Data Governance Measures

[1046] The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are only given access to relevant data, confidential data is encrypted, and access logs are recorded.

[1047] Data visualization and analysis tools

[1048] The device visualizes data and displays analysis results in response to user requests. The server extracts the relevant data from the integrated database and analyzes it using an AI model. Users can view the resulting dashboards and graphs on their device.

[1049] Feedback reflection method

[1050] Users can provide feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server, and the AI ​​model and the entire system are improved based on the collected feedback.

[1051] Real-time data collection methods

[1052] Data is collected in real time from each system within the logistics center and updated immediately, allowing operations to be managed based on the latest information at all times.

[1053] Efficiency improvement proposal methods

[1054] The server uses AI models to make logistics optimization suggestions based on the collected and pre-processed data, such as displaying optimized delivery routes and inventory management alerts.

[1055] Dashboard display method

[1056] The terminal visualizes data in real time, visually displaying each process and its status in the logistics center.

[1057] Examples and prompts

[1058] For example, if a user enters a prompt such as "Please propose the optimal delivery schedule for next week using the latest logistics information for optimizing delivery routes," the server will extract the necessary data from the integrated database, analyze and optimize it using an AI model, and display the results on the terminal as a dashboard, allowing the logistics center manager to efficiently manage operations.

[1059] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1060] Step 1:

[1061] Data collection: The server collects data from each system in the distribution center (e.g., sales database, human resources database) through API. In this collection process, new data is obtained every 10 minutes. The input is raw data from each database, and the output is raw data stored on the server.

[1062] Step 2:

[1063] Data preprocessing: The server completes the collected data by filling in missing values, removing duplicate data, and standardizing the data format. For example, it standardizes the date format and completes missing sales data. The input is the collected raw data, and the output is the preprocessed data.

[1064] Step 3:

[1065] Data Integration: The server maps the pre-processed data to a unified schema and integrates data from different sources. For example, linking customer IDs with order IDs to associate sales data with customer data. The input is the pre-processed data, and the output is the data transformed into a unified data model.

[1066] Step 4:

[1067] Implementing data governance: The server uses AI to manage data access rights, classify data, and protect privacy. Specific personnel are granted access only to relevant data, confidential data is encrypted, and access logs are recorded. The input is data management policies and database configuration information, and the output is data with access restrictions applied.

[1068] Step 5:

[1069] Data visualization and analysis: The terminal extracts data from the server based on the user's request and performs analysis. The server uses the integrated data to perform analysis using an AI model (Scikit-learn). The results are displayed on the terminal as graphs and dashboards. The input is the user's request and the integrated database, and the output is the analysis results displayed to the user.

[1070] Step 6:

[1071] Feedback reflection: The user provides feedback on the displayed analysis results. For example, an accountant may comment on points of dissatisfaction with the income and expenditure analysis results. This feedback is sent to the server and used to improve the AI ​​model. The input is the user's feedback, and the output is the parameters of the improved AI model.

[1072] Step 7:

[1073] Real-time data collection: The server collects data from each system in the distribution center in real time and updates it immediately. The input is real-time data from each system, and the output is the latest data stored on the server.

[1074] Step 8:

[1075] Efficiency proposals: The server uses an AI model based on the collected and preprocessed data to make logistics optimization proposals. For example, optimized delivery routes and inventory management alerts are provided to the user. The inputs are the preprocessed data and the AI ​​model, and the output is the optimization proposals.

[1076] Step 9:

[1077] Dashboard display: The terminal visualizes data in real time, visually displaying each process and its status in the distribution center. The input is real-time data and analysis results, and the output is a dashboard that users can access.

[1078] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1079] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and an emotion engine that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system are described below.

[1080] Data collection methods

[1081] The server collects data from multiple internal data sources (e.g., sales database, logistics system, human resources database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, by configuring it to retrieve new sales data from the database every hour, it becomes possible to collect timely data.

[1082] Pretreatment means

[1083] The server preprocesses the collected data. Specifically, it imputes missing values, removes duplicate data, and standardizes data formats. For example, it standardizes the date and time format and imputes missing sales data with the average value. This process maintains the quality of the data and ensures smooth subsequent processing.

