system

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting data from a plurality of systems in an enterprise and storing the data in an integrated database; means for analyzing a program code or SQL for data processing and understanding a data flow; means for generating a data flow diagram from an analysis result; means for visually providing the generated data flow diagram to a user; and interactive artificial intelligence means for responding to a user's question based on analyzed data flow information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, many companies have been required to efficiently manage massive amounts of data in order to utilize AI technology. However, as the amount of data increases, the cost of managing it also increases, making it particularly difficult to understand data flows, detect anomalies, and respond quickly. Furthermore, with the strengthening of privacy protection and regulations, it is necessary to accurately understand data flows and ensure transparency. Against this background, efficient data management using conventional methods is difficult, and there are challenges such as the need for large amounts of human resources. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides a system that includes a means for collecting data from multiple systems within a company and storing it in an integrated database, a means for analyzing program code and SQL that processes data to understand the data flow, a means for generating a data flow diagram from the analysis results, a means for visually presenting the generated data flow diagram to the user, a means for detecting data loss or anomalies and notifying the user, and an interactive artificial intelligence means for answering user questions based on the analyzed data flow information. This system improves the efficiency of data management, reduces human resources, and enables rapid problem resolution. It also enables privacy protection and compliance with regulations while maintaining data transparency.

[0006] "Data collection" is the process of obtaining necessary data from multiple systems within a company and storing it in an integrated database.

[0007] An "integrated database" is a database system for centrally managing data collected from multiple systems.

[0008] "Program code" is a set of instructions written to perform a particular calculation or process data.

[0009] "SQL" is an abbreviation for Structured Query Language, a programming language for querying and manipulating database management systems.

[0010] "Analysis" is the process of examining and examining data and program code in detail to understand their structure and behavior.

[0011] A "data flow diagram" is a visual representation of how data moves and is processed.

[0012] "Visually providing" refers to displaying data and analysis results in a format that users can intuitively understand.

[0013] "Missing" refers to a state in which part of the data is missing.

[0014] An "anomaly" refers to an unusual phenomenon or condition that deviates from expected data or behavior.

[0015] A "notification" is the act of conveying information to a user about a particular event or condition.

[0016] "Conversational artificial intelligence" is an AI system that provides appropriate answers and assistance in response to questions and requests from users in natural language.

[0017] "Data flow information" is data that includes detailed information about the flow and processing of data.

[0018] "Anomaly detection" is the process of automatically detecting missing or anomalies in data. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention relates to a system that uses interactive artificial intelligence to analyze and manage data flows in order to improve the efficiency of data management within a company.

[0041] System Overview

[0042] This system has the following configuration:

[0043] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[0044] Program understanding module: The server sends the program code and SQL that processes the data to the AI ​​engine for analysis.

[0045] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[0046] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[0047] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[0048] Program processing

[0049] Data collection

[0050] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as temporary files and then inserted into the integrated database.

[0051] Program Comprehension

[0052] Users upload the program code and SQL scripts they use to process data to the server, which then sends them to the interactive AI engine for analysis.

[0053] Data Flow Analysis

[0054] The AI ​​engine analyzes program code and SQL scripts to understand the data flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[0055] visualization

[0056] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[0057] Incident response

[0058] The server uses database monitoring tools to detect missing data or abnormalities. If detected, the user is notified. The user can check detailed information on the dashboard and ask questions to the interactive AI. The AI ​​engine responds to the user's questions by providing appropriate answers based on the analyzed data flow information.

[0059] Specific examples

[0060] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0061] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. Where does this affect?" and receives information about the extent of the impact from the AI ​​engine. In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] The server collects sales data, customer data, inventory data, etc. from multiple systems within the company using APIs and ETL tools. The collected data is temporarily stored in files.

[0065] Step 2:

[0066] The server reads the data from the temporary file and inserts it into the consolidated database. After the insert process is complete, the temporary file is deleted.

[0067] Step 3:

[0068] Users upload data processing program codes and SQL scripts to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[0069] Step 4:

[0070] The AI ​​engine analyzes the received program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[0071] Step 5:

[0072] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram is created in a format that includes node and edge information.

[0073] Step 6:

[0074] The server displays the generated data flow diagram on a dashboard, and users can access the dashboard through their terminals to visually check the data flow diagram.

[0075] Step 7:

[0076] The server uses the integrated database monitoring tool to detect data loss or anomalies, and if detected, generates an alert and notifies the user.

[0077] Step 8:

[0078] Users can check alert notifications on a dashboard via their device and ask questions to the conversational AI.

[0079] Step 9:

[0080] The conversational AI engine responds to user questions based on analyzed data flow information, allowing users to quickly take steps to resolve problems based on the AI's answers.

[0081] Through these steps, the system will streamline data management for companies, reduce human resources and costs, and enable faster response.

[0082] Example 1

[0083] 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."

[0084] Modern companies need to collect and manage a wide variety of data from multiple systems. There is a need to improve the efficiency and accuracy of this data management, as well as to quickly detect and address missing or anomalies in the data. However, with conventional systems, it is difficult to accurately understand the data flow and provide a visual representation of it, and it is also difficult to quickly respond to missing or anomalies in the data. The objective of this invention is to efficiently solve these problems and improve the efficiency of data management operations by introducing interactive artificial intelligence.

[0085] 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.

[0086] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that processes data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive artificial intelligence means for responding to a user's questions based on analyzed data flow information; means for requesting analysis of a data processing program using the interactive artificial intelligence means; means for generating a data flow diagram based on the analysis results from the AI ​​engine; means for detecting database loss or anomalies using a monitoring tool; and means for notifying the user of detected anomalies. This enables the series of tasks of collecting, analyzing, visualizing, and monitoring data to be performed efficiently and accurately.

[0087] 1. "Means for collecting data from multiple systems within a company and storing it in an integrated database" refers to a method for collecting data from various information systems within a company and storing it in a centrally managed database.

[0088] 2. "Methods for understanding data flow by analyzing program code and SQL that processes data" refers to methods for analyzing program code and SQL scripts provided by users, thereby understanding the flow and relationships of data.

[0089] 3. "Means for generating a data flow diagram from analysis results" refers to a method for creating a diagram that visually represents the flow of data based on the analyzed information.

[0090] 4. "Means for visually presenting the generated data flow diagram to the user" refers to a method for presenting the generated data flow diagram in a format that allows the user to visually confirm it.

[0091] 5. "Means for detecting missing or abnormal data and notifying users" refers to a method for detecting missing or abnormal data in a database and notifying users of that information.

[0092] 6. "Interactive AI means that answers user questions based on analyzed data flow information" refers to an AI system that uses analyzed data flow information to provide appropriate answers to user questions.

[0093] 7. "Means for requesting the analysis of a data processing program using interactive artificial intelligence means" means a method for requesting the analysis of a data processing program using interactive artificial intelligence.

[0094] 8. "Means for generating a data flow diagram based on the analysis results from an AI engine" means a method for creating a data flow diagram based on the analysis results provided by an AI engine.

[0095] 9. "Means for detecting database defects and abnormalities using monitoring tools" refers to a method for detecting defects and abnormalities in a database using dedicated monitoring tools.

[0096] 10. "Means for notifying users of detected abnormalities" refers to a method for notifying users of information about detected abnormalities, thereby enabling early detection and response to problems.

[0097] The present invention provides a system that uses interactive artificial intelligence to improve the efficiency of data management within a company and quickly detect and respond to data loss and anomalies. The following describes in detail the embodiments of the present invention.

[0098] Data Collection and Management

[0099] 1. The server collects data from multiple information systems within the company, either through APIs or using ETL tools (e.g., Apache NiFi or Talend).

[0100] 2. The collected data is first saved as a temporary file, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[0101] Program Comprehension and Analysis

[0102] 3. The user uploads the program code (e.g., Python script) or SQL script for data processing to the server.

[0103] 4. The server sends the uploaded program code and SQL script to an interactive artificial intelligence engine (e.g., OpenAI's GPT-4) and requests analysis.

[0104] Dataflow Analysis and Visualization

[0105] 5. The server receives the analysis results returned from the AI ​​engine in JSON format and generates a data flow diagram based on them. A visualization tool such as Graphviz can be used to generate this diagram.

[0106] 6. The generated data flow diagram is provided from the server to the user's device and visually displayed on a dashboard, allowing the user to intuitively understand the data flow.

[0107] Data Monitoring and Incident Response

[0108] 7. The server uses a monitoring tool (e.g., Prometheus or Nagios) to monitor the database and detect missing data or abnormalities.

[0109] 8. If an abnormality is detected, the server notifies the user of the information, often via email or SMS.

[0110] 9. Users can view detailed information on the dashboard and ask questions to the conversational AI, such as, "What is the impact of the data loss on 2023-03-01?"

[0111] 10. The AI ​​engine provides appropriate answers to user questions based on the analyzed data flow information.

[0112] Specific examples

[0113] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0114] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" The AI ​​engine responds, "The impact applies to all reports related to the date column in the sales table." In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[0115] Prompt Sentence Examples

[0116] Analyze the following SQL query and explain the data flow: SELECT FROM sales WHERE date = '2023-03-01';

[0117] "What is the extent of the impact if sales data is missing?"

[0118] This invention makes it possible to efficiently and accurately perform a series of tasks, including data collection, analysis, visualization, and monitoring, thereby significantly improving corporate data management operations.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] Data Collection Request

[0122] The server initiates API requests and ETL processes to collect data from multiple systems within the enterprise.

[0123] Input: The server uses the endpoint URL and authentication information for a specific system.

[0124] Output: Data collected from each system (sales data, customer data, inventory data, etc.)

[0125] Specific operation: The server uses the REST API to send a GET request to the sales data system to obtain the latest sales data.

[0126] Step 2:

[0127] Temporary data storage

[0128] The server stores the retrieved data in a temporary file to ensure that the data is not lost if subsequent processing fails.

[0129] Input: Data collected in step 1

[0130] Output: Data saved to a temporary file

[0131] Specific operation: The server saves the acquired sales data in a temporary file in JSON format.

[0132] Step 3:

[0133] Inserting into the database

[0134] The server reads the data stored in the temporary file and inserts it into the consolidated database.

[0135] Input: Data saved in a temporary file

[0136] Output: Data inserted into the integrated database

[0137] Specific operation: The server writes sales data to the MySQL database using an INSERT statement.

[0138] Step 4:

[0139] Uploading the program code

[0140] Users upload program code and SQL scripts for data processing to the server.

[0141] Input: User-supplied program code or SQL script

[0142] Output: Code or script uploaded to the server

[0143] What it does: A user uploads their Python script to the server using a file upload form in their browser.

[0144] Step 5:

[0145] Request for program code analysis

[0146] The server sends the uploaded program code and SQL scripts to an interactive artificial intelligence engine and requests analysis.

[0147] Input: Uploaded program code or SQL script

[0148] Output: Analysis request sent to the AI ​​engine

[0149] Specific operation: The server sends the Python script to the AI ​​engine as an HTTP request.

[0150] Step 6:

[0151] Analysis by AI engine

[0152] The AI ​​engine analyzes the received program code and SQL scripts and understands the data flow.

[0153] Input: Submitted program code or SQL script

[0154] Output: Analysis results (detailed data flow information)

[0155] What it does: The AI ​​engine analyzes the Python script and identifies which tables and columns are used.

[0156] Step 7:

[0157] Receiving analysis results

[0158] The server receives the analysis results from the AI ​​engine and stores them in JSON format.

[0159] Input: Analysis results from the AI ​​engine

[0160] Output: Parsed results saved in JSON format

[0161] Specific operation: The server saves the JSON data received from the AI ​​engine in a temporary file.

[0162] Step 8:

[0163] Generate a data flow diagram

[0164] The server generates a data flow diagram based on the analysis results.

[0165] Input: Parsed result in JSON format

[0166] Output: Generated data flow diagram

[0167] Specific operation: The server generates a data flow diagram using Graphviz and saves it in PNG format.

[0168] Step 9:

[0169] Providing data flow diagrams

[0170] The server provides the generated data flow diagram to the user's terminal.

[0171] Input: Generated Data Flow Diagram

[0172] Output: A data flow diagram displayed on the user's dashboard

[0173] Specific operation: The server displays a link to the data flow diagram on the dashboard, and when the user clicks it, the image is displayed.

[0174] Step 10:

[0175] User visual confirmation

[0176] The user visually checks the data flow diagram on the dashboard.

[0177] Input: Data flow diagram on dashboard

[0178] Output: Data flow diagram understanding and analysis results

[0179] Specific operation: The user accesses the dashboard using a browser and checks the displayed data flow diagram.

[0180] Step 11:

[0181] Data monitoring and anomaly detection

[0182] The server uses a database monitoring tool to detect missing data or abnormalities.

[0183] Input: Monitoring data from monitoring tools

[0184] Output: Information about detected anomalies

[0185] What it does: The server uses Prometheus to monitor specific database tables and generates alerts if anything is abnormal.

[0186] Step 12:

[0187] Sending abnormality notifications

[0188] The server notifies the user of the detected abnormality.

[0189] Input: Information about the detected anomaly

[0190] Output: Notification sent to the user

[0191] Specific operation: The server notifies the user of the missing data via email or SMS.

[0192] Step 13:

[0193] Find out more information and ask questions

[0194] Users can view detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[0195] Input: Details on the dashboard

[0196] Output: Questions sent to the conversational AI

[0197] Specific behavior: A user uses the chat window on the dashboard to ask, "What is the impact of the data loss on 2023-03-01?"

[0198] Step 14:

[0199] Answers from the AI ​​engine

[0200] The AI ​​engine provides answers to user questions based on analyzed data flow information.

[0201] Input: User question

[0202] Output: Parsed data flow information as an answer

[0203] Specific operation: Based on the analysis results, the AI ​​engine responds, "This affects the relevant records in the sales table."

[0204] (Application example 1)

[0205] 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."

[0206] Logistics centers require a method to efficiently integrate large amounts of operational data, such as inventory data, delivery data, and order data, collected from multiple systems, and visualize the data flow in real time. They also need a method to quickly detect missing or abnormal data and identify the extent of the impact so that users can take appropriate action. While systems utilizing interactive artificial intelligence are expected to solve these problems, existing systems often cannot adequately address these issues.

[0207] 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.

[0208] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that process data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting missing or abnormal data and notifying the user; interactive AI means for answering user questions based on the analyzed data flow information; means for acquiring business data via an interface and improving the efficiency of data management at the logistics center; means for analyzing the flow of inventory data, delivery data, and order data at the logistics center and visualizing it in real time; and means for identifying the scope of impact using interactive AI when a problem occurs. This enables integrated management of large-scale business data at a logistics center, real-time visualization of data flow, and rapid detection and response to data abnormalities.

[0209] A "data collection module" is a means of collecting data from multiple systems within a company and storing it in an integrated database.

[0210] The "program comprehension module" is a means of analyzing program code and SQL that processes data and understanding the flow of data.

[0211] The "data flow analysis module" is a means for generating a data flow diagram from the analysis results.

[0212] The "visualization module" is a means for visually presenting the generated data flow diagram to the user.

[0213] The "incident response module" is a means of detecting data loss or abnormalities and notifying users.

[0214] "Interactive AI" is a method of answering user questions based on analyzed data flow information.

[0215] An "interface" is a means of acquiring business data and streamlining data management at logistics centers.

[0216] "Real-time visualization" is a method of analyzing the flow of inventory data, delivery data, and order data at a logistics center and visualizing it in real time.

[0217] The "means for identifying the extent of impact" is a means for identifying the extent of impact using interactive artificial intelligence when a problem occurs.

[0218] This invention is a system for improving the efficiency of data management in logistics centers, and is composed of a server, a smartphone application, and interactive artificial intelligence.

[0219] System Configuration

[0220] Data Collection Module

[0221] The server collects inventory data, shipping data, order data, and other data from multiple systems within the company. This collection is performed using APIs and ETL tools, and the data is saved as temporary files before being inserted into an integrated database. The specific hardware and software used are AWS Lambda, Amazon RDS, and API Gateway.

[0222] Program Comprehension Module

[0223] The program code and SQL scripts uploaded by the user are sent to the server and analyzed by the interactive AI engine. This analysis is performed using AWS SageMaker, and the analysis results are returned to the server in JSON format.

[0224] Dataflow Analysis Module

[0225] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. This generation is also performed by AWS Lambda.

[0226] Visualization Module

[0227] The generated data flow diagram is stored in Amazon S3 and displayed on a dashboard using Amazon QuickSight, allowing users to visually check the flow of data.

[0228] Incident Response Module

[0229] The server uses CloudWatch, a database monitoring tool, to monitor and detect missing data or anomalies. If an anomaly is detected, the user is notified via Amazon SNS. In addition, a conversational artificial intelligence (AWS SageMaker) responds to user questions based on the analyzed data flow information.

[0230] Specific operation examples

[0231] At a logistics center, daily inventory data, delivery data, and order data are collected from each system onto a server and stored in an integrated database. If an abnormality occurs in the inventory data for a specific product one day, the system automatically detects the abnormality and notifies the user. The user uses a smartphone application to ask the conversational AI, "The inventory data for 2023-10-05 is incomplete. Which orders will be affected?" The conversational AI then provides a list of affected orders.

[0232] Prompt Sentence Examples

[0233] "I'm seeing gaps in my inventory data for a specific date. What impact does the missing data have on my business and which orders are affected?"

[0234] This system enables integrated management of large-scale business data at logistics centers, real-time visualization of data flow, and rapid detection and response to data anomalies.

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1:

[0237] The server collects inventory data, shipping data, and order data from multiple systems within the company using APIs and ETL tools. This is done using AWS Lambda and API Gateway. The collected data is saved as temporary files and then inserted into a consolidated database in Amazon RDS. The input is raw data from each system, and the output is updates to the consolidated database.

[0238] Step 2:

[0239] Users upload the program code and SQL scripts they use to process data to the server. The server then sends these codes and scripts to AWS SageMaker for analysis. The input is the program code and SQL scripts provided by the user, and the output is the analysis results (in JSON format) from AWS SageMaker.

[0240] Step 3:

[0241] The server processes the analysis results received from AWS SageMaker and generates a data flow diagram. This process uses AWS Lambda. The input is the analysis results in JSON format, and the output is a data flow diagram.

