System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing a data flow using interactive artificial intelligence; means for inputting a data processing program or a query used in an enterprise to the interactive artificial intelligence and specifying a data dependency relation; means for visually displaying the specified data dependency relation; and means for responding to anomaly detection or an inquiry in an interactive manner based on the visually displayed data flow.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] Companies need systems that can efficiently grasp data flows and dependencies by utilizing interactive artificial intelligence. However, as data becomes larger and more complex, traditional methods make manual management difficult, and compliance with privacy protection regulations is also difficult. Furthermore, when an anomaly occurs, the ability to quickly identify the situation and take countermeasures is required. The problem that this invention aims to solve is how to improve the efficiency of such complex data management and appropriately detect and respond to anomalies. [Means for solving the problem]

[0005] The present invention provides a system for analyzing data flows using interactive AI. Specifically, the system includes a means for inputting data processing programs and queries used within a company into the interactive AI, identifying data dependencies, and visually displaying the identified data dependencies. The system also includes a means for detecting anomalies and responding promptly to inquiries interactively based on the visually displayed data flow diagram. Furthermore, Mermaid notation and other graph drawing tools are used to visualize the data flows, and the interactive AI extracts data relationships based on program analysis and outputs the results in JSON format. This enables companies to improve the efficiency of data management and respond quickly to abnormalities.

[0006] "Conversational AI" refers to AI that understands and generates natural language to provide information and answer questions through dialogue with users.

[0007] "Data flow" refers to the flow of how data moves within a system and how it is processed.

[0008] "Dependency" refers to a relationship in which data or processes within a system depend on other data or processes.

[0009] "Visually displaying" refers to representing data and its relationships in a visual format such as a graph or chart.

[0010] "Anomaly detection" refers to the automatic detection of unusual conditions or behavior within a system.

[0011] An "inquiry" refers to the act of a user posing a question to the system and receiving an answer.

[0012] "Program analysis" refers to analyzing source code and queries to identify their structure, functions, and dependencies.

[0013] "Mermaid notation" refers to a text-based notation for creating diagrams such as flowcharts and sequence diagrams.

[0014] A "graph drawing tool" refers to a software tool used to visually represent data and its relationships.

[0015] "JSON format" is an abbreviation for JavaScript Object Notation, which represents data in text format and enables structured data exchange. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The present invention relates to a system for streamlining the flow and management of large-scale corporate data using interactive artificial intelligence. Specific embodiments of this system are described below.

[0038] Overall system overview

[0039] This system consists of multiple components, including a server, a terminal, and an interactive AI. The server receives data processing programs and SQL queries from users and passes them to the interactive AI for analysis. The analysis results are used to visualize data flows and detect anomalies.

[0040] Data Entry and Analysis

[0041] Users upload SQL code or Python programs to process data to the system via a terminal. The terminal sends the user-provided code to the server, which passes the code to an API endpoint of the conversational AI for analysis. The conversational AI then identifies database tables, fields, and their dependencies from the code.

[0042] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is visually displayed using Mermaid notation and other graph drawing tools. The diagram is designed to help users intuitively understand data flows and dependencies.

[0043] Data flow visualization

[0044] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can use a browser to view the generated data flow diagram and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[0045] Anomaly detection and response

[0046] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to users.

[0047] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will answer, "The customer_name comes from the customers table. The two tables are joined on the customer_id field in the sales table."

[0048] As described above, the system of the present invention utilizes the analytical capabilities and interactive functions of interactive AI to efficiently manage complex data flows and quickly detect anomalies and respond to inquiries. This system allows companies to improve the efficiency and transparency of data management.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[0052] Step 2:

[0053] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[0054] Step 3:

[0055] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[0056] Step 4:

[0057] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[0058] Step 5:

[0059] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[0060] Step 6:

[0061] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[0062] Step 7:

[0063] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[0064] Step 8:

[0065] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[0066] Step 9:

[0067] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[0068] Step 10:

[0069] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[0070] Step 11:

[0071] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[0072] Step 12:

[0073] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[0074] Step 13:

[0075] The server monitors data processing in real time and detects anomalies while it is running, monitoring logs and metrics and applying rules to detect anomalies.

[0076] Step 14:

[0077] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[0078] Step 15:

[0079] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[0080] Through these steps, the system achieves efficient data management and rapid response in the event of an abnormality.