[1084] Data Integration Methods

[1085] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and defining data relationships. For example, linking customer IDs with order IDs associates sales data with customer data. This data is then stored in a data warehouse and serves as the basis for subsequent analysis and visualization.

[1086] Data Governance Measures

[1087] The server uses AI to enforce data governance, including managing access rights, data classification, and privacy protection. For example, certain business personnel can only access data relevant to their department. Furthermore, sensitive data is encrypted and access logs are recorded for traceability.

[1088] Data visualization and analysis tools

[1089] The terminal performs data visualization and analysis in response to user requests. Users can access the system from their terminal and request specific data analysis and visualization. For example, if a sales department representative (user) requests a sales trend report, the terminal sends the request to the server. The server extracts the relevant data from the integrated database and analyzes it using an AI model. The terminal displays the resulting analysis results as graphs and dashboards.

[1090] Feedback reflection method

[1091] Users can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the AI ​​model to improve the accuracy of future analyses.

[1092] Emotion Engine

[1093] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the AI ​​model, contributing to improved analysis accuracy and user experience in future analyses.

[1094] As a concrete example, when a sales representative uses this system to check sales trends, they send a request to the system from their device. The server extracts the data and sends the analysis results to their device. The representative then checks the results and expresses their feelings of dissatisfaction or joy. This emotional data is analyzed by the emotion engine, and this feedback and emotional data is reflected in the AI ​​model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[1095] In this way, the invented system efficiently carries out a series of processes from data collection to pre-processing, integration, governance, analysis, emotion recognition, and feedback reflection, centralizing internal data management and decision-making, and achieving improved efficiency and accuracy of operations.

[1096] The processing flow will be explained below.

[1097] Step 1:

[1098] The server collects data from multiple internal data sources (e.g., sales database, logistics system, HR database, etc.). It connects to each data source using an API and periodically retrieves the latest data. For example, you can set it to retrieve new sales data from the database every hour.

[1099] Step 2:

[1100] The server preprocesses the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes the data format. For example, it standardizes the date and time format and complements missing sales data with the average value. This process maintains the quality of the data.

[1101] Step 3:

[1102] The server integrates the pre-processed data into a common data model. It maps data from different data sources into a unified schema and defines data relationships. For example, sales data can be associated with customer data by linking customer IDs with order IDs. This integrated data is then stored in a data warehouse.

[1103] Step 4:

[1104] The server uses AI to apply data governance. It sets access rights and limits the range of data accessible to each user. For example, specific business personnel are only allowed to access data related to their department. It also encrypts confidential data and records access logs.

[1105] Step 5:

[1106] Users access the system from their own devices and make requests for specific data visualization or analysis. For example, a sales representative requests a "sales trend report." The device then sends the request to the server.

[1107] Step 6:

[1108] Based on the request, the server extracts the necessary data from the integrated database. The server then inputs the extracted data into the generative AI for analysis and prediction. For example, future sales forecasts are made based on sales data.

[1109] Step 7:

[1110] The server passes the analysis results to a visualization tool to generate graphs and charts. The terminal displays the visualized analysis results to the user. For example, a sales trend graph is displayed on a dashboard.

[1111] Step 8:

[1112] The user provides evaluation and feedback on the displayed analysis results. For example, an accountant comments on areas for improvement in the income and expenditure analysis results. The device then sends that feedback to the server.

[1113] Step 9:

[1114] The server improves the AI ​​model based on the feedback collected, and uses the feedback reflection method to improve the accuracy of analysis from the next time onwards.

[1115] Step 10:

[1116] The server uses an emotion engine to recognize the user's emotions. For example, when a user enters feedback, it analyzes text and voice data to identify the user's emotions. This emotion data is collected and reflected in the AI ​​model. This will further improve future analyses and the user experience.