[0242] Step 4:

[0243] The server stores the generated data flow diagram in Amazon S3 and uses Amazon QuickSight to visually display it on a dashboard. Users can check the data flow in real time through this dashboard. The input is the data flow diagram, and the output is the visual display on the Amazon QuickSight dashboard.

[0244] Step 5:

[0245] The server uses Amazon CloudWatch to monitor the integrated database and detect missing data or anomalies. If an anomaly is detected, it notifies the user using Amazon SNS. The input is the current state of the database, and the output is a notification when an anomaly is detected.

[0246] Step 6:

[0247] A user uses a smartphone application to ask the conversational AI about an anomaly, for example, "The inventory data for 2023-10-05 is incomplete. Which orders does this affect?" The input is the user's question, and the output is the answer from the conversational AI (AWS SageMaker).

[0248] Step 7:

[0249] The interactive AI identifies the scope of impact based on the analyzed data flow information and provides the user with an answer. This answer is displayed to the user through a smartphone application. The input is the data flow information and the user's question, and the output is the identified scope of impact and the answer.

[0250] These steps will improve the efficiency of data management in logistics centers, enabling real-time visualization of data flow and rapid detection and response to abnormalities.

[0251] 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.

[0252] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company.

[0253] System Overview

[0254] This system has the following configuration:

[0255] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[0256] Program understanding module: The server sends the program code and SQL that processes data to the interactive artificial intelligence engine for analysis.

[0257] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[0258] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[0259] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[0260] Emotion engine module: Recognizes the user's emotions and adjusts the conversational AI's responses accordingly.

[0261] Program processing

[0262] Data collection

[0263] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as a temporary file and then inserted into an integrated database.

[0264] Program Comprehension

[0265] Users upload data processing program codes and SQL scripts to the server, which then sends them to the interactive AI engine for analysis.

[0266] Data Flow Analysis

[0267] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[0268] visualization

[0269] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[0270] Incident response

[0271] The server uses the integrated database monitoring tool to detect missing data or anomalies. If detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine answers questions from the user based on the analyzed data flow information.

[0272] Utilizing the Emotion Engine

[0273] The emotion engine module analyzes the user's input and recognizes their emotions. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI engine. The conversational AI engine then adjusts its response based on the user's emotional state, for example, by replying in a more friendly tone or providing additional support information.

[0274] Specific examples

[0275] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0276] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" and receives information about the extent of the impact from the AI ​​engine. At this point, the emotion engine recognizes that the user is feeling stressed and feeds that information back to the conversational AI. As a result, the AI ​​speaks in a more friendly tone and provides additional support information, improving user satisfaction.

[0277] In this way, the system of the present invention improves the efficiency of data management for companies and provides a better user experience by responding to the user's emotional state.

[0278] The processing flow will be explained below.

[0279] Step 1:

[0280] The server collects sales data, customer data, and inventory data from multiple systems within the company using APIs and ETL tools, and stores the collected data as temporary files.

[0281] Step 2:

[0282] The server reads the data from the temporary file, inserts it into the consolidated database, and deletes the temporary file after the insert is complete.

[0283] Step 3:

[0284] Users upload program codes and SQL scripts to be used for data processing to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[0285] Step 4:

[0286] The conversational AI engine analyzes program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[0287] Step 5:

[0288] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram consists of nodes (starting points, intermediate points, and ending points of data) and edges (data flow).

[0289] Step 6:

[0290] The server provides the generated data flow diagram to the user's device, where the user can visually check the data flow diagram through the device's dashboard.

[0291] Step 7:

[0292] The server uses the integrated database monitoring tool to detect missing data or abnormalities. For example, if data for a specific date is missing, the server detects this information.

[0293] Step 8:

[0294] The server notifies the user of any detected defects or abnormalities, and the user receives an alert notification via their terminal and can check detailed information.

[0295] Step 9:

[0296] After checking the detailed information on the dashboard, users can ask the conversational AI a question, such as, "There is missing data for 2023-03-01. What impact does this have?"

[0297] Step 10:

[0298] The conversational AI engine provides appropriate answers to questions from the analyzed data flow information, and the answers are displayed to the user.

[0299] Step 11:

[0300] When a user asks a question, the device uses an emotion engine to analyze the user's emotions. For example, it can determine whether the user is feeling stressed based on the tempo at which they type and the choice of words.

[0301] Step 12:

[0302] The emotion engine feeds the analysis results back to the conversational artificial intelligence engine, which then adapts its response based on the user's emotional state. For example, if a user is feeling stressed, it will respond in a more friendly tone and provide additional support information.

[0303] Step 13:

[0304] The server uses the emotion engine and the adjusted AI engine to display the final answer to the user, allowing the user to take prompt and appropriate action based on this information.

[0305] Through these steps, the system will streamline data management for companies and provide a better user experience by responding to users' emotional states.

[0306] Example 2

[0307] 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."

[0308] In corporate data management, it is difficult to efficiently integrate and analyze data collected from multiple information systems, quickly detect missing data or anomalies, and notify users. Furthermore, there is a lack of a way to visually understand the flow of data processing, and when responses are required based on the user's emotional state, it is even more difficult to respond quickly and appropriately to discovered problems.

[0309] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting data from multiple information systems within a company and storing it in an integrated database; means for analyzing program code and database queries that perform data processing to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually providing the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive AI means for responding to user questions based on analyzed data flow information; and means for recognizing the user's emotional state and adjusting the interactive AI's response accordingly. This makes data management within the company more efficient, enables quick detection and notification of data loss or anomalies, enables visual understanding of data flows, and enables appropriate responses according to the user's emotional state.

[0310] "Multiple information systems within a company" refers to multiple independent digital systems operated by a company, including systems for sales, customer management, inventory management, etc.

[0311] "Means of collecting data and storing it in an integrated database" refers to the process of extracting data from multiple information systems using APIs and ETL tools, saving that data as temporary files, and then storing it in an integrated database.

[0312] "Data processing program code and database queries" refers to software code, SQL scripts, and other commands used to manipulate and analyze data.

[0313] "Data flow understanding" refers to the process of analyzing program code and database queries to determine how data moves and is transformed.

[0314] "Means for generating data flow diagrams" refers to the process of creating flowcharts or diagrams that visually represent the results of data analysis.

[0315] "Means for visually presenting the generated data flow diagram" refers to a process of displaying the data flow diagram in a visual interface such as a dashboard so that a user can intuitively understand the flow of data.

[0316] "Means for detecting data loss or anomalies and notifying users" refers to a system that uses an integrated database monitoring tool to detect data inconsistencies or loss and notify users of this as a warning.

[0317] "Interactive AI means" refers to an AI system that responds to user questions in text or voice and provides detailed information based on the results of data analysis.

[0318] "Means for recognizing the user's emotional state and adjusting the response accordingly" refers to the function of detecting the user's emotional state from their input and behavior and adapting the conversational AI's response accordingly.

[0319] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company. The system includes the following components, and is capable of collecting, analyzing, visualizing data, responding to incidents, and recognizing emotions.

[0320] System Configuration

[0321] Data collection modules:

[0322] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect data from multiple information systems within the company. Specifically, sales data, customer data, inventory data, etc. are collected from multiple systems. The collected data is first saved as a temporary file in local storage, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[0323] Example: Customer data is extracted from an internal customer relationship management system (CRM) via an API, saved as a temporary file, and then stored in a MySQL database.

[0324] Program Comprehension Module:

[0325] Users upload data processing program code and database queries (e.g., SQL scripts) to the server, which then sends the code and SQL scripts to an interactive AI engine (e.g., GPT-3, BERT) for analysis.

[0326] Example: A user uploads a SQL script for data processing through a designated upload interface on the server.

[0327] Dataflow Analysis Module:

[0328] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format, and the server uses this to generate a data flow diagram. This diagram is generated using tools such as D3.js and Graphviz.

[0329] Example: An interactive artificial intelligence engine interprets data join and transformation rules from SQL scripts and generates a diagram showing the data flow between each table.

[0330] Visualization Module:

[0331] The server provides the generated data flow diagram to the user's device, allowing the user to intuitively view the data flow diagram visually on a dashboard (e.g., Tableau, Power BI).

[0332] Example: The server sends the generated data flow diagram to the user's device via a web API, and the user can view the diagram by operating the dashboard through a browser.

[0333] Incident Response Module:

[0334] The server uses an integrated database monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine responds to questions from the user based on the analyzed data flow information.

[0335] Example: The server detects that sales data for a specific date is missing and notifies the user, who then asks, "The data for 2023-03-01 is missing, what impact does this have?"

[0336] Emotion Engine Module:

[0337] The emotion engine module analyzes user input and recognizes the emotional state (e.g., Affectiva, IBM Watson Tone Analyzer). If the user is feeling stressed, this information is fed back to the conversational AI engine, which adjusts the response, for example, by using a friendlier tone and providing additional support information.

[0338] Example: An emotion engine detects stress from user input, and the conversational AI responds in a friendly tone, "Let us know if we can help you. Additional support information is available here."

[0339] Prompt Sentence Examples

[0340] "There is a missing data for 2023-03-01, what is the impact?"

[0341] Through the above-mentioned modules and operation flow, this system can streamline data management within a company and provide appropriate feedback to users.

[0342] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0343] Step 1: Data collection

[0344] Input: Data from multiple information systems within the company

[0345] Output: Data stored in the integrated database

[0346] Operation:

[0347] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect sales data, customer data, and inventory data within the company from each information system.

[0348] The collected data is stored as a temporary file in the server's local storage.

[0349] The server extracts the data from these temporary files and inserts it into a consolidated database (e.g. MySQL, PostgreSQL).

[0350] Step 2: Uploading program code from the user

[0351] Input: Program code or SQL scripts uploaded by the user

[0352] Output: Data sent to the conversational AI engine

[0353] Operation:

[0354] The user uploads the program code or SQL script for data processing through the server's designated upload interface.

[0355] The server sends the uploaded program code or SQL script to an interactive artificial intelligence engine (e.g., GPT-3, BERT) for analysis.

[0356] Step 3: Analyzing the program code

[0357] Input: Program code or SQL script sent from the server to the interactive AI engine

[0358] Output: Parsed data flow information (JSON format)

[0359] Operation:

[0360] The interactive artificial intelligence engine analyzes program code and SQL scripts to understand data flow and processing flow.

[0361] The data flow information generated as a result of the analysis is returned to the server in JSON format.

[0362] The server receives and stores this JSON data.

[0363] Step 4: Generate a Data Flow Diagram

[0364] Input: Parsed data flow information (JSON format)

[0365] Output: Data flow diagram (visual format)

[0366] Operation:

[0367] The server generates a data flow diagram based on the data flow information in JSON format.

[0368] This generation uses tools such as D3.js and Graphviz.

[0369] The generated data flow diagram is saved in the server.

[0370] Step 5: Visualizing the Data Flow Diagram

[0371] Input: Generated data flow diagram

[0372] Output: A visual data flow diagram delivered to the user's device.

[0373] Operation:

[0374] The server sends the generated data flow diagram to the user's device via a web API.

[0375] Users can visually check the data flow diagram using a dashboard on their device (e.g., Tableau, Power BI).

[0376] Step 6: Data monitoring and incident response

[0377] Input: Data stream from the integrated database

[0378] Output: Alerts and conversational AI questions and responses

[0379] Operation:

[0380] The server periodically checks the data stream in the integrated database using a monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies.

[0381] If data loss or anomalies are detected, the server generates an alert to notify the user.

[0382] Users can view detailed information on the dashboard and ask questions to the conversational AI (e.g., "Data for 2023-03-01 is missing. What impact does this have?").

[0383] The interactive AI engine generates answers to questions from users based on the analyzed data flow information.

[0384] Step 7: Leverage your emotional engine

[0385] Input: User-entered data

[0386] Output: Tailored conversational AI response

[0387] Operation:

[0388] The emotion engine module analyzes the user's input and recognizes the emotional state (e.g., stress level).

[0389] The emotion engine feeds back this emotional situation information to the interactive artificial intelligence engine via the server.

[0390] The conversational AI engine adapts its responses depending on the emotional state, for example, replying in a friendly tone and providing additional supporting information.

[0391] (Application example 2)

[0392] 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."

[0393] Conventional corporate data management systems struggled to efficiently collect and integrate data from multiple information processing systems, requiring timely responses to missing or abnormal data. They also lacked a means to visually grasp data flow or a mechanism for providing rapid feedback based on data analysis results. Furthermore, they were unable to engage in dialogue that reflected the user's emotional state, and lacked functionality to reduce operator stress. There is a need to resolve these issues and improve data management efficiency and user experience.

[0394] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0395] In this invention, the server includes means for collecting data from multiple information processing systems within a company and storing it on an integrated recording medium, means for analyzing program code and database manipulation language for data processing to understand the flow of information, means for generating an information flow diagram from the analysis results, means for visually presenting the generated information flow diagram to the user, means for detecting missing or abnormal data and notifying the user, interactive artificial intelligence means for responding to user questions based on the analyzed information flow information, and emotion engine means for recognizing the user's emotional state and adjusting the response content. This makes data management within the company more efficient and enables flexible feedback that corresponds to the user's emotional state.

[0396] "Multiple information processing systems within an enterprise" refers collectively to multiple computer systems and software used within an enterprise for the purposes of generating, processing, storing, and managing data.

[0397] An "integrated recording medium" is a physical or virtual database or storage system for centrally storing and managing data collected from multiple information processing systems.

[0398] "Program code or database manipulation language" means a computer program or script, such as Structured Query Language (SQL), written to process, retrieve, or manipulate data.

[0399] "Information flow" is a concept that describes the process by which data flows from one system or process to another.

[0400] An "information flow diagram" is a diagram that visually represents the flow of data movement and transformation, and is also called a data flow diagram.

[0401] "Visually providing" means displaying the data graphically so that the user can intuitively understand the contents and flow of the data.

[0402] "Missing or anomalous data" refers to data that does not match the expected format or content, or is missing.

[0403] "Interactive artificial intelligence means" means an artificial intelligence technology that has the ability to answer questions and provide appropriate feedback through dialogue with a user.

[0404] An "emotion engine means" is a technology or module for analyzing a user's emotional state and adjusting the system's response or behavior based on that.

[0405] The present invention provides a system for improving the efficiency of data management within a company and providing a better user experience by responding to the emotional state of the user. This system is configured and operates as follows.

[0406] 1. Data Collection Module

[0407] The server collects data from multiple information processing systems within the company. APIs and ETL (Extract, Transform, Load) tools are used to collect a wide variety of information, including sales data, customer data, and inventory data. This information is saved in files as temporary storage media, and then inserted into a database, which serves as an integrated storage medium.

[0408] 2. Program Comprehension Module

[0409] Users upload program code and database manipulation language (SQL scripts) to the server. The server sends this code to an interactive AI engine for analysis. The analysis results are returned to the server in structured data format (JSON format).

[0410] 3. Dataflow Analysis Module

[0411] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow, and the server generates an information flow diagram based on the analysis results.

[0412] 4. Visualization Module

[0413] The server provides the generated information flow diagram to the user's terminal. The user can visually check the information flow diagram on the dashboard. The user interface uses a graphical user interface (GUI), allowing intuitive operation.

[0414] 5. Incident Response Module

[0415] The server uses the integrated recording media's monitoring tool to detect data loss or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine, which then provides answers based on the analyzed information flow information.

[0416] 6. Emotion Engine Module

[0417] The emotion engine analyzes the user's input and recognizes their emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The conversational AI then adjusts its response based on the user's emotional state, providing a more friendly tone or additional support information.

[0418] For example, a factory is using this system to manage production line data. It can monitor the data flow of machines and lines in the factory in real time, and take immediate action if an abnormality occurs. Furthermore, if an operator is feeling stressed, the emotion engine recognizes this and the conversational AI provides advice and encouraging messages.

[0419] An example prompt is:

[0420] "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the scope of its impact."

[0421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0422] Step 1:

[0423] The server collects data from multiple information processing systems within a company. Specifically, it uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. The collected data is stored on temporary recording media. The input is raw data obtained from each information processing system, and format conversion and data cleansing are performed to insert this data into the integrated recording media. The output is clean data in a unified format.

[0424] Step 2:

[0425] Users upload program code and SQL scripts for data processing to the server. The server sends these codes to the interactive AI engine. The input is the program code and SQL scripts provided by the user, and the interactive AI engine analyzes them to understand the code's processing flow and dependencies. The output is the analysis results returned in a structured data format (JSON).

[0426] Step 3:

[0427] The server generates an information flow diagram based on the analysis results received from the conversational AI engine. The input is the analysis results (JSON format) from the conversational AI engine, and the output is a visually easy-to-understand information flow diagram. This diagram is displayed on the dashboard.

[0428] Step 4:

[0429] The server provides the generated information flow diagram to the user's device. The user can visually check the information flow diagram on a dashboard. The input is the data from the information flow diagram, and the output is a graphical interface displayed on the user's device. Specifically, the user can check the details of the data flow using mouse or touch operations.

[0430] Step 5:

[0431] The server uses the integrated recording media monitoring tool to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The input is real-time monitored data, and the output is an alert and notification when an anomaly is detected. When the user receives this notification, they can check detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[0432] Step 6:

[0433] The user inputs a question to the conversational AI. For example, they input a prompt such as, "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the extent of its impact." The server receives this input and generates an answer based on the analyzed information flow information. The input is the user's question, and the output is the answer from the conversational AI.

[0434] Step 7:

[0435] The emotion engine analyzes the user's input and recognizes the user's emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The input is the user's emotional state, and the output is the adjusted response content of the conversational AI. The conversational AI provides a response according to the user's emotional state, for example, replying in a more friendly tone or providing additional support information.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] [Second embodiment]

[0440] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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."

[0452] The present invention relates to a system that uses interactive artificial intelligence to analyze and manage data flows in order to improve the efficiency of data management within a company.

[0453] System Overview

[0454] This system has the following configuration:

[0455] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[0456] Program understanding module: The server sends the program code and SQL that processes the data to the AI ​​engine for analysis.

[0457] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[0458] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[0459] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[0460] Program processing

[0461] Data collection

[0462] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as temporary files and then inserted into the integrated database.

[0463] Program Comprehension

[0464] Users upload the program code and SQL scripts they use to process data to the server, which then sends them to the interactive AI engine for analysis.