[0081] Example 1

[0082] 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."

[0083] Data management in modern companies is becoming increasingly complex, requiring efficient analysis, visualization, anomaly detection, and rapid response to data flows. However, traditional data management systems make it difficult to intuitively understand the overall picture of data flows, and it is also difficult to respond quickly when an anomaly occurs. Furthermore, many systems rely on individual tools and manual processes, preventing integrated data management. This creates challenges that delay improvements in data management efficiency and transparency.

[0084] 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.

[0085] In this invention, the server includes: a means for analyzing data flow using an interactive AI; a means for inputting data processing programs and queries used within the company and identifying data dependencies; a means for transmitting the programs and queries from a terminal to the server; a means for the server to pass the received code to the interactive AI; a means for the interactive AI to analyze the code and return the results to the server; a means for visually displaying the identified data dependencies; a means for detecting anomalies and responding interactively to inquiries based on the visually displayed data flow; a means for notifying the interactive AI in real time when an anomaly occurs and returning the analysis results to the server; and a means for a user to make inquiries to the interactive AI through a web interface. This facilitates visualization and analysis of data flow, enabling rapid response when an anomaly occurs. Furthermore, interactive inquiry responses can improve the transparency and efficiency of data management.

[0086] "Conversational AI" is AI that understands input from a user and generates responses in natural language.

[0087] "Data flow" is a concept that indicates the sequence of events that data goes through, from input to processing, storage, and output.

[0088] A "data processing program" is code that contains a series of commands or algorithms for processing specific data.

[0089] A "query" is a statement expressing a question or request used to retrieve information from a database.

[0090] "Data dependency" refers to the interrelationships and dependencies that exist between multiple pieces of data.

[0091] A "server" is a computer dedicated to processing data and providing services to other computers and devices.

[0092] A "terminal" is a device that a user directly operates to input data or execute a program.

[0093] "Analysis" is the process of examining data in detail for a specific purpose to understand its structure and patterns.

[0094] "Visually displaying" means showing data flow and analysis results on a screen in a graphical format.

[0095] "Anomaly detection" refers to the automatic identification of abnormal conditions or errors that occur during normal data processing.

[0096] A "web interface" is a user interface that a user can access and operate via a web browser.

[0097] This invention relates to a system that uses interactive AI to streamline the flow and management of large amounts of data in a company. The system is primarily composed of a server, a terminal, and interactive AI.

[0098] First, the user sends the SQL code or Python program used for data processing to the system via the terminal. The terminal is responsible for sending the code received from the user as an HTTP request to the server. For example, the user may enter the following SQL query on the terminal: "SELECT customer_name FROM customers WHERE customer_id = 123".

[0099] The server passes the received code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the received SQL code or Python program to identify database tables, fields, and their dependencies. Specifically, it performs analysis based on the information extracted from the code and returns the results to the server in JSON or other data formats.

[0100] The server then receives the analysis results from the interactive AI and formats them to generate a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools. For example, if a "customers" table is related to a "sales" table through the "customer_id" field, this dependency is clearly visible.

[0101] The generated data flow diagram is displayed on a web interface via the server. Users can view it using a browser and intuitively understand the data flow and dependencies. The system also monitors data processing in real time, immediately notifying the interactive AI if an abnormality is detected. The interactive AI analyzes the scope of the abnormality and its cause, and sends the results back to the server.

[0102] Users can ask the conversational AI questions via the chat function of the web interface. For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will respond, "Customer_name comes from the customers table." This makes it quick and easy to understand abnormalities and complex data flows.

[0103] This system will make corporate data management more efficient, increase transparency, and enable rapid response in the event of an abnormality.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] The user enters the data processing program or SQL code from the terminal.

[0107] Specifically, a user uses an SQL editor or programming IDE to write code for data management. For example, the user enters the SQL query "SELECT customer_name FROM customers WHERE customer_id = 123."

[0108] Input: The SQL code or program used to process the data.

[0109] Output: Input code data on the terminal.

[0110] Step 2:

[0111] The terminal sends the user's input to the server.

[0112] Specifically, the device generates an HTTP request, includes SQL code or a program in the request, and sends it to the server, for example, to send data using a RESTful API endpoint.

[0113] Input: SQL code or programs typed into a terminal by a user.

[0114] Output: The code data sent to the server.