[1117] Example 2

[1118] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1119] In conventional data management systems, data collection from each data source, data preprocessing, data integration, data governance, data visualization and analysis, and user feedback were all performed separately, reducing the efficiency of the entire system. Furthermore, analysis results and feedback provided without considering user sentiment could degrade the quality of the user experience. To address these issues, a system is needed that centralizes in-house data management and decision-making, improving operational efficiency and accuracy.

[1120] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1121] In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to efficiently collect data from each data source and execute preprocessing, integration, governance, visualization, and analysis as a series of processes. Furthermore, by recognizing the user's emotions and reflecting them in feedback, it is possible to improve the user experience and improve the accuracy of subsequent analyses.

[1122] "Data collection means" refers to a means for collecting data from multiple data sources within the company and obtaining the data periodically using an API.

[1123] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[1124] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[1125] "Data governance measures" are measures for setting data access permissions, classifying data and protecting privacy, and recording data access logs.

[1126] "Data visualization and analysis means" refers to means for visualizing data in response to user requests and performing data analysis using AI models.

[1127] "Feedback reflection means" refers to a means for collecting feedback provided by users and reflecting it in the AI ​​model to improve the accuracy of analysis from the next time onwards.

[1128] An "emotion recognition means" is a means for analyzing a user's input, voice, and facial expressions to identify emotions and provide feedback based on those emotions.

[1129] This invention is a system that combines data collection means, preprocessing means, data integration means, data governance means, data visualization and analysis means, feedback reflection means, and emotion recognition means that recognizes user emotions, in order to solve problems related to in-house data management. Details for implementing this system will be described below.

[1130] Data collection methods

[1131] The server collects data from multiple internal data sources (sales database, logistics system, HR database, etc.). It connects to each data source using APIs and periodically retrieves the latest data. This data collection is automated, and is set to retrieve new sales data from the database every hour, for example.

[1132] Pretreatment means

[1133] The server performs preprocessing on the collected data. Specifically, it complements missing values, removes duplicate data, and standardizes data formats. For example, standardizing the date and time format and complementing missing sales data with the average value ensures data quality and ensures smooth subsequent processing.

[1134] Data Integration Methods

[1135] The server integrates the pre-processed data into a common data model, mapping data from different data sources to a unified schema and clarifying data relationships (for example, linking customer IDs to order IDs to associate sales data with customer data). This data is then stored in a data warehouse, forming the basis for subsequent analysis and visualization.

[1136] Data Governance Measures

[1137] The server uses AI to enforce data governance, including access rights management, data classification, and privacy protection. For example, specific personnel are only allowed access to data relevant to their job. Sensitive data is encrypted and all access logs are kept for traceability.

[1138] Data visualization and analysis tools

[1139] The terminal visualizes and analyzes data based on the user's request. The user accesses the system from the terminal and requests specific data analysis or visualization. For example, when a sales representative requests a sales trend report, the terminal sends the request to the server. The server extracts data from the integrated database, performs analysis using a generative AI model, and sends the results to the terminal. The terminal displays the results as graphs and dashboards.

[1140] Feedback reflection method

[1141] The user can provide feedback on the displayed analysis results. For example, if an accounting staff member comments on areas for improvement in the income and expenditure analysis results, the device sends that feedback to the server. The server collects the feedback and reflects it in the generative AI model, thereby improving the accuracy of future analyses.

[1142] emotion recognition means

[1143] The server uses emotion recognition means to recognize the user's emotions. The emotion recognition means analyzes the user's input, voice, and facial expressions to identify emotions. For example, when a user enters a rating into the system, the system recognizes the user's emotion (happiness, sadness, anger, etc.) from the input and voice. Based on this, it provides feedback that matches the user's emotional state. Emotion data is collected and reflected in the generative AI model, contributing to improved analysis accuracy and user experience in future analyses.

[1144] Specific examples

[1145] As a concrete example, when a sales representative uses this system to check sales trends, they send a request from their terminal to the system. The server extracts the data and sends the analysis results to the terminal. The representative then checks the results and expresses their feedback and emotions about them. This emotional data is analyzed by the emotion recognition means, and the feedback and emotional data are reflected in the generative AI model during the next analysis. This process allows the system to continuously improve and maintain high user satisfaction.