[0465] Data Flow Analysis

[0466] The AI ​​engine analyzes program code and SQL scripts to understand the data flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[0467] visualization

[0468] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[0469] Incident response

[0470] The server uses database monitoring tools to detect missing data or abnormalities. If detected, the user is notified. The user can check detailed information on the dashboard and ask questions to the interactive AI. The AI ​​engine responds to the user's questions by providing appropriate answers based on the analyzed data flow information.

[0471] Specific examples

[0472] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0473] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. Where does this affect?" and receives information about the extent of the impact from the AI ​​engine. In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[0474] The processing flow will be explained below.

[0475] Step 1:

[0476] The server collects sales data, customer data, inventory data, etc. from multiple systems within the company using APIs and ETL tools. The collected data is temporarily stored in files.

[0477] Step 2:

[0478] The server reads the data from the temporary file and inserts it into the consolidated database. After the insert process is complete, the temporary file is deleted.

[0479] Step 3:

[0480] Users upload data processing program codes and SQL scripts to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[0481] Step 4:

[0482] The AI ​​engine analyzes the received program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[0483] Step 5:

[0484] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram is created in a format that includes node and edge information.

[0485] Step 6:

[0486] The server displays the generated data flow diagram on a dashboard, and users can access the dashboard through their terminals to visually check the data flow diagram.

[0487] Step 7:

[0488] The server uses the integrated database monitoring tool to detect data loss or anomalies, and if detected, generates an alert and notifies the user.

[0489] Step 8:

[0490] Users can check alert notifications on a dashboard via their device and ask questions to the conversational AI.

[0491] Step 9:

[0492] The conversational AI engine responds to user questions based on analyzed data flow information, allowing users to quickly take steps to resolve problems based on the AI's answers.

[0493] Through these steps, the system will streamline data management for companies, reduce human resources and costs, and enable faster response.

[0494] Example 1

[0495] 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."

[0496] Modern companies need to collect and manage a wide variety of data from multiple systems. There is a need to improve the efficiency and accuracy of this data management, as well as to quickly detect and address missing or anomalies in the data. However, with conventional systems, it is difficult to accurately understand the data flow and provide a visual representation of it, and it is also difficult to quickly respond to missing or anomalies in the data. The objective of this invention is to efficiently solve these problems and improve the efficiency of data management operations by introducing interactive artificial intelligence.

[0497] 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.

[0498] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that processes data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive artificial intelligence means for responding to a user's questions based on analyzed data flow information; means for requesting analysis of a data processing program using the interactive artificial intelligence means; means for generating a data flow diagram based on the analysis results from the AI ​​engine; means for detecting database loss or anomalies using a monitoring tool; and means for notifying the user of detected anomalies. This enables the series of tasks of collecting, analyzing, visualizing, and monitoring data to be performed efficiently and accurately.

[0499] 1. "Means for collecting data from multiple systems within a company and storing it in an integrated database" refers to a method for collecting data from various information systems within a company and storing it in a centrally managed database.

[0500] 2. "Methods for understanding data flow by analyzing program code and SQL that processes data" refers to methods for analyzing program code and SQL scripts provided by users, thereby understanding the flow and relationships of data.

[0501] 3. "Means for generating a data flow diagram from analysis results" refers to a method for creating a diagram that visually represents the flow of data based on the analyzed information.

[0502] 4. "Means for visually presenting the generated data flow diagram to the user" refers to a method for presenting the generated data flow diagram in a format that allows the user to visually confirm it.

[0503] 5. "Means for detecting missing or abnormal data and notifying users" refers to a method for detecting missing or abnormal data in a database and notifying users of that information.

[0504] 6. "Interactive AI means that answers user questions based on analyzed data flow information" refers to an AI system that uses analyzed data flow information to provide appropriate answers to user questions.

[0505] 7. "Means for requesting the analysis of a data processing program using interactive artificial intelligence means" means a method for requesting the analysis of a data processing program using interactive artificial intelligence.

[0506] 8. "Means for generating a data flow diagram based on the analysis results from an AI engine" means a method for creating a data flow diagram based on the analysis results provided by an AI engine.

[0507] 9. "Means for detecting database defects and abnormalities using monitoring tools" refers to a method for detecting defects and abnormalities in a database using dedicated monitoring tools.

[0508] 10. "Means for notifying users of detected abnormalities" refers to a method for notifying users of information about detected abnormalities, thereby enabling early detection and response to problems.

[0509] The present invention provides a system that uses interactive artificial intelligence to improve the efficiency of data management within a company and quickly detect and respond to data loss and anomalies. The following describes in detail the embodiments of the present invention.

[0510] Data Collection and Management

[0511] 1. The server collects data from multiple information systems within the company, either through APIs or using ETL tools (e.g., Apache NiFi or Talend).

[0512] 2. The collected data is first saved as a temporary file, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[0513] Program Comprehension and Analysis

[0514] 3. The user uploads the program code (e.g., Python script) or SQL script for data processing to the server.

[0515] 4. The server sends the uploaded program code and SQL script to an interactive artificial intelligence engine (e.g., OpenAI's GPT-4) and requests analysis.

[0516] Dataflow Analysis and Visualization

[0517] 5. The server receives the analysis results returned from the AI ​​engine in JSON format and generates a data flow diagram based on them. A visualization tool such as Graphviz can be used to generate this diagram.

[0518] 6. The generated data flow diagram is provided from the server to the user's device and visually displayed on a dashboard, allowing the user to intuitively understand the data flow.

[0519] Data Monitoring and Incident Response

[0520] 7. The server uses a monitoring tool (e.g., Prometheus or Nagios) to monitor the database and detect missing data or abnormalities.

[0521] 8. If an abnormality is detected, the server notifies the user of the information, often via email or SMS.

[0522] 9. Users can view detailed information on the dashboard and ask questions to the conversational AI, such as, "What is the impact of the data loss on 2023-03-01?"

[0523] 10. The AI ​​engine provides appropriate answers to user questions based on the analyzed data flow information.

[0524] Specific examples

[0525] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0526] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" The AI ​​engine responds, "The impact applies to all reports related to the date column in the sales table." In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[0527] Prompt Sentence Examples

[0528] Analyze the following SQL query and explain the data flow: SELECT FROM sales WHERE date = '2023-03-01';

[0529] "What is the extent of the impact if sales data is missing?"

[0530] This invention makes it possible to efficiently and accurately perform a series of tasks, including data collection, analysis, visualization, and monitoring, thereby significantly improving corporate data management operations.

[0531] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0532] Step 1:

[0533] Data Collection Request

[0534] The server initiates API requests and ETL processes to collect data from multiple systems within the enterprise.

[0535] Input: The server uses the endpoint URL and authentication information for a specific system.

[0536] Output: Data collected from each system (sales data, customer data, inventory data, etc.)

[0537] Specific operation: The server uses the REST API to send a GET request to the sales data system to obtain the latest sales data.

[0538] Step 2:

[0539] Temporary data storage

[0540] The server stores the retrieved data in a temporary file to ensure that the data is not lost if subsequent processing fails.

[0541] Input: Data collected in step 1

[0542] Output: Data saved to a temporary file

[0543] Specific operation: The server saves the acquired sales data in a temporary file in JSON format.

[0544] Step 3:

[0545] Inserting into the database

[0546] The server reads the data stored in the temporary file and inserts it into the consolidated database.

[0547] Input: Data saved in a temporary file

[0548] Output: Data inserted into the integrated database

[0549] Specific operation: The server writes sales data to the MySQL database using an INSERT statement.

[0550] Step 4:

[0551] Uploading the program code

[0552] Users upload program code and SQL scripts for data processing to the server.

[0553] Input: User-supplied program code or SQL script

[0554] Output: Code or script uploaded to the server

[0555] What it does: A user uploads their Python script to the server using a file upload form in their browser.

[0556] Step 5:

[0557] Request for program code analysis

[0558] The server sends the uploaded program code and SQL scripts to an interactive artificial intelligence engine and requests analysis.

[0559] Input: Uploaded program code or SQL script

[0560] Output: Analysis request sent to the AI ​​engine

[0561] Specific operation: The server sends the Python script to the AI ​​engine as an HTTP request.

[0562] Step 6:

[0563] Analysis by AI engine

[0564] The AI ​​engine analyzes the received program code and SQL scripts and understands the data flow.

[0565] Input: Submitted program code or SQL script

[0566] Output: Analysis results (detailed data flow information)

[0567] What it does: The AI ​​engine analyzes the Python script and identifies which tables and columns are used.

[0568] Step 7:

[0569] Receiving analysis results

[0570] The server receives the analysis results from the AI ​​engine and stores them in JSON format.

[0571] Input: Analysis results from the AI ​​engine

[0572] Output: Parsed results saved in JSON format

[0573] Specific operation: The server saves the JSON data received from the AI ​​engine in a temporary file.

[0574] Step 8:

[0575] Generate a data flow diagram

[0576] The server generates a data flow diagram based on the analysis results.

[0577] Input: Parsed result in JSON format

[0578] Output: Generated data flow diagram

[0579] Specific operation: The server generates a data flow diagram using Graphviz and saves it in PNG format.

[0580] Step 9:

[0581] Providing data flow diagrams

[0582] The server provides the generated data flow diagram to the user's terminal.

[0583] Input: Generated Data Flow Diagram

[0584] Output: A data flow diagram displayed on the user's dashboard

[0585] Specific operation: The server displays a link to the data flow diagram on the dashboard, and when the user clicks it, the image is displayed.

[0586] Step 10:

[0587] User visual confirmation

[0588] The user visually checks the data flow diagram on the dashboard.

[0589] Input: Data flow diagram on dashboard

[0590] Output: Data flow diagram understanding and analysis results

[0591] Specific operation: The user accesses the dashboard using a browser and checks the displayed data flow diagram.

[0592] Step 11:

[0593] Data monitoring and anomaly detection

[0594] The server uses a database monitoring tool to detect missing data or abnormalities.

[0595] Input: Monitoring data from monitoring tools

[0596] Output: Information about detected anomalies

[0597] What it does: The server uses Prometheus to monitor specific database tables and generates alerts if anything is abnormal.

[0598] Step 12:

[0599] Sending abnormality notifications

[0600] The server notifies the user of the detected abnormality.

[0601] Input: Information about the detected anomaly

[0602] Output: Notification sent to the user

[0603] Specific operation: The server notifies the user of the missing data via email or SMS.

[0604] Step 13:

[0605] Find out more information and ask questions

[0606] Users can view detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[0607] Input: Details on the dashboard

[0608] Output: Questions sent to the conversational AI

[0609] Specific behavior: A user uses the chat window on the dashboard to ask, "What is the impact of the data loss on 2023-03-01?"

[0610] Step 14:

[0611] Answers from the AI ​​engine

[0612] The AI ​​engine provides answers to user questions based on analyzed data flow information.

[0613] Input: User question

[0614] Output: Parsed data flow information as an answer

[0615] Specific operation: Based on the analysis results, the AI ​​engine responds, "This affects the relevant records in the sales table."

[0616] (Application example 1)

[0617] 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."

[0618] Logistics centers require a method to efficiently integrate large amounts of operational data, such as inventory data, delivery data, and order data, collected from multiple systems, and visualize the data flow in real time. They also need a method to quickly detect missing or abnormal data and identify the extent of the impact so that users can take appropriate action. While systems utilizing interactive artificial intelligence are expected to solve these problems, existing systems often cannot adequately address these issues.

[0619] 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.

[0620] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that process data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting missing or abnormal data and notifying the user; interactive AI means for answering user questions based on the analyzed data flow information; means for acquiring business data via an interface and improving the efficiency of data management at the logistics center; means for analyzing the flow of inventory data, delivery data, and order data at the logistics center and visualizing it in real time; and means for identifying the scope of impact using interactive AI when a problem occurs. This enables integrated management of large-scale business data at a logistics center, real-time visualization of data flow, and rapid detection and response to data abnormalities.

[0621] A "data collection module" is a means of collecting data from multiple systems within a company and storing it in an integrated database.

[0622] The "program comprehension module" is a means of analyzing program code and SQL that processes data and understanding the flow of data.

[0623] The "data flow analysis module" is a means for generating a data flow diagram from the analysis results.

[0624] The "visualization module" is a means for visually presenting the generated data flow diagram to the user.

[0625] The "incident response module" is a means of detecting data loss or abnormalities and notifying users.

[0626] "Interactive AI" is a method of answering user questions based on analyzed data flow information.

[0627] An "interface" is a means of acquiring business data and streamlining data management at logistics centers.

[0628] "Real-time visualization" is a method of analyzing the flow of inventory data, delivery data, and order data at a logistics center and visualizing it in real time.

[0629] The "means for identifying the extent of impact" is a means for identifying the extent of impact using interactive artificial intelligence when a problem occurs.

[0630] This invention is a system for improving the efficiency of data management in logistics centers, and is composed of a server, a smartphone application, and interactive artificial intelligence.

[0631] System Configuration

[0632] Data Collection Module

[0633] The server collects inventory data, shipping data, order data, and other data from multiple systems within the company. This collection is performed using APIs and ETL tools, and the data is saved as temporary files before being inserted into an integrated database. The specific hardware and software used are AWS Lambda, Amazon RDS, and API Gateway.

[0634] Program Comprehension Module

[0635] The program code and SQL scripts uploaded by the user are sent to the server and analyzed by the interactive AI engine. This analysis is performed using AWS SageMaker, and the analysis results are returned to the server in JSON format.

[0636] Dataflow Analysis Module

[0637] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. This generation is also performed by AWS Lambda.

[0638] Visualization Module

[0639] The generated data flow diagram is stored in Amazon S3 and displayed on a dashboard using Amazon QuickSight, allowing users to visually check the flow of data.

[0640] Incident Response Module

[0641] The server uses CloudWatch, a database monitoring tool, to monitor and detect missing data or anomalies. If an anomaly is detected, the user is notified via Amazon SNS. In addition, a conversational artificial intelligence (AWS SageMaker) responds to user questions based on the analyzed data flow information.

[0642] Specific operation examples

[0643] At a logistics center, daily inventory data, delivery data, and order data are collected from each system onto a server and stored in an integrated database. If an abnormality occurs in the inventory data for a specific product one day, the system automatically detects the abnormality and notifies the user. The user uses a smartphone application to ask the conversational AI, "The inventory data for 2023-10-05 is incomplete. Which orders will be affected?" The conversational AI then provides a list of affected orders.

[0644] Prompt Sentence Examples

[0645] "I'm seeing gaps in my inventory data for a specific date. What impact does the missing data have on my business and which orders are affected?"

[0646] This system enables integrated management of large-scale business data at logistics centers, real-time visualization of data flow, and rapid detection and response to data anomalies.

[0647] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0648] Step 1:

[0649] The server collects inventory data, shipping data, and order data from multiple systems within the company using APIs and ETL tools. This is done using AWS Lambda and API Gateway. The collected data is saved as temporary files and then inserted into a consolidated database in Amazon RDS. The input is raw data from each system, and the output is updates to the consolidated database.

[0650] Step 2:

[0651] Users upload the program code and SQL scripts they use to process data to the server. The server then sends these codes and scripts to AWS SageMaker for analysis. The input is the program code and SQL scripts provided by the user, and the output is the analysis results (in JSON format) from AWS SageMaker.

[0652] Step 3:

[0653] The server processes the analysis results received from AWS SageMaker and generates a data flow diagram. This process uses AWS Lambda. The input is the analysis results in JSON format, and the output is a data flow diagram.

[0654] Step 4:

[0655] The server stores the generated data flow diagram in Amazon S3 and uses Amazon QuickSight to visually display it on a dashboard. Users can check the data flow in real time through this dashboard. The input is the data flow diagram, and the output is the visual display on the Amazon QuickSight dashboard.

[0656] Step 5:

[0657] The server uses Amazon CloudWatch to monitor the integrated database and detect missing data or anomalies. If an anomaly is detected, it notifies the user using Amazon SNS. The input is the current state of the database, and the output is a notification when an anomaly is detected.

[0658] Step 6:

[0659] A user uses a smartphone application to ask the conversational AI about an anomaly, for example, "The inventory data for 2023-10-05 is incomplete. Which orders does this affect?" The input is the user's question, and the output is the answer from the conversational AI (AWS SageMaker).

[0660] Step 7:

[0661] The interactive AI identifies the scope of impact based on the analyzed data flow information and provides the user with an answer. This answer is displayed to the user through a smartphone application. The input is the data flow information and the user's question, and the output is the identified scope of impact and the answer.

[0662] These steps will improve the efficiency of data management in logistics centers, enabling real-time visualization of data flow and rapid detection and response to abnormalities.

[0663] 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.

[0664] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company.

[0665] System Overview

[0666] This system has the following configuration:

[0667] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[0668] Program understanding module: The server sends the program code and SQL that processes data to the interactive artificial intelligence engine for analysis.

[0669] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[0670] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[0671] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[0672] Emotion engine module: Recognizes the user's emotions and adjusts the conversational AI's responses accordingly.

[0673] Program processing

[0674] Data collection

[0675] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as a temporary file and then inserted into an integrated database.

[0676] Program Comprehension

[0677] Users upload data processing program codes and SQL scripts to the server, which then sends them to the interactive AI engine for analysis.

[0678] Data Flow Analysis

[0679] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[0680] visualization

[0681] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[0682] Incident response

[0683] The server uses the integrated database monitoring tool to detect missing data or anomalies. If detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine answers questions from the user based on the analyzed data flow information.

[0684] Utilizing the Emotion Engine

[0685] The emotion engine module analyzes the user's input and recognizes their emotions. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI engine. The conversational AI engine then adjusts its response based on the user's emotional state, for example, by replying in a more friendly tone or providing additional support information.

[0686] Specific examples

[0687] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0688] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" and receives information about the extent of the impact from the AI ​​engine. At this point, the emotion engine recognizes that the user is feeling stressed and feeds that information back to the conversational AI. As a result, the AI ​​speaks in a more friendly tone and provides additional support information, improving user satisfaction.

[0689] In this way, the system of the present invention improves the efficiency of data management for companies and provides a better user experience by responding to the user's emotional state.

[0690] The processing flow will be explained below.

[0691] Step 1:

[0692] The server collects sales data, customer data, and inventory data from multiple systems within the company using APIs and ETL tools, and stores the collected data as temporary files.