[0115] Step 3:

[0116] The server passes the received code to an interactive artificial intelligence.

[0117] Specifically, the server sends an analysis request to the API endpoint of the conversational artificial intelligence and passes on the data containing the received SQL code or program.

[0118] Input: Code data sent from the terminal.

[0119] Output: The analysis request sent to the conversational artificial intelligence.

[0120] Step 4:

[0121] Conversational artificial intelligence analyzes the code.

[0122] Specifically, the conversational AI analyzes the received code to identify database tables, fields, and their dependencies, and generates the analysis results in a data format (e.g., JSON).

[0123] Input: Code data sent from the server.

[0124] Output: Analysis of database tables, fields, and dependencies.

[0125] Step 5:

[0126] The server generates a data flow diagram based on the analysis results.

[0127] Specifically, the server formats the analysis results obtained from the interactive AI and creates a graphical data flow diagram, using Mermaid notation for visualization.

[0128] Input: Analysis results obtained from interactive artificial intelligence.

[0129] Output: Graphical data flow diagram.

[0130] Step 6:

[0131] The server displays the generated data flow diagram to the user through a web interface.

[0132] Specifically, the server embeds the generated data flow diagram in a web page and displays it on the user's browser.

[0133] Input: The generated data flow diagram.

[0134] Output: A data flow diagram displayed in the user's browser.

[0135] Step 7:

[0136] The server monitors data processing in real time and notifies the conversational artificial intelligence if any abnormalities occur.

[0137] Specifically, the server monitors log files and real-time data streams, and if an anomaly is detected, it sends an analysis request to the interactive artificial intelligence.

[0138] Input: Real-time data and log files.

[0139] Output: Anomaly analysis request sent to the conversational artificial intelligence.

[0140] Step 8:

[0141] The interactive artificial intelligence analyzes the anomaly and sends the results back to the server.

[0142] Specifically, the interactive AI analyzes the scope and cause of the anomaly and returns the results to the server. The analysis results may also include recommended solutions.

[0143] Input: Anomaly analysis request sent from the server.

[0144] Output: Analysis of the anomaly's scope and cause, as well as recommended solutions.

[0145] Step 9:

[0146] Users use the chat function of the web interface to ask questions to the interactive artificial intelligence.

[0147] Specifically, a user opens the chat function on the web interface and asks a question such as, "Which table does the customer_name retrieved in this SQL query come from?" The conversational AI instantly generates an answer and provides it to the user.

[0148] Input: A query prompt from the user.

[0149] Output: Response from the conversational artificial intelligence.

[0150] (Application example 1)

[0151] 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."

[0152] Logistics facilities are required to manage large amounts of data in real time and detect and respond to abnormalities efficiently and quickly. However, to achieve this, advanced data analysis capabilities, intuitive visualization of data flow, and rapid notification and response in the event of an abnormality are required. Conventional systems have had difficulty meeting these requirements, and have faced the issue of the considerable time and effort required for data analysis and abnormality response.

[0153] 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.

[0154] In this invention, the server includes: means for analyzing data flow using an interactive artificial intelligence; means for inputting data processing programs and queries used within the company into the interactive artificial intelligence and identifying data dependencies; means for visually displaying the data dependencies together with real-time data from various sensors within the logistics facility; means for interactively responding to anomaly detections and inquiries in real time based on the visually displayed data flow; and means for notifying the user when an anomaly is detected, analyzing the cause, and automatically generating work instructions. This allows for efficient management of data flow within the logistics facility and enables rapid response when an anomaly occurs.

[0155] "Conversational artificial intelligence" is an artificial intelligence system that analyzes data and solves problems through natural language dialogue with users.

[0156] "Data flow" refers to the flow of how data flows and is processed within a system.

[0157] "Data dependency" refers to a relationship in which certain data is processed depending on other data, and includes relationships between tables in a database.

[0158] "Visual display means" refers to a method for displaying the results of data analysis in a visual format such as a graph or chart.

[0159] "Real-time data" is data that is constantly being updated from sensors and other data sources.

[0160] "Anomaly detection" is the automatic identification of unusual patterns and problems based on the analysis of data flows and data dependencies.

[0161] "Notification" refers to informing the user of an abnormality when it is detected.

[0162] "Work instructions" refer to specific action plans and instructions for dealing with detected abnormalities.