[1146] Prompt Sentence Examples

[1147] "Get sales data, analyze and visualize sales trends over the past six months. Also, collect feedback on the analysis results, analyze user sentiment, and reflect it in your next project."

[1148] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1149] Step 1:

[1150] The server connects to multiple internal data sources (sales database, logistics system, human resources database, etc.) and collects data. API endpoints and authentication information are required as input. The server periodically calls the API to obtain data and saves it in local storage. For example, new sales data is obtained from the sales database every hour. The collected data in JSON format is saved as output. Specific operations include sending API requests and receiving response data.

[1151] Step 2:

[1152] The server performs preprocessing on the collected data. The collected JSON data is required as input. The server performs processes to impute missing values, remove duplicate data, and standardize data formats. For example, it standardizes the date and time format to "YYYY-MM-DD HH:MM:SS" and imputes missing sales data with the average value. A preprocessed data frame is generated as output. Specific operations include data cleansing and format conversion.

[1153] Step 3:

[1154] The server integrates the preprocessed data into a common data model. It requires a preprocessed data frame as input. The server maps data from different data sources into a unified schema and defines data relationships. For example, it associates sales data with customer data by linking customer IDs with order IDs. As output, it generates an integrated dataset and stores it in the data warehouse. Specific actions include write operations to the database.

[1155] Step 4:

[1156] The server uses AI to apply data governance. It requires an integrated dataset and access permission information as input. The server sets data access permissions and performs data classification and privacy protection. For example, it may grant access permission only to data related to a specific department. Sensitive data is encrypted and an access log is recorded. The output is a governed dataset and access log. Specific operations include setting access control lists and encryption.

[1157] Step 5:

[1158] The terminal visualizes and analyzes data based on the user's request. As input, it requires the user's request and a governed dataset. For example, if a user requests a sales trend report, the terminal sends the request to the server. The server performs data analysis using a generative AI model and sends the results to the terminal. As output, visualized graphs and dashboards are generated and displayed to the user. Specific operations include data extraction and rendering of analysis results.

[1159] Step 6:

[1160] The user provides feedback on the displayed analysis results. The analysis results and user feedback are required as input. The device sends the feedback to the server. The server collects the feedback and reflects it in the generative AI model to improve the accuracy of future analyses. An updated AI model is generated as output. Specific operations include collecting feedback data and retraining the model.

[1161] Step 7:

[1162] The server uses emotion recognition means to recognize the user's emotions. The input required is the user's input content, voice, and facial expression data. The server applies an emotion recognition algorithm to identify the user's emotions. For example, when a user enters a rating into the system, the server analyzes the emotion from the content and voice. The output is the user's emotional state, and appropriate feedback is provided based on that. Specific operations include emotion analysis and feedback generation.

[1163] (Application example 2)

[1164] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1165] In conventional factory data management systems, the processes of data collection, preprocessing, integration, governance, visualization, analysis, and feedback reflection are not integrated, making it difficult to analyze data and reflect feedback in real time.In addition, there is no system that analyzes workers' emotions and reflects them in feedback, so there are still challenges in improving the working environment.

[1166] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a data collection means, a preprocessing means, a data integration means, a data governance means, a data visualization and analysis means, a feedback reflection means, and an emotion recognition means. This makes it possible to collect, preprocess, and integrate data in real time from multiple data sources within the factory. In addition, data visualization and analysis can be performed based on the integrated data, and feedback can be reflected immediately. Furthermore, by using the emotion recognition means, it is possible to analyze the emotions of workers and use this information to improve the work environment.

[1167] "Data collection means" refers to a means of collecting data from multiple data sources and periodically obtaining the latest data using an API.

[1168] "Preprocessing means" refers to means for complementing missing values ​​in collected data, deleting duplicate data, and standardizing data formats.

[1169] A "data integration tool" is a tool that integrates pre-processed data into a common data model and maps data from different data sources into a unified schema.

[1170] "Data governance measures" are measures that use AI to manage access rights, classify data, and protect privacy.