[0693] Step 2:

[0694] The server reads the data from the temporary file, inserts it into the consolidated database, and deletes the temporary file after the insert is complete.

[0695] Step 3:

[0696] Users upload program codes and SQL scripts to be used for data processing to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[0697] Step 4:

[0698] The conversational AI engine analyzes program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[0699] Step 5:

[0700] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram consists of nodes (starting points, intermediate points, and ending points of data) and edges (data flow).

[0701] Step 6:

[0702] The server provides the generated data flow diagram to the user's device, where the user can visually check the data flow diagram through the device's dashboard.

[0703] Step 7:

[0704] The server uses the integrated database monitoring tool to detect missing data or abnormalities. For example, if data for a specific date is missing, the server detects this information.

[0705] Step 8:

[0706] The server notifies the user of any detected defects or abnormalities, and the user receives an alert notification via their terminal and can check detailed information.

[0707] Step 9:

[0708] After checking the detailed information on the dashboard, users can ask the conversational AI a question, such as, "There is missing data for 2023-03-01. What impact does this have?"

[0709] Step 10:

[0710] The conversational AI engine provides appropriate answers to questions from the analyzed data flow information, and the answers are displayed to the user.

[0711] Step 11:

[0712] When a user asks a question, the device uses an emotion engine to analyze the user's emotions. For example, it can determine whether the user is feeling stressed based on the tempo at which they type and the choice of words.

[0713] Step 12:

[0714] The emotion engine feeds the analysis results back to the conversational artificial intelligence engine, which then adapts its response based on the user's emotional state. For example, if a user is feeling stressed, it will respond in a more friendly tone and provide additional support information.

[0715] Step 13:

[0716] The server uses the emotion engine and the adjusted AI engine to display the final answer to the user, allowing the user to take prompt and appropriate action based on this information.

[0717] Through these steps, the system will streamline data management for companies and provide a better user experience by responding to users' emotional states.

[0718] Example 2

[0719] 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."

[0720] In corporate data management, it is difficult to efficiently integrate and analyze data collected from multiple information systems, quickly detect missing data or anomalies, and notify users. Furthermore, there is a lack of a way to visually understand the flow of data processing, and when responses are required based on the user's emotional state, it is even more difficult to respond quickly and appropriately to discovered problems.

[0721] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting data from multiple information systems within a company and storing it in an integrated database; means for analyzing program code and database queries that perform data processing to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually providing the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive AI means for responding to user questions based on analyzed data flow information; and means for recognizing the user's emotional state and adjusting the interactive AI's response accordingly. This makes data management within the company more efficient, enables quick detection and notification of data loss or anomalies, enables visual understanding of data flows, and enables appropriate responses according to the user's emotional state.

[0722] "Multiple information systems within a company" refers to multiple independent digital systems operated by a company, including systems for sales, customer management, inventory management, etc.

[0723] "Means of collecting data and storing it in an integrated database" refers to the process of extracting data from multiple information systems using APIs and ETL tools, saving that data as temporary files, and then storing it in an integrated database.

[0724] "Data processing program code and database queries" refers to software code, SQL scripts, and other commands used to manipulate and analyze data.

[0725] "Data flow understanding" refers to the process of analyzing program code and database queries to determine how data moves and is transformed.

[0726] "Means for generating data flow diagrams" refers to the process of creating flowcharts or diagrams that visually represent the results of data analysis.

[0727] "Means for visually presenting the generated data flow diagram" refers to a process of displaying the data flow diagram in a visual interface such as a dashboard so that a user can intuitively understand the flow of data.

[0728] "Means for detecting data loss or anomalies and notifying users" refers to a system that uses an integrated database monitoring tool to detect data inconsistencies or loss and notify users of this as a warning.

[0729] "Interactive AI means" refers to an AI system that responds to user questions in text or voice and provides detailed information based on the results of data analysis.

[0730] "Means for recognizing the user's emotional state and adjusting the response accordingly" refers to the function of detecting the user's emotional state from their input and behavior and adapting the conversational AI's response accordingly.

[0731] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company. The system includes the following components, and is capable of collecting, analyzing, visualizing data, responding to incidents, and recognizing emotions.

[0732] System Configuration

[0733] Data collection modules:

[0734] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect data from multiple information systems within the company. Specifically, sales data, customer data, inventory data, etc. are collected from multiple systems. The collected data is first saved as a temporary file in local storage, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[0735] Example: Customer data is extracted from an internal customer relationship management system (CRM) via an API, saved as a temporary file, and then stored in a MySQL database.

[0736] Program Comprehension Module:

[0737] Users upload data processing program code and database queries (e.g., SQL scripts) to the server, which then sends the code and SQL scripts to an interactive AI engine (e.g., GPT-3, BERT) for analysis.

[0738] Example: A user uploads a SQL script for data processing through a designated upload interface on the server.

[0739] Dataflow Analysis Module:

[0740] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format, and the server uses this to generate a data flow diagram. This diagram is generated using tools such as D3.js and Graphviz.

[0741] Example: An interactive artificial intelligence engine interprets data join and transformation rules from SQL scripts and generates a diagram showing the data flow between each table.

[0742] Visualization Module:

[0743] The server provides the generated data flow diagram to the user's device, allowing the user to intuitively view the data flow diagram visually on a dashboard (e.g., Tableau, Power BI).

[0744] Example: The server sends the generated data flow diagram to the user's device via a web API, and the user can view the diagram by operating the dashboard through a browser.

[0745] Incident Response Module:

[0746] The server uses an integrated database monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine responds to questions from the user based on the analyzed data flow information.

[0747] Example: The server detects that sales data for a specific date is missing and notifies the user, who then asks, "The data for 2023-03-01 is missing, what impact does this have?"

[0748] Emotion Engine Module:

[0749] The emotion engine module analyzes user input and recognizes the emotional state (e.g., Affectiva, IBM Watson Tone Analyzer). If the user is feeling stressed, this information is fed back to the conversational AI engine, which adjusts the response, for example, by using a friendlier tone and providing additional support information.

[0750] Example: An emotion engine detects stress from user input, and the conversational AI responds in a friendly tone, "Let us know if we can help you. Additional support information is available here."

[0751] Prompt Sentence Examples

[0752] "There is a missing data for 2023-03-01, what is the impact?"

[0753] Through the above-mentioned modules and operation flow, this system can streamline data management within a company and provide appropriate feedback to users.

[0754] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0755] Step 1: Data collection

[0756] Input: Data from multiple information systems within the company

[0757] Output: Data stored in the integrated database

[0758] Operation:

[0759] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect sales data, customer data, and inventory data within the company from each information system.

[0760] The collected data is stored as a temporary file in the server's local storage.

[0761] The server extracts the data from these temporary files and inserts it into a consolidated database (e.g. MySQL, PostgreSQL).

[0762] Step 2: Uploading program code from the user

[0763] Input: Program code or SQL scripts uploaded by the user

[0764] Output: Data sent to the conversational AI engine

[0765] Operation:

[0766] The user uploads the program code or SQL script for data processing through the server's designated upload interface.

[0767] The server sends the uploaded program code or SQL script to an interactive artificial intelligence engine (e.g., GPT-3, BERT) for analysis.

[0768] Step 3: Analyzing the program code

[0769] Input: Program code or SQL script sent from the server to the interactive AI engine

[0770] Output: Parsed data flow information (JSON format)

[0771] Operation:

[0772] The interactive artificial intelligence engine analyzes program code and SQL scripts to understand data flow and processing flow.

[0773] The data flow information generated as a result of the analysis is returned to the server in JSON format.

[0774] The server receives and stores this JSON data.

[0775] Step 4: Generate a Data Flow Diagram

[0776] Input: Parsed data flow information (JSON format)

[0777] Output: Data flow diagram (visual format)

[0778] Operation:

[0779] The server generates a data flow diagram based on the data flow information in JSON format.

[0780] This generation uses tools such as D3.js and Graphviz.

[0781] The generated data flow diagram is saved in the server.

[0782] Step 5: Visualizing the Data Flow Diagram

[0783] Input: Generated data flow diagram

[0784] Output: A visual data flow diagram delivered to the user's device.

[0785] Operation:

[0786] The server sends the generated data flow diagram to the user's device via a web API.

[0787] Users can visually check the data flow diagram using a dashboard on their device (e.g., Tableau, Power BI).

[0788] Step 6: Data monitoring and incident response

[0789] Input: Data stream from the integrated database

[0790] Output: Alerts and conversational AI questions and responses

[0791] Operation:

[0792] The server periodically checks the data stream in the integrated database using a monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies.

[0793] If data loss or anomalies are detected, the server generates an alert to notify the user.

[0794] Users can view detailed information on the dashboard and ask questions to the conversational AI (e.g., "Data for 2023-03-01 is missing. What impact does this have?").

[0795] The interactive AI engine generates answers to questions from users based on the analyzed data flow information.

[0796] Step 7: Leverage your emotional engine

[0797] Input: User-entered data

[0798] Output: Tailored conversational AI response

[0799] Operation:

[0800] The emotion engine module analyzes the user's input and recognizes the emotional state (e.g., stress level).

[0801] The emotion engine feeds back this emotional situation information to the interactive artificial intelligence engine via the server.

[0802] The conversational AI engine adapts its responses depending on the emotional state, for example, replying in a friendly tone and providing additional supporting information.

[0803] (Application example 2)

[0804] 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."

[0805] Conventional corporate data management systems struggled to efficiently collect and integrate data from multiple information processing systems, requiring timely responses to missing or abnormal data. They also lacked a means to visually grasp data flow or a mechanism for providing rapid feedback based on data analysis results. Furthermore, they were unable to engage in dialogue that reflected the user's emotional state, and lacked functionality to reduce operator stress. There is a need to resolve these issues and improve data management efficiency and user experience.

[0806] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0807] In this invention, the server includes means for collecting data from multiple information processing systems within a company and storing it on an integrated recording medium, means for analyzing program code and database manipulation language for data processing to understand the flow of information, means for generating an information flow diagram from the analysis results, means for visually presenting the generated information flow diagram to the user, means for detecting missing or abnormal data and notifying the user, interactive artificial intelligence means for responding to user questions based on the analyzed information flow information, and emotion engine means for recognizing the user's emotional state and adjusting the response content. This makes data management within the company more efficient and enables flexible feedback that corresponds to the user's emotional state.

[0808] "Multiple information processing systems within an enterprise" refers collectively to multiple computer systems and software used within an enterprise for the purposes of generating, processing, storing, and managing data.

[0809] An "integrated recording medium" is a physical or virtual database or storage system for centrally storing and managing data collected from multiple information processing systems.

[0810] "Program code or database manipulation language" means a computer program or script, such as Structured Query Language (SQL), written to process, retrieve, or manipulate data.

[0811] "Information flow" is a concept that describes the process by which data flows from one system or process to another.

[0812] An "information flow diagram" is a diagram that visually represents the flow of data movement and transformation, and is also called a data flow diagram.

[0813] "Visually providing" means displaying the data graphically so that the user can intuitively understand the contents and flow of the data.

[0814] "Missing or anomalous data" refers to data that does not match the expected format or content, or is missing.

[0815] "Interactive artificial intelligence means" means an artificial intelligence technology that has the ability to answer questions and provide appropriate feedback through dialogue with a user.

[0816] An "emotion engine means" is a technology or module for analyzing a user's emotional state and adjusting the system's response or behavior based on that.

[0817] The present invention provides a system for improving the efficiency of data management within a company and providing a better user experience by responding to the emotional state of the user. This system is configured and operates as follows.

[0818] 1. Data Collection Module

[0819] The server collects data from multiple information processing systems within the company. APIs and ETL (Extract, Transform, Load) tools are used to collect a wide variety of information, including sales data, customer data, and inventory data. This information is saved in files as temporary storage media, and then inserted into a database, which serves as an integrated storage medium.

[0820] 2. Program Comprehension Module

[0821] Users upload program code and database manipulation language (SQL scripts) to the server. The server sends this code to an interactive AI engine for analysis. The analysis results are returned to the server in structured data format (JSON format).

[0822] 3. Dataflow Analysis Module

[0823] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow, and the server generates an information flow diagram based on the analysis results.

[0824] 4. Visualization Module

[0825] The server provides the generated information flow diagram to the user's terminal. The user can visually check the information flow diagram on the dashboard. The user interface uses a graphical user interface (GUI), allowing intuitive operation.

[0826] 5. Incident Response Module

[0827] The server uses the integrated recording media's monitoring tool to detect data loss or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine, which then provides answers based on the analyzed information flow information.

[0828] 6. Emotion Engine Module

[0829] The emotion engine analyzes the user's input and recognizes their emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The conversational AI then adjusts its response based on the user's emotional state, providing a more friendly tone or additional support information.

[0830] For example, a factory is using this system to manage production line data. It can monitor the data flow of machines and lines in the factory in real time, and take immediate action if an abnormality occurs. Furthermore, if an operator is feeling stressed, the emotion engine recognizes this and the conversational AI provides advice and encouraging messages.

[0831] An example prompt is:

[0832] "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the scope of its impact."

[0833] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0834] Step 1:

[0835] The server collects data from multiple information processing systems within a company. Specifically, it uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. The collected data is stored on temporary recording media. The input is raw data obtained from each information processing system, and format conversion and data cleansing are performed to insert this data into the integrated recording media. The output is clean data in a unified format.

[0836] Step 2:

[0837] Users upload program code and SQL scripts for data processing to the server. The server sends these codes to the interactive AI engine. The input is the program code and SQL scripts provided by the user, and the interactive AI engine analyzes them to understand the code's processing flow and dependencies. The output is the analysis results returned in a structured data format (JSON).

[0838] Step 3:

[0839] The server generates an information flow diagram based on the analysis results received from the conversational AI engine. The input is the analysis results (JSON format) from the conversational AI engine, and the output is a visually easy-to-understand information flow diagram. This diagram is displayed on the dashboard.

[0840] Step 4:

[0841] The server provides the generated information flow diagram to the user's device. The user can visually check the information flow diagram on a dashboard. The input is the data from the information flow diagram, and the output is a graphical interface displayed on the user's device. Specifically, the user can check the details of the data flow using mouse or touch operations.

[0842] Step 5:

[0843] The server uses the integrated recording media monitoring tool to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The input is real-time monitored data, and the output is an alert and notification when an anomaly is detected. When the user receives this notification, they can check detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[0844] Step 6:

[0845] The user inputs a question to the conversational AI. For example, they input a prompt such as, "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the extent of its impact." The server receives this input and generates an answer based on the analyzed information flow information. The input is the user's question, and the output is the answer from the conversational AI.

[0846] Step 7:

[0847] The emotion engine analyzes the user's input and recognizes the user's emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The input is the user's emotional state, and the output is the adjusted response content of the conversational AI. The conversational AI provides a response according to the user's emotional state, for example, replying in a more friendly tone or providing additional support information.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] [Third embodiment]

[0852] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0853] 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.

[0854] 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).

[0855] 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.

[0856] 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.

[0857] 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).

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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."

[0864] The present invention relates to a system that uses interactive artificial intelligence to analyze and manage data flows in order to improve the efficiency of data management within a company.

[0865] System Overview

[0866] This system has the following configuration:

[0867] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[0868] Program understanding module: The server sends the program code and SQL that processes the data to the AI ​​engine for analysis.

[0869] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[0870] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[0871] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[0872] Program processing

[0873] Data collection

[0874] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as temporary files and then inserted into the integrated database.

[0875] Program Comprehension

[0876] Users upload the program code and SQL scripts they use to process data to the server, which then sends them to the interactive AI engine for analysis.

[0877] Data Flow Analysis

[0878] The AI ​​engine analyzes program code and SQL scripts to understand the data flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[0879] visualization

[0880] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[0881] Incident response

[0882] The server uses database monitoring tools to detect missing data or abnormalities. If detected, the user is notified. The user can check detailed information on the dashboard and ask questions to the interactive AI. The AI ​​engine responds to the user's questions by providing appropriate answers based on the analyzed data flow information.

[0883] Specific examples

[0884] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0885] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. Where does this affect?" and receives information about the extent of the impact from the AI ​​engine. In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] The server collects sales data, customer data, inventory data, etc. from multiple systems within the company using APIs and ETL tools. The collected data is temporarily stored in files.

[0889] Step 2:

[0890] The server reads the data from the temporary file and inserts it into the consolidated database. After the insert process is complete, the temporary file is deleted.

[0891] Step 3:

[0892] Users upload data processing program codes and SQL scripts to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[0893] Step 4:

[0894] The AI ​​engine analyzes the received program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[0895] Step 5:

[0896] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram is created in a format that includes node and edge information.

[0897] Step 6:

[0898] The server displays the generated data flow diagram on a dashboard, and users can access the dashboard through their terminals to visually check the data flow diagram.

[0899] Step 7:

[0900] The server uses the integrated database monitoring tool to detect data loss or anomalies, and if detected, generates an alert and notifies the user.

[0901] Step 8:

[0902] Users can check alert notifications on a dashboard via their device and ask questions to the conversational AI.

[0903] Step 9:

[0904] The conversational AI engine responds to user questions based on analyzed data flow information, allowing users to quickly take steps to resolve problems based on the AI's answers.

[0905] Through these steps, the system will streamline data management for companies, reduce human resources and costs, and enable faster response.

[0906] Example 1

[0907] 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."

[0908] Modern companies need to collect and manage a wide variety of data from multiple systems. There is a need to improve the efficiency and accuracy of this data management, as well as to quickly detect and address missing or anomalies in the data. However, with conventional systems, it is difficult to accurately understand the data flow and provide a visual representation of it, and it is also difficult to quickly respond to missing or anomalies in the data. The objective of this invention is to efficiently solve these problems and improve the efficiency of data management operations by introducing interactive artificial intelligence.

[0909] 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.

[0910] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that processes data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive artificial intelligence means for responding to a user's questions based on analyzed data flow information; means for requesting analysis of a data processing program using the interactive artificial intelligence means; means for generating a data flow diagram based on the analysis results from the AI ​​engine; means for detecting database loss or anomalies using a monitoring tool; and means for notifying the user of detected anomalies. This enables the series of tasks of collecting, analyzing, visualizing, and monitoring data to be performed efficiently and accurately.

[0911] 1. "Means for collecting data from multiple systems within a company and storing it in an integrated database" refers to a method for collecting data from various information systems within a company and storing it in a centrally managed database.

[0912] 2. "Methods for understanding data flow by analyzing program code and SQL that processes data" refers to methods for analyzing program code and SQL scripts provided by users, thereby understanding the flow and relationships of data.

[0913] 3. "Means for generating a data flow diagram from analysis results" refers to a method for creating a diagram that visually represents the flow of data based on the analyzed information.

[0914] 4. "Means for visually presenting the generated data flow diagram to the user" refers to a method for presenting the generated data flow diagram in a format that allows the user to visually confirm it.

[0915] 5. "Means for detecting missing or abnormal data and notifying users" refers to a method for detecting missing or abnormal data in a database and notifying users of that information.

[0916] 6. "Interactive AI means that answers user questions based on analyzed data flow information" refers to an AI system that uses analyzed data flow information to provide appropriate answers to user questions.

[0917] 7. "Means for requesting the analysis of a data processing program using interactive artificial intelligence means" means a method for requesting the analysis of a data processing program using interactive artificial intelligence.

[0918] 8. "Means for generating a data flow diagram based on the analysis results from an AI engine" means a method for creating a data flow diagram based on the analysis results provided by an AI engine.

[0919] 9. "Means for detecting database defects and abnormalities using monitoring tools" refers to a method for detecting defects and abnormalities in a database using dedicated monitoring tools.

[0920] 10. "Means for notifying users of detected abnormalities" refers to a method for notifying users of information about detected abnormalities, thereby enabling early detection and response to problems.

[0921] The present invention provides a system that uses interactive artificial intelligence to improve the efficiency of data management within a company and quickly detect and respond to data loss and anomalies. The following describes in detail the embodiments of the present invention.

[0922] Data Collection and Management

[0923] 1. The server collects data from multiple information systems within the company, either through APIs or using ETL tools (e.g., Apache NiFi or Talend).

[0924] 2. The collected data is first saved as a temporary file, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[0925] Program Comprehension and Analysis

[0926] 3. The user uploads the program code (e.g., Python script) or SQL script for data processing to the server.

[0927] 4. The server sends the uploaded program code and SQL script to an interactive artificial intelligence engine (e.g., OpenAI's GPT-4) and requests analysis.

[0928] Dataflow Analysis and Visualization

[0929] 5. The server receives the analysis results returned from the AI ​​engine in JSON format and generates a data flow diagram based on them. A visualization tool such as Graphviz can be used to generate this diagram.

[0930] 6. The generated data flow diagram is provided from the server to the user's device and visually displayed on a dashboard, allowing the user to intuitively understand the data flow.

[0931] Data Monitoring and Incident Response

[0932] 7. The server uses a monitoring tool (e.g., Prometheus or Nagios) to monitor the database and detect missing data or abnormalities.

[0933] 8. If an abnormality is detected, the server notifies the user of the information, often via email or SMS.

[0934] 9. Users can view detailed information on the dashboard and ask questions to the conversational AI, such as, "What is the impact of the data loss on 2023-03-01?"

[0935] 10. The AI ​​engine provides appropriate answers to user questions based on the analyzed data flow information.

[0936] Specific examples

[0937] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[0938] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" The AI ​​engine responds, "The impact applies to all reports related to the date column in the sales table." In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[0939] Prompt Sentence Examples

[0940] Analyze the following SQL query and explain the data flow: SELECT FROM sales WHERE date = '2023-03-01';

[0941] "What is the extent of the impact if sales data is missing?"

[0942] This invention makes it possible to efficiently and accurately perform a series of tasks, including data collection, analysis, visualization, and monitoring, thereby significantly improving corporate data management operations.

[0943] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0944] Step 1:

[0945] Data Collection Request

[0946] The server initiates API requests and ETL processes to collect data from multiple systems within the enterprise.

[0947] Input: The server uses the endpoint URL and authentication information for a specific system.

[0948] Output: Data collected from each system (sales data, customer data, inventory data, etc.)

[0949] Specific operation: The server uses the REST API to send a GET request to the sales data system to obtain the latest sales data.

[0950] Step 2:

[0951] Temporary data storage

[0952] The server stores the retrieved data in a temporary file to ensure that the data is not lost if subsequent processing fails.

[0953] Input: Data collected in step 1

[0954] Output: Data saved to a temporary file

[0955] Specific operation: The server saves the acquired sales data in a temporary file in JSON format.

[0956] Step 3:

[0957] Inserting into the database

[0958] The server reads the data stored in the temporary file and inserts it into the consolidated database.

[0959] Input: Data saved in a temporary file

[0960] Output: Data inserted into the integrated database

[0961] Specific operation: The server writes sales data to the MySQL database using an INSERT statement.

[0962] Step 4:

[0963] Uploading the program code

[0964] Users upload program code and SQL scripts for data processing to the server.

[0965] Input: User-supplied program code or SQL script

[0966] Output: Code or script uploaded to the server

[0967] What it does: A user uploads their Python script to the server using a file upload form in their browser.

[0968] Step 5:

[0969] Request for program code analysis

[0970] The server sends the uploaded program code and SQL scripts to an interactive artificial intelligence engine and requests analysis.

[0971] Input: Uploaded program code or SQL script

[0972] Output: Analysis request sent to the AI ​​engine

[0973] Specific operation: The server sends the Python script to the AI ​​engine as an HTTP request.

[0974] Step 6:

[0975] Analysis by AI engine

[0976] The AI ​​engine analyzes the received program code and SQL scripts and understands the data flow.

[0977] Input: Submitted program code or SQL script

[0978] Output: Analysis results (detailed data flow information)

[0979] What it does: The AI ​​engine analyzes the Python script and identifies which tables and columns are used.

[0980] Step 7:

[0981] Receiving analysis results

[0982] The server receives the analysis results from the AI ​​engine and stores them in JSON format.

[0983] Input: Analysis results from the AI ​​engine

[0984] Output: Parsed results saved in JSON format

[0985] Specific operation: The server saves the JSON data received from the AI ​​engine in a temporary file.

[0986] Step 8:

[0987] Generate a data flow diagram

[0988] The server generates a data flow diagram based on the analysis results.

[0989] Input: Parsed result in JSON format

[0990] Output: Generated data flow diagram

[0991] Specific operation: The server generates a data flow diagram using Graphviz and saves it in PNG format.

[0992] Step 9:

[0993] Providing data flow diagrams

[0994] The server provides the generated data flow diagram to the user's terminal.

[0995] Input: Generated Data Flow Diagram

[0996] Output: A data flow diagram displayed on the user's dashboard

[0997] Specific operation: The server displays a link to the data flow diagram on the dashboard, and when the user clicks it, the image is displayed.

[0998] Step 10:

[0999] User visual confirmation

[1000] The user visually checks the data flow diagram on the dashboard.

[1001] Input: Data flow diagram on dashboard

[1002] Output: Data flow diagram understanding and analysis results

[1003] Specific operation: The user accesses the dashboard using a browser and checks the displayed data flow diagram.

[1004] Step 11:

[1005] Data monitoring and anomaly detection

[1006] The server uses a database monitoring tool to detect missing data or abnormalities.

[1007] Input: Monitoring data from monitoring tools

[1008] Output: Information about detected anomalies

[1009] What it does: The server uses Prometheus to monitor specific database tables and generates alerts if anything is abnormal.

[1010] Step 12:

[1011] Sending abnormality notifications

[1012] The server notifies the user of the detected abnormality.

[1013] Input: Information about the detected anomaly

[1014] Output: Notification sent to the user

[1015] Specific operation: The server notifies the user of the missing data via email or SMS.

[1016] Step 13:

[1017] Find out more information and ask questions

[1018] Users can view detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[1019] Input: Details on the dashboard

[1020] Output: Questions sent to the conversational AI

[1021] Specific behavior: A user uses the chat window on the dashboard to ask, "What is the impact of the data loss on 2023-03-01?"

[1022] Step 14:

[1023] Answers from the AI ​​engine

[1024] The AI ​​engine provides answers to user questions based on analyzed data flow information.

[1025] Input: User question

[1026] Output: Parsed data flow information as an answer

[1027] Specific operation: Based on the analysis results, the AI ​​engine responds, "This affects the relevant records in the sales table."

[1028] (Application example 1)

[1029] 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."

[1030] Logistics centers require a method to efficiently integrate large amounts of operational data, such as inventory data, delivery data, and order data, collected from multiple systems, and visualize the data flow in real time. They also need a method to quickly detect missing or abnormal data and identify the extent of the impact so that users can take appropriate action. While systems utilizing interactive artificial intelligence are expected to solve these problems, existing systems often cannot adequately address these issues.

[1031] 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.

[1032] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that process data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting missing or abnormal data and notifying the user; interactive AI means for answering user questions based on the analyzed data flow information; means for acquiring business data via an interface and improving the efficiency of data management at the logistics center; means for analyzing the flow of inventory data, delivery data, and order data at the logistics center and visualizing it in real time; and means for identifying the scope of impact using interactive AI when a problem occurs. This enables integrated management of large-scale business data at a logistics center, real-time visualization of data flow, and rapid detection and response to data abnormalities.

[1033] A "data collection module" is a means of collecting data from multiple systems within a company and storing it in an integrated database.

[1034] The "program comprehension module" is a means of analyzing program code and SQL that processes data and understanding the flow of data.

[1035] The "data flow analysis module" is a means for generating a data flow diagram from the analysis results.

[1036] The "visualization module" is a means for visually presenting the generated data flow diagram to the user.

[1037] The "incident response module" is a means of detecting data loss or abnormalities and notifying users.

[1038] "Interactive AI" is a method of answering user questions based on analyzed data flow information.

[1039] An "interface" is a means of acquiring business data and streamlining data management at logistics centers.

[1040] "Real-time visualization" is a method of analyzing the flow of inventory data, delivery data, and order data at a logistics center and visualizing it in real time.

[1041] The "means for identifying the extent of impact" is a means for identifying the extent of impact using interactive artificial intelligence when a problem occurs.

[1042] This invention is a system for improving the efficiency of data management in logistics centers, and is composed of a server, a smartphone application, and interactive artificial intelligence.

[1043] System Configuration

[1044] Data Collection Module

[1045] The server collects inventory data, shipping data, order data, and other data from multiple systems within the company. This collection is performed using APIs and ETL tools, and the data is saved as temporary files before being inserted into an integrated database. The specific hardware and software used are AWS Lambda, Amazon RDS, and API Gateway.

[1046] Program Comprehension Module

[1047] The program code and SQL scripts uploaded by the user are sent to the server and analyzed by the interactive AI engine. This analysis is performed using AWS SageMaker, and the analysis results are returned to the server in JSON format.

[1048] Dataflow Analysis Module

[1049] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. This generation is also performed by AWS Lambda.

[1050] Visualization Module

[1051] The generated data flow diagram is stored in Amazon S3 and displayed on a dashboard using Amazon QuickSight, allowing users to visually check the flow of data.

[1052] Incident Response Module

[1053] The server uses CloudWatch, a database monitoring tool, to monitor and detect missing data or anomalies. If an anomaly is detected, the user is notified via Amazon SNS. In addition, a conversational artificial intelligence (AWS SageMaker) responds to user questions based on the analyzed data flow information.

[1054] Specific operation examples

[1055] At a logistics center, daily inventory data, delivery data, and order data are collected from each system onto a server and stored in an integrated database. If an abnormality occurs in the inventory data for a specific product one day, the system automatically detects the abnormality and notifies the user. The user uses a smartphone application to ask the conversational AI, "The inventory data for 2023-10-05 is incomplete. Which orders will be affected?" The conversational AI then provides a list of affected orders.

[1056] Prompt Sentence Examples

[1057] "I'm seeing gaps in my inventory data for a specific date. What impact does the missing data have on my business and which orders are affected?"

[1058] This system enables integrated management of large-scale business data at logistics centers, real-time visualization of data flow, and rapid detection and response to data anomalies.

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

[1060] Step 1:

[1061] The server collects inventory data, shipping data, and order data from multiple systems within the company using APIs and ETL tools. This is done using AWS Lambda and API Gateway. The collected data is saved as temporary files and then inserted into a consolidated database in Amazon RDS. The input is raw data from each system, and the output is updates to the consolidated database.

[1062] Step 2:

[1063] Users upload the program code and SQL scripts they use to process data to the server. The server then sends these codes and scripts to AWS SageMaker for analysis. The input is the program code and SQL scripts provided by the user, and the output is the analysis results (in JSON format) from AWS SageMaker.

[1064] Step 3:

[1065] The server processes the analysis results received from AWS SageMaker and generates a data flow diagram. This process uses AWS Lambda. The input is the analysis results in JSON format, and the output is a data flow diagram.

[1066] Step 4:

[1067] The server stores the generated data flow diagram in Amazon S3 and uses Amazon QuickSight to visually display it on a dashboard. Users can check the data flow in real time through this dashboard. The input is the data flow diagram, and the output is the visual display on the Amazon QuickSight dashboard.

[1068] Step 5:

[1069] The server uses Amazon CloudWatch to monitor the integrated database and detect missing data or anomalies. If an anomaly is detected, it notifies the user using Amazon SNS. The input is the current state of the database, and the output is a notification when an anomaly is detected.

[1070] Step 6:

[1071] A user uses a smartphone application to ask the conversational AI about an anomaly, for example, "The inventory data for 2023-10-05 is incomplete. Which orders does this affect?" The input is the user's question, and the output is the answer from the conversational AI (AWS SageMaker).

[1072] Step 7:

[1073] The interactive AI identifies the scope of impact based on the analyzed data flow information and provides the user with an answer. This answer is displayed to the user through a smartphone application. The input is the data flow information and the user's question, and the output is the identified scope of impact and the answer.

[1074] These steps will improve the efficiency of data management in logistics centers, enabling real-time visualization of data flow and rapid detection and response to abnormalities.

[1075] 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.

[1076] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company.

[1077] System Overview

[1078] This system has the following configuration:

[1079] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[1080] Program understanding module: The server sends the program code and SQL that processes data to the interactive artificial intelligence engine for analysis.

[1081] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[1082] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[1083] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[1084] Emotion engine module: Recognizes the user's emotions and adjusts the conversational AI's responses accordingly.

[1085] Program processing

[1086] Data collection

[1087] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as a temporary file and then inserted into an integrated database.

[1088] Program Comprehension

[1089] Users upload data processing program codes and SQL scripts to the server, which then sends them to the interactive AI engine for analysis.

[1090] Data Flow Analysis

[1091] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[1092] visualization

[1093] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[1094] Incident response

[1095] The server uses the integrated database monitoring tool to detect missing data or anomalies. If detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine answers questions from the user based on the analyzed data flow information.

[1096] Utilizing the Emotion Engine

[1097] The emotion engine module analyzes the user's input and recognizes their emotions. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI engine. The conversational AI engine then adjusts its response based on the user's emotional state, for example, by replying in a more friendly tone or providing additional support information.

[1098] Specific examples

[1099] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[1100] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" and receives information about the extent of the impact from the AI ​​engine. At this point, the emotion engine recognizes that the user is feeling stressed and feeds that information back to the conversational AI. As a result, the AI ​​speaks in a more friendly tone and provides additional support information, improving user satisfaction.

[1101] In this way, the system of the present invention improves the efficiency of data management for companies and provides a better user experience by responding to the user's emotional state.

[1102] The processing flow will be explained below.

[1103] Step 1:

[1104] The server collects sales data, customer data, and inventory data from multiple systems within the company using APIs and ETL tools, and stores the collected data as temporary files.

[1105] Step 2:

[1106] The server reads the data from the temporary file, inserts it into the consolidated database, and deletes the temporary file after the insert is complete.

[1107] Step 3:

[1108] Users upload program codes and SQL scripts to be used for data processing to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[1109] Step 4:

[1110] The conversational AI engine analyzes program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[1111] Step 5:

[1112] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram consists of nodes (starting points, intermediate points, and ending points of data) and edges (data flow).

[1113] Step 6:

[1114] The server provides the generated data flow diagram to the user's device, where the user can visually check the data flow diagram through the device's dashboard.

[1115] Step 7:

[1116] The server uses the integrated database monitoring tool to detect missing data or abnormalities. For example, if data for a specific date is missing, the server detects this information.

[1117] Step 8:

[1118] The server notifies the user of any detected defects or abnormalities, and the user receives an alert notification via their terminal and can check detailed information.

[1119] Step 9:

[1120] After checking the detailed information on the dashboard, users can ask the conversational AI a question, such as, "There is missing data for 2023-03-01. What impact does this have?"

[1121] Step 10:

[1122] The conversational AI engine provides appropriate answers to questions from the analyzed data flow information, and the answers are displayed to the user.

[1123] Step 11:

[1124] When a user asks a question, the device uses an emotion engine to analyze the user's emotions. For example, it can determine whether the user is feeling stressed based on the tempo at which they type and the choice of words.

[1125] Step 12:

[1126] The emotion engine feeds the analysis results back to the conversational artificial intelligence engine, which then adapts its response based on the user's emotional state. For example, if a user is feeling stressed, it will respond in a more friendly tone and provide additional support information.

[1127] Step 13:

[1128] The server uses the emotion engine and the adjusted AI engine to display the final answer to the user, allowing the user to take prompt and appropriate action based on this information.

[1129] Through these steps, the system will streamline data management for companies and provide a better user experience by responding to users' emotional states.

[1130] Example 2

[1131] 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."

[1132] In corporate data management, it is difficult to efficiently integrate and analyze data collected from multiple information systems, quickly detect missing data or anomalies, and notify users. Furthermore, there is a lack of a way to visually understand the flow of data processing, and when responses are required based on the user's emotional state, it is even more difficult to respond quickly and appropriately to discovered problems.

[1133] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting data from multiple information systems within a company and storing it in an integrated database; means for analyzing program code and database queries that perform data processing to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually providing the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive AI means for responding to user questions based on analyzed data flow information; and means for recognizing the user's emotional state and adjusting the interactive AI's response accordingly. This makes data management within the company more efficient, enables quick detection and notification of data loss or anomalies, enables visual understanding of data flows, and enables appropriate responses according to the user's emotional state.

[1134] "Multiple information systems within a company" refers to multiple independent digital systems operated by a company, including systems for sales, customer management, inventory management, etc.