[1171] "Data visualization and analysis means" refers to a means of visualizing data in response to user requests and analyzing it using an AI model.

[1172] The "feedback reflection means" is a means for collecting feedback from users on the displayed analysis results and reflecting that feedback in the AI ​​model.

[1173] An "emotion recognition means" is a means of analyzing a user's input, voice, and facial expressions to identify emotions and reflect them in the system.

[1174] This invention relates to a data management system for industrial robots, and provides a system that efficiently performs a series of processes from data collection to preprocessing, integration, governance, visualization, analysis, feedback reflection, and emotion recognition.

[1175] System Program

[1176] Specific program processing to realize each means is carried out separately for the server, terminal, and user.

[1177] Natural language explanations

[1178] 1. Data collection methods:

[1179] The server collects data from multiple data sources (such as each manufacturing process and machine in the factory). It connects to these data sources using APIs and periodically obtains the latest data. For example, operation data and quality data from each manufacturing line are collected every hour and sent to the server.

[1180] 2. Pretreatment methods:

[1181] The server processes the collected data by removing noise, formatting, and filling in missing values. It uses Python to standardize data formats and remove duplicate data. For example, it standardizes data in different formats for each production line and fills in missing quality data with the average value.

[1182] 3. Data integration methods:

[1183] The server integrates the preprocessed data into the AWS data warehouse, mapping data from different data sources to a unified schema and defining data relationships. For example, by linking manufacturing process IDs and machine IDs, the operation data and quality data for each process can be associated.

[1184] 4. Data Governance Measures:

[1185] The server uses AI to manage access rights, classify data, and protect privacy. For example, quality control personnel can be granted access only to quality data and not to other data. Confidential data is also encrypted and access logs are recorded for traceability.

[1186] 5. Data visualization and analysis tools:

[1187] The device visualizes data in response to user requests and performs analysis using AI models. Power BI is used to display real-time factory operation status and anomaly detection on a dashboard. For example, when a manufacturing department employee requests a production line operation trend report, the device sends it to the server and displays the analysis results on the dashboard.

[1188] 6. Feedback methods:

[1189] Users can provide feedback on the displayed analysis results. The feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model to improve the accuracy of future analyses. For example, if a quality control officer comments on areas for improvement in anomaly detection results, these comments will be reflected in the next analysis.

[1190] 7. Emotion recognition means:

[1191] The server uses Azure Cognitive Services to analyze the user's emotions. It identifies emotions from the user's input, voice, and facial expressions and reflects them as feedback. For example, when a worker enters an evaluation into the system, it recognizes emotions such as joy or stress from the input and voice and provides appropriate feedback.

[1192] Examples of specific examples and prompts

[1193] Robots in the factory collect operational data and send it to a server. The server uses Python scripts to preprocess the data, fill in missing values, and standardize the format. The preprocessed data is integrated in an AWS data warehouse, and various data sources are mapped. Azure Cognitive Services is used to create an emotion engine that analyzes feedback from workers and recognizes emotions such as joy and stress. Power BI is used to display real-time factory operation status on a dashboard, and workers are notified if an abnormality is detected.

[1194] Example prompt sentence:

[1195] "Devout a system that handles data collection, preprocessing, data integration, data governance, data visualization, feedback, and emotion recognition within the factory, and program it using Python, AWS, and Azure Cognitive Services. This will enable real-time monitoring of factory operation status, anomaly detection, and worker emotion analysis."

[1196] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1197] Step 1:

[1198] (Data Collection)

[1199] The server connects to each data source using an API to collect the requested data from multiple data sources. The input is operation data, quality data, and production progress data for each manufacturing process and machine in the factory. The output is the transfer of this data to the server. Specifically, the data collection program periodically sends requests to the API endpoint and stores the latest collected data on the server.

[1200] Step 2:

[1201] (Data preprocessing)

[1202] The server processes the collected raw data to improve its quality. The input is the raw data stored on the server. The output is preprocessed, cleaned data. Specifically, it performs operations such as imputing missing values ​​in the data with the mean value, removing duplicate data, and standardizing date formats. These data cleaning operations are performed using Python scripts.