[1135] "Means of collecting data and storing it in an integrated database" refers to the process of extracting data from multiple information systems using APIs and ETL tools, saving that data as temporary files, and then storing it in an integrated database.

[1136] "Data processing program code and database queries" refers to software code, SQL scripts, and other commands used to manipulate and analyze data.

[1137] "Data flow understanding" refers to the process of analyzing program code and database queries to determine how data moves and is transformed.

[1138] "Means for generating data flow diagrams" refers to the process of creating flowcharts or diagrams that visually represent the results of data analysis.

[1139] "Means for visually presenting the generated data flow diagram" refers to a process of displaying the data flow diagram in a visual interface such as a dashboard so that a user can intuitively understand the flow of data.

[1140] "Means for detecting data loss or anomalies and notifying users" refers to a system that uses an integrated database monitoring tool to detect data inconsistencies or loss and notify users of this as a warning.

[1141] "Interactive AI means" refers to an AI system that responds to user questions in text or voice and provides detailed information based on the results of data analysis.

[1142] "Means for recognizing the user's emotional state and adjusting the response accordingly" refers to the function of detecting the user's emotional state from their input and behavior and adapting the conversational AI's response accordingly.

[1143] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company. The system includes the following components, and is capable of collecting, analyzing, visualizing data, responding to incidents, and recognizing emotions.

[1144] System Configuration

[1145] Data collection modules:

[1146] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect data from multiple information systems within the company. Specifically, sales data, customer data, inventory data, etc. are collected from multiple systems. The collected data is first saved as a temporary file in local storage, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[1147] Example: Customer data is extracted from an internal customer relationship management system (CRM) via an API, saved as a temporary file, and then stored in a MySQL database.

[1148] Program Comprehension Module:

[1149] Users upload data processing program code and database queries (e.g., SQL scripts) to the server, which then sends the code and SQL scripts to an interactive AI engine (e.g., GPT-3, BERT) for analysis.

[1150] Example: A user uploads a SQL script for data processing through a designated upload interface on the server.

[1151] Dataflow Analysis Module:

[1152] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format, and the server uses this to generate a data flow diagram. This diagram is generated using tools such as D3.js and Graphviz.

[1153] Example: An interactive artificial intelligence engine interprets data join and transformation rules from SQL scripts and generates a diagram showing the data flow between each table.

[1154] Visualization Module:

[1155] The server provides the generated data flow diagram to the user's device, allowing the user to intuitively view the data flow diagram visually on a dashboard (e.g., Tableau, Power BI).

[1156] Example: The server sends the generated data flow diagram to the user's device via a web API, and the user can view the diagram by operating the dashboard through a browser.

[1157] Incident Response Module:

[1158] The server uses an integrated database monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine responds to questions from the user based on the analyzed data flow information.

[1159] Example: The server detects that sales data for a specific date is missing and notifies the user, who then asks, "The data for 2023-03-01 is missing, what impact does this have?"

[1160] Emotion Engine Module:

[1161] The emotion engine module analyzes user input and recognizes the emotional state (e.g., Affectiva, IBM Watson Tone Analyzer). If the user is feeling stressed, this information is fed back to the conversational AI engine, which adjusts the response, for example, by using a friendlier tone and providing additional support information.

[1162] Example: An emotion engine detects stress from user input, and the conversational AI responds in a friendly tone, "Let us know if we can help you. Additional support information is available here."

[1163] Prompt Sentence Examples

[1164] "There is a missing data for 2023-03-01, what is the impact?"

[1165] Through the above-mentioned modules and operation flow, this system can streamline data management within a company and provide appropriate feedback to users.

[1166] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1167] Step 1: Data collection

[1168] Input: Data from multiple information systems within the company

[1169] Output: Data stored in the integrated database

[1170] Operation:

[1171] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect sales data, customer data, and inventory data within the company from each information system.

[1172] The collected data is stored as a temporary file in the server's local storage.

[1173] The server extracts the data from these temporary files and inserts it into a consolidated database (e.g. MySQL, PostgreSQL).

[1174] Step 2: Uploading program code from the user

[1175] Input: Program code or SQL scripts uploaded by the user

[1176] Output: Data sent to the conversational AI engine

[1177] Operation:

[1178] The user uploads the program code or SQL script for data processing through the server's designated upload interface.

[1179] The server sends the uploaded program code or SQL script to an interactive artificial intelligence engine (e.g., GPT-3, BERT) for analysis.

[1180] Step 3: Analyzing the program code

[1181] Input: Program code or SQL script sent from the server to the interactive AI engine

[1182] Output: Parsed data flow information (JSON format)

[1183] Operation:

[1184] The interactive artificial intelligence engine analyzes program code and SQL scripts to understand data flow and processing flow.

[1185] The data flow information generated as a result of the analysis is returned to the server in JSON format.

[1186] The server receives and stores this JSON data.

[1187] Step 4: Generate a Data Flow Diagram

[1188] Input: Parsed data flow information (JSON format)

[1189] Output: Data flow diagram (visual format)

[1190] Operation:

[1191] The server generates a data flow diagram based on the data flow information in JSON format.

[1192] This generation uses tools such as D3.js and Graphviz.

[1193] The generated data flow diagram is saved in the server.

[1194] Step 5: Visualizing the Data Flow Diagram

[1195] Input: Generated data flow diagram

[1196] Output: A visual data flow diagram delivered to the user's device.

[1197] Operation:

[1198] The server sends the generated data flow diagram to the user's device via a web API.

[1199] Users can visually check the data flow diagram using a dashboard on their device (e.g., Tableau, Power BI).

[1200] Step 6: Data monitoring and incident response

[1201] Input: Data stream from the integrated database

[1202] Output: Alerts and conversational AI questions and responses

[1203] Operation:

[1204] The server periodically checks the data stream in the integrated database using a monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies.

[1205] If data loss or anomalies are detected, the server generates an alert to notify the user.

[1206] Users can view detailed information on the dashboard and ask questions to the conversational AI (e.g., "Data for 2023-03-01 is missing. What impact does this have?").

[1207] The interactive AI engine generates answers to questions from users based on the analyzed data flow information.

[1208] Step 7: Leverage your emotional engine

[1209] Input: User-entered data

[1210] Output: Tailored conversational AI response

[1211] Operation:

[1212] The emotion engine module analyzes the user's input and recognizes the emotional state (e.g., stress level).

[1213] The emotion engine feeds back this emotional situation information to the interactive artificial intelligence engine via the server.

[1214] The conversational AI engine adapts its responses depending on the emotional state, for example, replying in a friendly tone and providing additional supporting information.

[1215] (Application example 2)

[1216] 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."

[1217] Conventional corporate data management systems struggled to efficiently collect and integrate data from multiple information processing systems, requiring timely responses to missing or abnormal data. They also lacked a means to visually grasp data flow or a mechanism for providing rapid feedback based on data analysis results. Furthermore, they were unable to engage in dialogue that reflected the user's emotional state, and lacked functionality to reduce operator stress. There is a need to resolve these issues and improve data management efficiency and user experience.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1219] In this invention, the server includes means for collecting data from multiple information processing systems within a company and storing it on an integrated recording medium, means for analyzing program code and database manipulation language for data processing to understand the flow of information, means for generating an information flow diagram from the analysis results, means for visually presenting the generated information flow diagram to the user, means for detecting missing or abnormal data and notifying the user, interactive artificial intelligence means for responding to user questions based on the analyzed information flow information, and emotion engine means for recognizing the user's emotional state and adjusting the response content. This makes data management within the company more efficient and enables flexible feedback that corresponds to the user's emotional state.

[1220] "Multiple information processing systems within an enterprise" refers collectively to multiple computer systems and software used within an enterprise for the purposes of generating, processing, storing, and managing data.

[1221] An "integrated recording medium" is a physical or virtual database or storage system for centrally storing and managing data collected from multiple information processing systems.

[1222] "Program code or database manipulation language" means a computer program or script, such as Structured Query Language (SQL), written to process, retrieve, or manipulate data.

[1223] "Information flow" is a concept that describes the process by which data flows from one system or process to another.

[1224] An "information flow diagram" is a diagram that visually represents the flow of data movement and transformation, and is also called a data flow diagram.

[1225] "Visually providing" means displaying the data graphically so that the user can intuitively understand the contents and flow of the data.

[1226] "Missing or anomalous data" refers to data that does not match the expected format or content, or is missing.

[1227] "Interactive artificial intelligence means" means an artificial intelligence technology that has the ability to answer questions and provide appropriate feedback through dialogue with a user.

[1228] An "emotion engine means" is a technology or module for analyzing a user's emotional state and adjusting the system's response or behavior based on that.

[1229] The present invention provides a system for improving the efficiency of data management within a company and providing a better user experience by responding to the emotional state of the user. This system is configured and operates as follows.

[1230] 1. Data Collection Module

[1231] The server collects data from multiple information processing systems within the company. APIs and ETL (Extract, Transform, Load) tools are used to collect a wide variety of information, including sales data, customer data, and inventory data. This information is saved in files as temporary storage media, and then inserted into a database, which serves as an integrated storage medium.

[1232] 2. Program Comprehension Module

[1233] Users upload program code and database manipulation language (SQL scripts) to the server. The server sends this code to an interactive AI engine for analysis. The analysis results are returned to the server in structured data format (JSON format).

[1234] 3. Dataflow Analysis Module

[1235] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow, and the server generates an information flow diagram based on the analysis results.

[1236] 4. Visualization Module

[1237] The server provides the generated information flow diagram to the user's terminal. The user can visually check the information flow diagram on the dashboard. The user interface uses a graphical user interface (GUI), allowing intuitive operation.

[1238] 5. Incident Response Module

[1239] The server uses the integrated recording media's monitoring tool to detect data loss or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine, which then provides answers based on the analyzed information flow information.

[1240] 6. Emotion Engine Module

[1241] The emotion engine analyzes the user's input and recognizes their emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The conversational AI then adjusts its response based on the user's emotional state, providing a more friendly tone or additional support information.

[1242] For example, a factory is using this system to manage production line data. It can monitor the data flow of machines and lines in the factory in real time, and take immediate action if an abnormality occurs. Furthermore, if an operator is feeling stressed, the emotion engine recognizes this and the conversational AI provides advice and encouraging messages.

[1243] An example prompt is:

[1244] "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the scope of its impact."

[1245] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1246] Step 1:

[1247] The server collects data from multiple information processing systems within a company. Specifically, it uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. The collected data is stored on temporary recording media. The input is raw data obtained from each information processing system, and format conversion and data cleansing are performed to insert this data into the integrated recording media. The output is clean data in a unified format.

[1248] Step 2:

[1249] Users upload program code and SQL scripts for data processing to the server. The server sends these codes to the interactive AI engine. The input is the program code and SQL scripts provided by the user, and the interactive AI engine analyzes them to understand the code's processing flow and dependencies. The output is the analysis results returned in a structured data format (JSON).

[1250] Step 3:

[1251] The server generates an information flow diagram based on the analysis results received from the conversational AI engine. The input is the analysis results (JSON format) from the conversational AI engine, and the output is a visually easy-to-understand information flow diagram. This diagram is displayed on the dashboard.

[1252] Step 4:

[1253] The server provides the generated information flow diagram to the user's device. The user can visually check the information flow diagram on a dashboard. The input is the data from the information flow diagram, and the output is a graphical interface displayed on the user's device. Specifically, the user can check the details of the data flow using mouse or touch operations.

[1254] Step 5:

[1255] The server uses the integrated recording media monitoring tool to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The input is real-time monitored data, and the output is an alert and notification when an anomaly is detected. When the user receives this notification, they can check detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[1256] Step 6:

[1257] The user inputs a question to the conversational AI. For example, they input a prompt such as, "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the extent of its impact." The server receives this input and generates an answer based on the analyzed information flow information. The input is the user's question, and the output is the answer from the conversational AI.

[1258] Step 7:

[1259] The emotion engine analyzes the user's input and recognizes the user's emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The input is the user's emotional state, and the output is the adjusted response content of the conversational AI. The conversational AI provides a response according to the user's emotional state, for example, replying in a more friendly tone or providing additional support information.

[1260] 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.

[1261] 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.

[1262] 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.

[1263] [Fourth embodiment]

[1264] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1265] 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.

[1266] 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).

[1267] 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.

[1268] 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.

[1269] 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).

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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.

[1274] 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.

[1275] 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.

[1276] 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."

[1277] The present invention relates to a system that uses interactive artificial intelligence to analyze and manage data flows in order to improve the efficiency of data management within a company.

[1278] System Overview

[1279] This system has the following configuration:

[1280] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[1281] Program understanding module: The server sends the program code and SQL that processes the data to the AI ​​engine for analysis.

[1282] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[1283] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[1284] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[1285] Program processing

[1286] Data collection

[1287] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as temporary files and then inserted into the integrated database.

[1288] Program Comprehension

[1289] Users upload the program code and SQL scripts they use to process data to the server, which then sends them to the interactive AI engine for analysis.

[1290] Data Flow Analysis

[1291] The AI ​​engine analyzes program code and SQL scripts to understand the data flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[1292] visualization

[1293] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[1294] Incident response

[1295] The server uses database monitoring tools to detect missing data or abnormalities. If detected, the user is notified. The user can check detailed information on the dashboard and ask questions to the interactive AI. The AI ​​engine responds to the user's questions by providing appropriate answers based on the analyzed data flow information.

[1296] Specific examples

[1297] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[1298] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. Where does this affect?" and receives information about the extent of the impact from the AI ​​engine. In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[1299] The processing flow will be explained below.

[1300] Step 1:

[1301] The server collects sales data, customer data, inventory data, etc. from multiple systems within the company using APIs and ETL tools. The collected data is temporarily stored in files.

[1302] Step 2:

[1303] The server reads the data from the temporary file and inserts it into the consolidated database. After the insert process is complete, the temporary file is deleted.

[1304] Step 3:

[1305] Users upload data processing program codes and SQL scripts to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[1306] Step 4:

[1307] The AI ​​engine analyzes the received program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[1308] Step 5:

[1309] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram is created in a format that includes node and edge information.

[1310] Step 6:

[1311] The server displays the generated data flow diagram on a dashboard, and users can access the dashboard through their terminals to visually check the data flow diagram.

[1312] Step 7:

[1313] The server uses the integrated database monitoring tool to detect data loss or anomalies, and if detected, generates an alert and notifies the user.

[1314] Step 8:

[1315] Users can check alert notifications on a dashboard via their device and ask questions to the conversational AI.

[1316] Step 9:

[1317] The conversational AI engine responds to user questions based on analyzed data flow information, allowing users to quickly take steps to resolve problems based on the AI's answers.

[1318] Through these steps, the system will streamline data management for companies, reduce human resources and costs, and enable faster response.

[1319] Example 1

[1320] 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."

[1321] Modern companies need to collect and manage a wide variety of data from multiple systems. There is a need to improve the efficiency and accuracy of this data management, as well as to quickly detect and address missing or anomalies in the data. However, with conventional systems, it is difficult to accurately understand the data flow and provide a visual representation of it, and it is also difficult to quickly respond to missing or anomalies in the data. The objective of this invention is to efficiently solve these problems and improve the efficiency of data management operations by introducing interactive artificial intelligence.

[1322] 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.

[1323] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that processes data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive artificial intelligence means for responding to a user's questions based on analyzed data flow information; means for requesting analysis of a data processing program using the interactive artificial intelligence means; means for generating a data flow diagram based on the analysis results from the AI ​​engine; means for detecting database loss or anomalies using a monitoring tool; and means for notifying the user of detected anomalies. This enables the series of tasks of collecting, analyzing, visualizing, and monitoring data to be performed efficiently and accurately.

[1324] 1. "Means for collecting data from multiple systems within a company and storing it in an integrated database" refers to a method for collecting data from various information systems within a company and storing it in a centrally managed database.

[1325] 2. "Methods for understanding data flow by analyzing program code and SQL that processes data" refers to methods for analyzing program code and SQL scripts provided by users, thereby understanding the flow and relationships of data.

[1326] 3. "Means for generating a data flow diagram from analysis results" refers to a method for creating a diagram that visually represents the flow of data based on the analyzed information.

[1327] 4. "Means for visually presenting the generated data flow diagram to the user" refers to a method for presenting the generated data flow diagram in a format that allows the user to visually confirm it.

[1328] 5. "Means for detecting missing or abnormal data and notifying users" refers to a method for detecting missing or abnormal data in a database and notifying users of that information.

[1329] 6. "Interactive AI means that answers user questions based on analyzed data flow information" refers to an AI system that uses analyzed data flow information to provide appropriate answers to user questions.

[1330] 7. "Means for requesting the analysis of a data processing program using interactive artificial intelligence means" means a method for requesting the analysis of a data processing program using interactive artificial intelligence.

[1331] 8. "Means for generating a data flow diagram based on the analysis results from an AI engine" means a method for creating a data flow diagram based on the analysis results provided by an AI engine.

[1332] 9. "Means for detecting database defects and abnormalities using monitoring tools" refers to a method for detecting defects and abnormalities in a database using dedicated monitoring tools.

[1333] 10. "Means for notifying users of detected abnormalities" refers to a method for notifying users of information about detected abnormalities, thereby enabling early detection and response to problems.

[1334] The present invention provides a system that uses interactive artificial intelligence to improve the efficiency of data management within a company and quickly detect and respond to data loss and anomalies. The following describes in detail the embodiments of the present invention.

[1335] Data Collection and Management

[1336] 1. The server collects data from multiple information systems within the company, either through APIs or using ETL tools (e.g., Apache NiFi or Talend).

[1337] 2. The collected data is first saved as a temporary file, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[1338] Program Comprehension and Analysis

[1339] 3. The user uploads the program code (e.g., Python script) or SQL script for data processing to the server.

[1340] 4. The server sends the uploaded program code and SQL script to an interactive artificial intelligence engine (e.g., OpenAI's GPT-4) and requests analysis.

[1341] Dataflow Analysis and Visualization

[1342] 5. The server receives the analysis results returned from the AI ​​engine in JSON format and generates a data flow diagram based on them. A visualization tool such as Graphviz can be used to generate this diagram.

[1343] 6. The generated data flow diagram is provided from the server to the user's device and visually displayed on a dashboard, allowing the user to intuitively understand the data flow.