[1203] Step 3:

[1204] (Data Integration)

[1205] The server integrates and centralizes the preprocessed data into a common data model. The input is the preprocessed data. The output is an integrated dataset. Specifically, using an AWS data warehouse or similar, the data provided from different data sources is mapped to a unified schema and linked based on keys such as manufacturing process IDs and machine IDs.

[1206] Step 4:

[1207] (Data Governance)

[1208] The server applies data governance to the integrated data using AI. The input is the integrated data set. The output is governance data that includes properly classified and encrypted data and access control information. Specifically, it sets data access rights, encrypts sensitive data, and records access logs. This is achieved using an access rights management system and encryption software.

[1209] Step 5:

[1210] (Data Visualization and Analysis)

[1211] The terminal visualizes data in response to user requests and performs analysis using an AI model. The input is the integrated dataset and the user request. The output is the analysis results and visualized data. Specifically, Power BI is used to display factory operation status and anomaly detection in real time on a dashboard. When a user requests analysis of specific data, it is sent to the server, which then analyzes it and sends the results to the terminal.

[1212] Step 6:

[1213] (Reflecting feedback)

[1214] The user provides feedback on the displayed analysis results. The input is the user's feedback. The output is the feedback results and data that will be reflected in the next analysis. Specifically, the feedback is sent from the device to the server, which collects it and reflects it in the AI ​​model. This improves the accuracy of data analysis from the next time onwards.

[1215] Step 7:

[1216] (emotion recognition)

[1217] The server uses Azure Cognitive Services to analyze the user's emotions. The inputs are the user's input, voice, and facial expression data. The output is the analyzed emotional data. Specifically, when the user enters an evaluation or feedback to the system, the system analyzes the text and voice data to identify the user's emotional state (for example, joy or stress), and feeds the results back to the system.

[1218] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1219] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1220] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1221] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1222] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1223] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1224] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1225] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1226] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1227] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1228] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1229] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1230] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1231] 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.

[1232] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1233] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1234] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1235] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1236] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1237] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1238] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1239] The following is further disclosed regarding the above embodiment.

[1240] (Claim 1)

[1241] data collection means;

[1242] A pre-processing means;

[1243] a data integration means;

[1244] Data governance measures;

[1245] data visualization and analysis tools;

[1246] A feedback reflection means;

[1247] A system including:

[1248] (Claim 2)

[1249] 2. The system according to claim 1, wherein the data collection means includes means for collecting data from a plurality of data sources and for periodically obtaining the data using an API.

[1250] (Claim 3)

[1251] 2. The system according to claim 1, wherein the preprocessing means includes means for completing missing values ​​of the collected data, deleting duplicate data, and standardizing data formats.

[1252] (Claim 4)

[1253] 2. The system of claim 1, wherein the data integration means includes means for integrating the pre-processed data into a common data model, defining relationships between the data, and performing normalization.

[1254] (Claim 5)

[1255] The system of claim 1 , wherein the data governance means includes means for using AI to manage access rights, data classification, and privacy management.

[1256] (Claim 6)

[1257] The system of claim 1, wherein the data visualization and analysis means includes means for extracting necessary data from the integrated database based on a user request, analyzing and predicting using AI, and displaying the results using a visualization tool.

[1258] (Claim 7)

[1259] 2. The system according to claim 1, wherein the feedback reflecting means includes means for collecting feedback from users and reflecting it in the AI ​​model to improve the accuracy of subsequent analyses.

[1260] "Example 1"

[1261] (Claim 1)

[1262] data collection means;

[1263] A pre-processing means;

[1264] a data integration means;

[1265] Data governance measures;

[1266] data visualization and analysis tools;

[1267] A feedback reflection means;

[1268] A system including:

[1269] (Claim 2)

[1270] 2. The system according to claim 1, wherein the data collection means includes means for collecting data from a plurality of data sources and for periodically obtaining the data using an API.

[1271] (Claim 3)

[1272] 2. The system according to claim 1, wherein the preprocessing means includes means for completing missing values ​​of the collected data, deleting duplicate data, and standardizing data formats.

[1273] (Claim 4)

[1274] 2. The system of claim 1, wherein the data integration means includes means for mapping data from different data sources to a unified schema and storing the data in a data warehouse.

[1275] (Claim 5)

[1276] 2. The system of claim 1, wherein the data governance means includes means for using AI to manage access rights and to classify and encrypt data.

[1277] (Claim 6)

[1278] 2. The system of claim 1, wherein the data visualization and analysis means includes means for analyzing data in response to a user request and displaying the data as a graph or dashboard.

[1279] (Claim 7)

[1280] 2. The system of claim 1, wherein the feedback reflecting means includes means for collecting feedback from users and retraining and improving the generative AI model based on the feedback.

[1281] "Application Example 1"

[1282] (Claim 1)

[1283] data collection means;

[1284] A pre-processing means;

[1285] a data integration means;

[1286] Data governance measures;

[1287] data visualization and analysis tools;

[1288] A feedback reflection means;

[1289] a real-time data collection means;

[1290] Proposal methods for improving efficiency,

[1291] a dashboard display means;

[1292] A system including:

[1293] (Claim 2)

[1294] 2. The system of claim 1, wherein the data collection means includes means for collecting data from multiple data sources, periodically obtaining data using an API, and further including means for updating each logistics process in real time.

[1295] (Claim 3)

[1296] 2. The system according to claim 1, wherein the preprocessing means includes means for completing missing values ​​in the collected data, deleting duplicate data, and standardizing data formats, and for implementing proposals for improving the efficiency of logistics data.

[1297] "Example 2: Combining Emotion Engines"

[1298] (Claim 1)

[1299] data collection means;

[1300] A pre-processing means;

[1301] a data integration means;

[1302] Data governance measures;

[1303] data visualization and analysis tools;

[1304] A feedback reflection means;

[1305] A system including an emotion recognition means.

[1306] (Claim 2)

[1307] 2. The system according to claim 1, wherein the data collection means includes means for collecting data from a plurality of data sources and for periodically obtaining the data using an API.

[1308] (Claim 3)

[1309] 2. The system according to claim 1, wherein the preprocessing means includes means for completing missing values ​​of the collected data, deleting duplicate data, and standardizing data formats.

[1310] "Application example 2 when combining emotion engines"

[1311] (Claim 1)

[1312] data collection means;

[1313] A pre-processing means;

[1314] a data integration means;

[1315] Data governance measures;

[1316] data visualization and analysis tools;

[1317] A feedback reflection means;

[1318] An emotion recognition means;

[1319] A system including:

[1320] (Claim 2)

[1321] 2. The system according to claim 1, wherein the data collection means includes means for collecting data from a plurality of data sources and for periodically obtaining the data using an API.

[1322] (Claim 3)

[1323] 2. The system according to claim 1, wherein the preprocessing means includes means for completing missing values ​​of the collected data, deleting duplicate data, and standardizing data formats.

[1324] (Claim 4)

[1325] 2. The system according to claim 1, wherein the emotion recognition means includes means for analyzing the user's emotion and reflecting the emotion as feedback.

[1326] (Claim 5)

[1327] 2. The system according to claim 1, wherein the data collection means, the preprocessing means, the data integration means, the data governance means, the data visualization and analysis means, the feedback reflection means and the emotion recognition means are installed on an industrial robot. [Explanation of symbols]

[1328] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A data collection means for collecting data from multiple data sources and periodically acquiring data using an API; A preprocessing method for completing missing values ​​in the collected data, deleting duplicate data, and standardizing the data format; A data integration method that integrates the preprocessed data into a common data model, defines data relationships, and normalizes the data; Data governance measures that use AI to manage access rights, data classification, and privacy; A data visualization and analysis means that extracts necessary data from the integrated database based on user requests, analyzes and predicts it using AI, and displays the results using a visualization tool; and A feedback reflection method that collects feedback from users and reflects it in the AI ​​model to improve the accuracy of analysis from the next time onwards; A system including:

Images