[1344] Data Monitoring and Incident Response

[1345] 7. The server uses a monitoring tool (e.g., Prometheus or Nagios) to monitor the database and detect missing data or abnormalities.

[1346] 8. If an abnormality is detected, the server notifies the user of the information, often via email or SMS.

[1347] 9. Users can view detailed information on the dashboard and ask questions to the conversational AI, such as, "What is the impact of the data loss on 2023-03-01?"

[1348] 10. The AI ​​engine provides appropriate answers to user questions based on the analyzed data flow information.

[1349] Specific examples

[1350] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[1351] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" The AI ​​engine responds, "The impact applies to all reports related to the date column in the sales table." In this way, the system of the present invention streamlines corporate data management, reducing costs and enabling rapid problem resolution.

[1352] Prompt Sentence Examples

[1353] Analyze the following SQL query and explain the data flow: SELECT FROM sales WHERE date = '2023-03-01';

[1354] "What is the extent of the impact if sales data is missing?"

[1355] This invention makes it possible to efficiently and accurately perform a series of tasks, including data collection, analysis, visualization, and monitoring, thereby significantly improving corporate data management operations.

[1356] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1357] Step 1:

[1358] Data Collection Request

[1359] The server initiates API requests and ETL processes to collect data from multiple systems within the enterprise.

[1360] Input: The server uses the endpoint URL and authentication information for a specific system.

[1361] Output: Data collected from each system (sales data, customer data, inventory data, etc.)

[1362] Specific operation: The server uses the REST API to send a GET request to the sales data system to obtain the latest sales data.

[1363] Step 2:

[1364] Temporary data storage

[1365] The server stores the retrieved data in a temporary file to ensure that the data is not lost if subsequent processing fails.

[1366] Input: Data collected in step 1

[1367] Output: Data saved to a temporary file

[1368] Specific operation: The server saves the acquired sales data in a temporary file in JSON format.

[1369] Step 3:

[1370] Inserting into the database

[1371] The server reads the data stored in the temporary file and inserts it into the consolidated database.

[1372] Input: Data saved in a temporary file

[1373] Output: Data inserted into the integrated database

[1374] Specific operation: The server writes sales data to the MySQL database using an INSERT statement.

[1375] Step 4:

[1376] Uploading the program code

[1377] Users upload program code and SQL scripts for data processing to the server.

[1378] Input: User-supplied program code or SQL script

[1379] Output: Code or script uploaded to the server

[1380] What it does: A user uploads their Python script to the server using a file upload form in their browser.

[1381] Step 5:

[1382] Request for program code analysis

[1383] The server sends the uploaded program code and SQL scripts to an interactive artificial intelligence engine and requests analysis.

[1384] Input: Uploaded program code or SQL script

[1385] Output: Analysis request sent to the AI ​​engine

[1386] Specific operation: The server sends the Python script to the AI ​​engine as an HTTP request.

[1387] Step 6:

[1388] Analysis by AI engine

[1389] The AI ​​engine analyzes the received program code and SQL scripts and understands the data flow.

[1390] Input: Submitted program code or SQL script

[1391] Output: Analysis results (detailed data flow information)

[1392] What it does: The AI ​​engine analyzes the Python script and identifies which tables and columns are used.

[1393] Step 7:

[1394] Receiving analysis results

[1395] The server receives the analysis results from the AI ​​engine and stores them in JSON format.

[1396] Input: Analysis results from the AI ​​engine

[1397] Output: Parsed results saved in JSON format

[1398] Specific operation: The server saves the JSON data received from the AI ​​engine in a temporary file.

[1399] Step 8:

[1400] Generate a data flow diagram

[1401] The server generates a data flow diagram based on the analysis results.

[1402] Input: Parsed result in JSON format

[1403] Output: Generated data flow diagram

[1404] Specific operation: The server generates a data flow diagram using Graphviz and saves it in PNG format.

[1405] Step 9:

[1406] Providing data flow diagrams

[1407] The server provides the generated data flow diagram to the user's terminal.

[1408] Input: Generated Data Flow Diagram

[1409] Output: A data flow diagram displayed on the user's dashboard

[1410] Specific operation: The server displays a link to the data flow diagram on the dashboard, and when the user clicks it, the image is displayed.

[1411] Step 10:

[1412] User visual confirmation

[1413] The user visually checks the data flow diagram on the dashboard.

[1414] Input: Data flow diagram on dashboard

[1415] Output: Data flow diagram understanding and analysis results

[1416] Specific operation: The user accesses the dashboard using a browser and checks the displayed data flow diagram.

[1417] Step 11:

[1418] Data monitoring and anomaly detection

[1419] The server uses a database monitoring tool to detect missing data or abnormalities.

[1420] Input: Monitoring data from monitoring tools

[1421] Output: Information about detected anomalies

[1422] What it does: The server uses Prometheus to monitor specific database tables and generates alerts if anything is abnormal.

[1423] Step 12:

[1424] Sending abnormality notifications

[1425] The server notifies the user of the detected abnormality.

[1426] Input: Information about the detected anomaly

[1427] Output: Notification sent to the user

[1428] Specific operation: The server notifies the user of the missing data via email or SMS.

[1429] Step 13:

[1430] Find out more information and ask questions

[1431] Users can view detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[1432] Input: Details on the dashboard

[1433] Output: Questions sent to the conversational AI

[1434] Specific behavior: A user uses the chat window on the dashboard to ask, "What is the impact of the data loss on 2023-03-01?"

[1435] Step 14:

[1436] Answers from the AI ​​engine

[1437] The AI ​​engine provides answers to user questions based on analyzed data flow information.

[1438] Input: User question

[1439] Output: Parsed data flow information as an answer

[1440] Specific operation: Based on the analysis results, the AI ​​engine responds, "This affects the relevant records in the sales table."

[1441] (Application example 1)

[1442] 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."

[1443] Logistics centers require a method to efficiently integrate large amounts of operational data, such as inventory data, delivery data, and order data, collected from multiple systems, and visualize the data flow in real time. They also need a method to quickly detect missing or abnormal data and identify the extent of the impact so that users can take appropriate action. While systems utilizing interactive artificial intelligence are expected to solve these problems, existing systems often cannot adequately address these issues.

[1444] 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.

[1445] In this invention, the server includes: means for collecting data from multiple systems within a company and storing it in an integrated database; means for analyzing program code and SQL that process data to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually presenting the generated data flow diagram to a user; means for detecting missing or abnormal data and notifying the user; interactive AI means for answering user questions based on the analyzed data flow information; means for acquiring business data via an interface and improving the efficiency of data management at the logistics center; means for analyzing the flow of inventory data, delivery data, and order data at the logistics center and visualizing it in real time; and means for identifying the scope of impact using interactive AI when a problem occurs. This enables integrated management of large-scale business data at a logistics center, real-time visualization of data flow, and rapid detection and response to data abnormalities.

[1446] A "data collection module" is a means of collecting data from multiple systems within a company and storing it in an integrated database.

[1447] The "program comprehension module" is a means of analyzing program code and SQL that processes data and understanding the flow of data.

[1448] The "data flow analysis module" is a means for generating a data flow diagram from the analysis results.

[1449] The "visualization module" is a means for visually presenting the generated data flow diagram to the user.

[1450] The "incident response module" is a means of detecting data loss or abnormalities and notifying users.

[1451] "Interactive AI" is a method of answering user questions based on analyzed data flow information.

[1452] An "interface" is a means of acquiring business data and streamlining data management at logistics centers.

[1453] "Real-time visualization" is a method of analyzing the flow of inventory data, delivery data, and order data at a logistics center and visualizing it in real time.

[1454] The "means for identifying the extent of impact" is a means for identifying the extent of impact using interactive artificial intelligence when a problem occurs.

[1455] This invention is a system for improving the efficiency of data management in logistics centers, and is composed of a server, a smartphone application, and interactive artificial intelligence.

[1456] System Configuration

[1457] Data Collection Module

[1458] The server collects inventory data, shipping data, order data, and other data from multiple systems within the company. This collection is performed using APIs and ETL tools, and the data is saved as temporary files before being inserted into an integrated database. The specific hardware and software used are AWS Lambda, Amazon RDS, and API Gateway.

[1459] Program Comprehension Module

[1460] The program code and SQL scripts uploaded by the user are sent to the server and analyzed by the interactive AI engine. This analysis is performed using AWS SageMaker, and the analysis results are returned to the server in JSON format.

[1461] Dataflow Analysis Module

[1462] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. This generation is also performed by AWS Lambda.

[1463] Visualization Module

[1464] The generated data flow diagram is stored in Amazon S3 and displayed on a dashboard using Amazon QuickSight, allowing users to visually check the flow of data.

[1465] Incident Response Module

[1466] The server uses CloudWatch, a database monitoring tool, to monitor and detect missing data or anomalies. If an anomaly is detected, the user is notified via Amazon SNS. In addition, a conversational artificial intelligence (AWS SageMaker) responds to user questions based on the analyzed data flow information.

[1467] Specific operation examples

[1468] At a logistics center, daily inventory data, delivery data, and order data are collected from each system onto a server and stored in an integrated database. If an abnormality occurs in the inventory data for a specific product one day, the system automatically detects the abnormality and notifies the user. The user uses a smartphone application to ask the conversational AI, "The inventory data for 2023-10-05 is incomplete. Which orders will be affected?" The conversational AI then provides a list of affected orders.

[1469] Prompt Sentence Examples

[1470] "I'm seeing gaps in my inventory data for a specific date. What impact does the missing data have on my business and which orders are affected?"

[1471] This system enables integrated management of large-scale business data at logistics centers, real-time visualization of data flow, and rapid detection and response to data anomalies.

[1472] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1473] Step 1:

[1474] The server collects inventory data, shipping data, and order data from multiple systems within the company using APIs and ETL tools. This is done using AWS Lambda and API Gateway. The collected data is saved as temporary files and then inserted into a consolidated database in Amazon RDS. The input is raw data from each system, and the output is updates to the consolidated database.

[1475] Step 2:

[1476] Users upload the program code and SQL scripts they use to process data to the server. The server then sends these codes and scripts to AWS SageMaker for analysis. The input is the program code and SQL scripts provided by the user, and the output is the analysis results (in JSON format) from AWS SageMaker.

[1477] Step 3:

[1478] The server processes the analysis results received from AWS SageMaker and generates a data flow diagram. This process uses AWS Lambda. The input is the analysis results in JSON format, and the output is a data flow diagram.

[1479] Step 4:

[1480] The server stores the generated data flow diagram in Amazon S3 and uses Amazon QuickSight to visually display it on a dashboard. Users can check the data flow in real time through this dashboard. The input is the data flow diagram, and the output is the visual display on the Amazon QuickSight dashboard.

[1481] Step 5:

[1482] The server uses Amazon CloudWatch to monitor the integrated database and detect missing data or anomalies. If an anomaly is detected, it notifies the user using Amazon SNS. The input is the current state of the database, and the output is a notification when an anomaly is detected.

[1483] Step 6:

[1484] A user uses a smartphone application to ask the conversational AI about an anomaly, for example, "The inventory data for 2023-10-05 is incomplete. Which orders does this affect?" The input is the user's question, and the output is the answer from the conversational AI (AWS SageMaker).

[1485] Step 7:

[1486] The interactive AI identifies the scope of impact based on the analyzed data flow information and provides the user with an answer. This answer is displayed to the user through a smartphone application. The input is the data flow information and the user's question, and the output is the identified scope of impact and the answer.

[1487] These steps will improve the efficiency of data management in logistics centers, enabling real-time visualization of data flow and rapid detection and response to abnormalities.

[1488] 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.

[1489] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company.

[1490] System Overview

[1491] This system has the following configuration:

[1492] Data collection module: The server collects data from multiple systems within the company and stores it in a consolidated database.

[1493] Program understanding module: The server sends the program code and SQL that processes data to the interactive artificial intelligence engine for analysis.

[1494] Data flow analysis module: The server generates a data flow diagram based on the analysis results received from the AI ​​engine.

[1495] Visualization module: The server displays the generated data flow diagram on a dashboard, allowing users to visually understand the data flow.

[1496] Incident response module: The server detects data loss or anomalies and notifies the user. In addition, conversational AI responds to user questions based on analyzed data flow information.

[1497] Emotion engine module: Recognizes the user's emotions and adjusts the conversational AI's responses accordingly.

[1498] Program processing

[1499] Data collection

[1500] The server uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. from multiple systems within the company. The collected data is saved as a temporary file and then inserted into an integrated database.

[1501] Program Comprehension

[1502] Users upload data processing program codes and SQL scripts to the server, which then sends them to the interactive AI engine for analysis.

[1503] Data Flow Analysis

[1504] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format. The server then generates a data flow diagram based on the analysis results.

[1505] visualization

[1506] The server provides the generated data flow diagram to the user's terminal, where the user can visually check the data flow diagram on a dashboard.

[1507] Incident response

[1508] The server uses the integrated database monitoring tool to detect missing data or anomalies. If detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine answers questions from the user based on the analyzed data flow information.

[1509] Utilizing the Emotion Engine

[1510] The emotion engine module analyzes the user's input and recognizes their emotions. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI engine. The conversational AI engine then adjusts its response based on the user's emotional state, for example, by replying in a more friendly tone or providing additional support information.

[1511] Specific examples

[1512] For example, suppose a company uses a system to manage sales data. This system collects sales data, customer data, and inventory data from multiple systems within the company and stores them in an integrated database. A user uploads SQL queries to the server to process the data, and the AI ​​engine analyzes them. A data flow diagram is generated from the analysis results and displayed on the user's dashboard.

[1513] One day, the server discovers that sales data for a specific date is missing and notifies the user. The user uses the conversational AI to ask, "The data for 2023-03-01 is missing. What impact does this have?" and receives information about the extent of the impact from the AI ​​engine. At this point, the emotion engine recognizes that the user is feeling stressed and feeds that information back to the conversational AI. As a result, the AI ​​speaks in a more friendly tone and provides additional support information, improving user satisfaction.

[1514] In this way, the system of the present invention improves the efficiency of data management for companies and provides a better user experience by responding to the user's emotional state.

[1515] The processing flow will be explained below.

[1516] Step 1:

[1517] The server collects sales data, customer data, and inventory data from multiple systems within the company using APIs and ETL tools, and stores the collected data as temporary files.

[1518] Step 2:

[1519] The server reads the data from the temporary file, inserts it into the consolidated database, and deletes the temporary file after the insert is complete.

[1520] Step 3:

[1521] Users upload program codes and SQL scripts to be used for data processing to the server, which then sends the uploaded files to the interactive artificial intelligence engine.

[1522] Step 4:

[1523] The conversational AI engine analyzes program code and SQL scripts to understand the data flow and processing flow, and returns the analysis results to the server in JSON format.

[1524] Step 5:

[1525] The server generates a data flow diagram based on the analysis results received from the AI ​​engine. The data flow diagram consists of nodes (starting points, intermediate points, and ending points of data) and edges (data flow).

[1526] Step 6:

[1527] The server provides the generated data flow diagram to the user's device, where the user can visually check the data flow diagram through the device's dashboard.

[1528] Step 7:

[1529] The server uses the integrated database monitoring tool to detect missing data or abnormalities. For example, if data for a specific date is missing, the server detects this information.

[1530] Step 8:

[1531] The server notifies the user of any detected defects or abnormalities, and the user receives an alert notification via their terminal and can check detailed information.

[1532] Step 9:

[1533] After checking the detailed information on the dashboard, users can ask the conversational AI a question, such as, "There is missing data for 2023-03-01. What impact does this have?"

[1534] Step 10:

[1535] The conversational AI engine provides appropriate answers to questions from the analyzed data flow information, and the answers are displayed to the user.

[1536] Step 11:

[1537] When a user asks a question, the device uses an emotion engine to analyze the user's emotions. For example, it can determine whether the user is feeling stressed based on the tempo at which they type and the choice of words.

[1538] Step 12:

[1539] The emotion engine feeds the analysis results back to the conversational artificial intelligence engine, which then adapts its response based on the user's emotional state. For example, if a user is feeling stressed, it will respond in a more friendly tone and provide additional support information.

[1540] Step 13:

[1541] The server uses the emotion engine and the adjusted AI engine to display the final answer to the user, allowing the user to take prompt and appropriate action based on this information.

[1542] Through these steps, the system will streamline data management for companies and provide a better user experience by responding to users' emotional states.

[1543] Example 2

[1544] 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."

[1545] In corporate data management, it is difficult to efficiently integrate and analyze data collected from multiple information systems, quickly detect missing data or anomalies, and notify users. Furthermore, there is a lack of a way to visually understand the flow of data processing, and when responses are required based on the user's emotional state, it is even more difficult to respond quickly and appropriately to discovered problems.

[1546] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes: means for collecting data from multiple information systems within a company and storing it in an integrated database; means for analyzing program code and database queries that perform data processing to understand the data flow; means for generating a data flow diagram from the analysis results; means for visually providing the generated data flow diagram to a user; means for detecting data loss or anomalies and notifying the user; interactive AI means for responding to user questions based on analyzed data flow information; and means for recognizing the user's emotional state and adjusting the interactive AI's response accordingly. This makes data management within the company more efficient, enables quick detection and notification of data loss or anomalies, enables visual understanding of data flows, and enables appropriate responses according to the user's emotional state.

[1547] "Multiple information systems within a company" refers to multiple independent digital systems operated by a company, including systems for sales, customer management, inventory management, etc.

[1548] "Means of collecting data and storing it in an integrated database" refers to the process of extracting data from multiple information systems using APIs and ETL tools, saving that data as temporary files, and then storing it in an integrated database.

[1549] "Data processing program code and database queries" refers to software code, SQL scripts, and other commands used to manipulate and analyze data.

[1550] "Data flow understanding" refers to the process of analyzing program code and database queries to determine how data moves and is transformed.

[1551] "Means for generating data flow diagrams" refers to the process of creating flowcharts or diagrams that visually represent the results of data analysis.

[1552] "Means for visually presenting the generated data flow diagram" refers to a process of displaying the data flow diagram in a visual interface such as a dashboard so that a user can intuitively understand the flow of data.

[1553] "Means for detecting data loss or anomalies and notifying users" refers to a system that uses an integrated database monitoring tool to detect data inconsistencies or loss and notify users of this as a warning.

[1554] "Interactive AI means" refers to an AI system that responds to user questions in text or voice and provides detailed information based on the results of data analysis.

[1555] "Means for recognizing the user's emotional state and adjusting the response accordingly" refers to the function of detecting the user's emotional state from their input and behavior and adapting the conversational AI's response accordingly.

[1556] The present invention relates to a system that uses conversational artificial intelligence and an emotion engine to analyze data flows and provide appropriate feedback to users in order to improve the efficiency of data management within a company. The system includes the following components, and is capable of collecting, analyzing, visualizing data, responding to incidents, and recognizing emotions.

[1557] System Configuration

[1558] Data collection modules:

[1559] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect data from multiple information systems within the company. Specifically, sales data, customer data, inventory data, etc. are collected from multiple systems. The collected data is first saved as a temporary file in local storage, and then inserted into an integrated database (e.g., MySQL, PostgreSQL).

[1560] Example: Customer data is extracted from an internal customer relationship management system (CRM) via an API, saved as a temporary file, and then stored in a MySQL database.

[1561] Program Comprehension Module:

[1562] Users upload data processing program code and database queries (e.g., SQL scripts) to the server, which then sends the code and SQL scripts to an interactive AI engine (e.g., GPT-3, BERT) for analysis.

[1563] Example: A user uploads a SQL script for data processing through a designated upload interface on the server.

[1564] Dataflow Analysis Module:

[1565] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow. The analysis results are returned to the server in JSON format, and the server uses this to generate a data flow diagram. This diagram is generated using tools such as D3.js and Graphviz.

[1566] Example: An interactive artificial intelligence engine interprets data join and transformation rules from SQL scripts and generates a diagram showing the data flow between each table.

[1567] Visualization Module:

[1568] The server provides the generated data flow diagram to the user's device, allowing the user to intuitively view the data flow diagram visually on a dashboard (e.g., Tableau, Power BI).

[1569] Example: The server sends the generated data flow diagram to the user's device via a web API, and the user can view the diagram by operating the dashboard through a browser.

[1570] Incident Response Module:

[1571] The server uses an integrated database monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine. The interactive AI engine responds to questions from the user based on the analyzed data flow information.

[1572] Example: The server detects that sales data for a specific date is missing and notifies the user, who then asks, "The data for 2023-03-01 is missing, what impact does this have?"

[1573] Emotion Engine Module:

[1574] The emotion engine module analyzes user input and recognizes the emotional state (e.g., Affectiva, IBM Watson Tone Analyzer). If the user is feeling stressed, this information is fed back to the conversational AI engine, which adjusts the response, for example, by using a friendlier tone and providing additional support information.

[1575] Example: An emotion engine detects stress from user input, and the conversational AI responds in a friendly tone, "Let us know if we can help you. Additional support information is available here."

[1576] Prompt Sentence Examples

[1577] "There is a missing data for 2023-03-01, what is the impact?"

[1578] Through the above-mentioned modules and operation flow, this system can streamline data management within a company and provide appropriate feedback to users.

[1579] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1580] Step 1: Data collection

[1581] Input: Data from multiple information systems within the company

[1582] Output: Data stored in the integrated database

[1583] Operation:

[1584] The server uses APIs and ETL tools (e.g., Talend, Informatica) to collect sales data, customer data, and inventory data within the company from each information system.

[1585] The collected data is stored as a temporary file in the server's local storage.

[1586] The server extracts the data from these temporary files and inserts it into a consolidated database (e.g. MySQL, PostgreSQL).

[1587] Step 2: Uploading program code from the user

[1588] Input: Program code or SQL scripts uploaded by the user

[1589] Output: Data sent to the conversational AI engine

[1590] Operation:

[1591] The user uploads the program code or SQL script for data processing through the server's designated upload interface.

[1592] The server sends the uploaded program code or SQL script to an interactive artificial intelligence engine (e.g., GPT-3, BERT) for analysis.

[1593] Step 3: Analyzing the program code

[1594] Input: Program code or SQL script sent from the server to the interactive AI engine

[1595] Output: Parsed data flow information (JSON format)

[1596] Operation:

[1597] The interactive artificial intelligence engine analyzes program code and SQL scripts to understand data flow and processing flow.

[1598] The data flow information generated as a result of the analysis is returned to the server in JSON format.

[1599] The server receives and stores this JSON data.

[1600] Step 4: Generate a Data Flow Diagram

[1601] Input: Parsed data flow information (JSON format)

[1602] Output: Data flow diagram (visual format)

[1603] Operation:

[1604] The server generates a data flow diagram based on the data flow information in JSON format.

[1605] This generation uses tools such as D3.js and Graphviz.

[1606] The generated data flow diagram is saved in the server.

[1607] Step 5: Visualizing the Data Flow Diagram

[1608] Input: Generated data flow diagram

[1609] Output: A visual data flow diagram delivered to the user's device.

[1610] Operation:

[1611] The server sends the generated data flow diagram to the user's device via a web API.

[1612] Users can visually check the data flow diagram using a dashboard on their device (e.g., Tableau, Power BI).

[1613] Step 6: Data monitoring and incident response

[1614] Input: Data stream from the integrated database

[1615] Output: Alerts and conversational AI questions and responses

[1616] Operation:

[1617] The server periodically checks the data stream in the integrated database using a monitoring tool (e.g., Nagios, Zabbix) to detect missing data or anomalies.

[1618] If data loss or anomalies are detected, the server generates an alert to notify the user.

[1619] Users can view detailed information on the dashboard and ask questions to the conversational AI (e.g., "Data for 2023-03-01 is missing. What impact does this have?").

[1620] The interactive AI engine generates answers to questions from users based on the analyzed data flow information.

[1621] Step 7: Leverage your emotional engine

[1622] Input: User-entered data

[1623] Output: Tailored conversational AI response

[1624] Operation:

[1625] The emotion engine module analyzes the user's input and recognizes the emotional state (e.g., stress level).

[1626] The emotion engine feeds back this emotional situation information to the interactive artificial intelligence engine via the server.

[1627] The conversational AI engine adapts its responses depending on the emotional state, for example, replying in a friendly tone and providing additional supporting information.

[1628] (Application example 2)

[1629] 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."

[1630] Conventional corporate data management systems struggled to efficiently collect and integrate data from multiple information processing systems, requiring timely responses to missing or abnormal data. They also lacked a means to visually grasp data flow or a mechanism for providing rapid feedback based on data analysis results. Furthermore, they were unable to engage in dialogue that reflected the user's emotional state, and lacked functionality to reduce operator stress. There is a need to resolve these issues and improve data management efficiency and user experience.

[1631] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1632] In this invention, the server includes means for collecting data from multiple information processing systems within a company and storing it on an integrated recording medium, means for analyzing program code and database manipulation language for data processing to understand the flow of information, means for generating an information flow diagram from the analysis results, means for visually presenting the generated information flow diagram to the user, means for detecting missing or abnormal data and notifying the user, interactive artificial intelligence means for responding to user questions based on the analyzed information flow information, and emotion engine means for recognizing the user's emotional state and adjusting the response content. This makes data management within the company more efficient and enables flexible feedback that corresponds to the user's emotional state.

[1633] "Multiple information processing systems within an enterprise" refers collectively to multiple computer systems and software used within an enterprise for the purposes of generating, processing, storing, and managing data.

[1634] An "integrated recording medium" is a physical or virtual database or storage system for centrally storing and managing data collected from multiple information processing systems.

[1635] "Program code or database manipulation language" means a computer program or script, such as Structured Query Language (SQL), written to process, retrieve, or manipulate data.

[1636] "Information flow" is a concept that describes the process by which data flows from one system or process to another.

[1637] An "information flow diagram" is a diagram that visually represents the flow of data movement and transformation, and is also called a data flow diagram.

[1638] "Visually providing" means displaying the data graphically so that the user can intuitively understand the contents and flow of the data.

[1639] "Missing or anomalous data" refers to data that does not match the expected format or content, or is missing.

[1640] "Interactive artificial intelligence means" means an artificial intelligence technology that has the ability to answer questions and provide appropriate feedback through dialogue with a user.

[1641] An "emotion engine means" is a technology or module for analyzing a user's emotional state and adjusting the system's response or behavior based on that.

[1642] The present invention provides a system for improving the efficiency of data management within a company and providing a better user experience by responding to the emotional state of the user. This system is configured and operates as follows.

[1643] 1. Data Collection Module

[1644] The server collects data from multiple information processing systems within the company. APIs and ETL (Extract, Transform, Load) tools are used to collect a wide variety of information, including sales data, customer data, and inventory data. This information is saved in files as temporary storage media, and then inserted into a database, which serves as an integrated storage medium.

[1645] 2. Program Comprehension Module

[1646] Users upload program code and database manipulation language (SQL scripts) to the server. The server sends this code to an interactive AI engine for analysis. The analysis results are returned to the server in structured data format (JSON format).

[1647] 3. Dataflow Analysis Module

[1648] The interactive AI engine analyzes program code and SQL scripts to understand data flow and processing flow, and the server generates an information flow diagram based on the analysis results.

[1649] 4. Visualization Module

[1650] The server provides the generated information flow diagram to the user's terminal. The user can visually check the information flow diagram on the dashboard. The user interface uses a graphical user interface (GUI), allowing intuitive operation.

[1651] 5. Incident Response Module

[1652] The server uses the integrated recording media's monitoring tool to detect data loss or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The user can check detailed information on the dashboard and ask questions to the interactive AI engine, which then provides answers based on the analyzed information flow information.

[1653] 6. Emotion Engine Module

[1654] The emotion engine analyzes the user's input and recognizes their emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The conversational AI then adjusts its response based on the user's emotional state, providing a more friendly tone or additional support information.

[1655] For example, a factory is using this system to manage production line data. It can monitor the data flow of machines and lines in the factory in real time, and take immediate action if an abnormality occurs. Furthermore, if an operator is feeling stressed, the emotion engine recognizes this and the conversational AI provides advice and encouraging messages.

[1656] An example prompt is:

[1657] "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the scope of its impact."

[1658] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1659] Step 1:

[1660] The server collects data from multiple information processing systems within a company. Specifically, it uses APIs and ETL tools to collect sales data, customer data, inventory data, etc. The collected data is stored on temporary recording media. The input is raw data obtained from each information processing system, and format conversion and data cleansing are performed to insert this data into the integrated recording media. The output is clean data in a unified format.

[1661] Step 2:

[1662] Users upload program code and SQL scripts for data processing to the server. The server sends these codes to the interactive AI engine. The input is the program code and SQL scripts provided by the user, and the interactive AI engine analyzes them to understand the code's processing flow and dependencies. The output is the analysis results returned in a structured data format (JSON).

[1663] Step 3:

[1664] The server generates an information flow diagram based on the analysis results received from the conversational AI engine. The input is the analysis results (JSON format) from the conversational AI engine, and the output is a visually easy-to-understand information flow diagram. This diagram is displayed on the dashboard.

[1665] Step 4:

[1666] The server provides the generated information flow diagram to the user's device. The user can visually check the information flow diagram on a dashboard. The input is the data from the information flow diagram, and the output is a graphical interface displayed on the user's device. Specifically, the user can check the details of the data flow using mouse or touch operations.

[1667] Step 5:

[1668] The server uses the integrated recording media monitoring tool to detect missing data or anomalies. If an anomaly is detected, the server generates an alert and notifies the user. The input is real-time monitored data, and the output is an alert and notification when an anomaly is detected. When the user receives this notification, they can check detailed information on the dashboard and ask questions to the interactive artificial intelligence.

[1669] Step 6:

[1670] The user inputs a question to the conversational AI. For example, they input a prompt such as, "There is an abnormality in the data flow of production line 3 on 2023-10-07. Please tell me the cause of the abnormality and the extent of its impact." The server receives this input and generates an answer based on the analyzed information flow information. The input is the user's question, and the output is the answer from the conversational AI.

[1671] Step 7:

[1672] The emotion engine analyzes the user's input and recognizes the user's emotional state. For example, if the user is feeling stressed, the emotion engine feeds that information back to the conversational AI. The input is the user's emotional state, and the output is the adjusted response content of the conversational AI. The conversational AI provides a response according to the user's emotional state, for example, replying in a more friendly tone or providing additional support information.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] 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).

[1680] 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.

[1681] 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."

[1682] 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.

[1683] 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).

[1684] 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.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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.

[1689] 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.

[1690] 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.

[1691] 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.

[1692] 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.

[1693] 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.

[1694] The following is further disclosed regarding the above embodiment.

[1695] (Claim 1)

[1696] A means of collecting data from multiple systems within an enterprise and storing it in an integrated database;

[1697] A means to understand the flow of data by analyzing program code and SQL that processes data,

[1698] means for generating a data flow diagram from the analysis results;

[1699] a means for visually presenting the generated data flow diagram to a user;

[1700] A means for detecting data loss or abnormalities and notifying the user;

[1701] an interactive artificial intelligence means for answering a user's question based on the analyzed data flow information;

[1702] A system including:

[1703] (Claim 2)

[1704] 10. The system of claim 1, wherein data collected from multiple systems within an enterprise is saved in a temporary file and then inserted into an integrated database.

[1705] (Claim 3)

[1706] The system according to claim 1, wherein the program code or SQL script uploaded by the user is sent to the artificial intelligence engine and the analysis results are received in JSON format.

[1707] "Example 1"

[1708] (Claim 1)

[1709] A means of collecting data from multiple systems within an enterprise and storing it in an integrated database;

[1710] A means to understand the flow of data by analyzing program code and SQL that processes data,

[1711] means for generating a data flow diagram from the analysis results;

[1712] a means for visually presenting the generated data flow diagram to a user;

[1713] A means for detecting data loss or abnormalities and notifying the user;

[1714] an interactive artificial intelligence means for answering a user's question based on the analyzed data flow information;

[1715] means for requesting analysis of a data processing program using an interactive artificial intelligence means;

[1716] A means for generating a data flow diagram based on the analysis results from the AI ​​engine;

[1717] A means of detecting database defects and anomalies using monitoring tools;

[1718] means for notifying the detected anomaly;

[1719] A system including:

[1720] (Claim 2)

[1721] 10. The system of claim 1, wherein data collected from multiple systems within an enterprise is saved in a temporary file and then inserted into an integrated database.

[1722] (Claim 3)

[1723] The system according to claim 1, wherein the program code or SQL script uploaded by the user is sent to the artificial intelligence engine and the analysis results are received in JSON format.

[1724] "Application Example 1"

[1725] (Claim 1)

[1726] A means of collecting data from multiple systems within an enterprise and storing it in an integrated database;

[1727] A means to understand the flow of data by analyzing program code and SQL that processes data,

[1728] means for generating a data flow diagram from the analysis results;

[1729] a means for visually presenting the generated data flow diagram to a user;

[1730] A means for detecting data loss or abnormalities and notifying the user;

[1731] an interactive artificial intelligence means for answering a user's question based on the analyzed data flow information;

[1732] A means to acquire business data through an interface and improve the efficiency of data management at the logistics center.

[1733] A means to analyze the flow of inventory data, delivery data, and order data from the logistics center and visualize it in real time,

[1734] When a problem occurs, a means of identifying the extent of the impact using interactive artificial intelligence,

[1735] A system including:

[1736] (Claim 2)

[1737] 10. The system of claim 1, wherein data collected from multiple systems within an enterprise is saved in a temporary file and then inserted into an integrated database.

[1738] (Claim 3)

[1739] The system according to claim 1, wherein the program code or SQL script uploaded by the user is sent to the artificial intelligence engine and the analysis results are received in JSON format.

[1740] "Example 2: Combining Emotion Engines"

[1741] (Claim 1)

[1742] A means for collecting data from multiple information systems within a company and storing it in an integrated database;

[1743] A means of understanding the flow of data by analyzing data processing program code and database queries, and

[1744] means for generating a data flow diagram from the analysis results;

[1745] A means for visually providing the generated data flow diagram to a user;

[1746] A means of detecting data loss or abnormalities and notifying users,

[1747] an interactive artificial intelligence means for answering user questions based on the analyzed data flow information;

[1748] A means for recognizing the emotional state of the user and adjusting the response content of the conversational artificial intelligence accordingly;

[1749] A system including:

[1750] (Claim 2)

[1751] 2. The system of claim 1, wherein data collected from multiple information systems within a company is saved in a temporary file and then inserted into an integrated database.

[1752] (Claim 3)

[1753] 2. The system of claim 1, wherein the system transmits program code and database queries uploaded by a user to the artificial intelligence engine and receives the analysis results in a data exchange format.

[1754] "Application example 2 when combining emotion engines"

[1755] (Claim 1)

[1756] a means for collecting data from a plurality of information processing systems within a company and storing the data in an integrated recording medium;

[1757] A means of analyzing data processing program codes and database operation languages ​​to understand the flow of information,

[1758] a means for generating an information flow diagram from the analysis results;

[1759] a means for visually presenting the generated information flow diagram to a user;

[1760] A means for detecting data loss or abnormalities and notifying the user;

[1761] an interactive artificial intelligence means for answering a user's question based on the analyzed information flow information;

[1762] an emotion engine means for recognizing the user's emotional state and adjusting the response content;

[1763] A system including:

[1764] (Claim 2)

[1765] 2. The system according to claim 1, wherein data collected from a plurality of information processing systems within a company is stored in a temporary recording medium and then inserted into an integrated recording medium.

[1766] (Claim 3)

[1767] 2. The system according to claim 1, wherein the program code or database manipulation language script uploaded by the user is sent to the artificial intelligence engine, and the analysis results are received in a structured data format. [Explanation of symbols]

[1768] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data from multiple systems within an enterprise and storing it in an integrated database; A means to understand the flow of data by analyzing program code and SQL that processes data, means for generating a data flow diagram from the analysis results; a means for visually presenting the generated data flow diagram to a user; A means for detecting data loss or abnormalities and notifying the user; an interactive artificial intelligence means for answering a user's question based on the analyzed data flow information; A system including:

2. 2. The system of claim 1, wherein the data collected from multiple systems within a company is saved in a temporary file and then inserted into the integrated database.

3. The system according to claim 1, wherein the system transmits program code and SQL scripts uploaded by the user to the artificial intelligence engine and receives the analysis results in JSON format.

Images