[0163] This system is designed to analyze large amounts of data from logistics facilities in real time, detect anomalies, and automatically generate related work instructions. A specific embodiment of the system is shown below.

[0164] Overall system overview

[0165] The system is composed of multiple components, including a server, terminals, and interactive AI. The server receives real-time data from sensors within the logistics facility and passes it to the interactive AI for analysis. The analysis results are used to visualize data flow and detect anomalies, and notify users as necessary.

[0166] Data Entry and Analysis

[0167] The terminals transmit real-time data from the sensors to a server, which then passes the data to an API endpoint for a conversational AI system to perform analysis. The conversational AI then uses the data to identify data flows and dependencies within the facility.

[0168] Data flow visualization

[0169] After the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram. This diagram is visually displayed using a graph drawing tool. The device (e.g., a smartphone or smart glasses) provides this visualized data flow diagram to the user, allowing them to view it in real time.

[0170] Anomaly detection and response

[0171] The server monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server. The user can receive the generated notification through their device and check specific work instructions to address the problem. This includes detailed analysis results and recommended countermeasures when an abnormality is detected.

[0172] Hardware and Software Used

[0173] Server: A high-performance data processing server, such as AWS EC2 or Google Cloud Compute Engine.

[0174] Device: User devices such as smartphones (iOS, Android), smart glasses, and head-mounted displays (HMD).

[0175] Conversational artificial intelligence: For example, "OpenAI GPT-3" and "Dialogflow."

[0176] Graph drawing tools: Visualization tools such as "Mermaid" and "D3.js".

[0177] Specific examples

[0178] Consider the example of monitoring the movement of large containers in a logistics facility in real time. Sensors send the container's location information to a server, which then uses an interactive AI to analyze the data. The analysis results are visualized as the container's movement path and displayed on a smartphone or smart glasses. If an abnormality is detected, for example, if the container moves to an unexpected location, the user is notified. At the same time, the interactive AI analyzes the cause of the abnormality and automatically generates recommended countermeasures as work instructions.

[0179] Example of input prompt for generative AI model:

[0180] "Generate a program to detect and visualize anomalies based on real-time data obtained from sensors in logistics facilities. The programming language used is Python, and the API endpoints are https: / / example.com / api / ai_endpoint and https: / / example.com / api / visualization. The sensor ID list is ['123', '456', '789']."

[0181] In this way, it is possible to build a system that improves the efficiency of data management within logistics facilities and supports rapid response in the event of an abnormality.

[0182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0183] Step 1:

[0184] The terminal acquires real-time data from various sensors within the logistics facility and sends it to the server. The input includes the sensor ID and the acquired data (location, temperature, weight, etc.). The server receives this data and proceeds to the next analysis step.

[0185] Step 2:

[0186] The server passes the received real-time data to the API endpoint of the conversational AI to perform analysis. The input is the data from step 1, and the output is the analysis results of data flow and dependency. The server sends a request to the conversational AI and receives the analysis results.

[0187] Step 3:

[0188] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The input is the analysis results from step 2, and the output is a visualized data flow diagram. The data flow diagram is generated using a graph drawing tool such as Mermaid or D3.js.

[0189] Step 4:

[0190] The server sends the generated data flow diagram to the terminal, which then visually displays it to the user. The input is the data flow diagram from step 3, and the output is the information displayed on the terminal's display. The user can use this visualized data flow diagram to check the movement of data in real time.

[0191] Step 5:

[0192] The server monitors the data flow in real time and detects anomalies. If an anomaly is detected, it notifies the interactive AI. The input is real-time data, and the output is the anomaly detection result. Differences in data patterns are used to detect anomalies.

[0193] Step 6:

[0194] The interactive AI analyzes the scope of the anomaly's impact and its cause, and returns the results to the server. The input is the anomaly detection result from step 5, and the output is the detailed information about the anomaly and the analysis results of the scope of its impact. The interactive AI performs its analysis using a cause identification algorithm.

[0195] Step 7:

[0196] When an anomaly is detected, the server notifies the user and sends the cause and countermeasures to the terminal. The input is the analysis result from step 6, and the output is the notification to the user. The notification includes the cause of the anomaly and recommended countermeasures.

[0197] Step 8:

[0198] The user receives the notification and takes the necessary measures. Specifically, they check the details of the abnormality and implement the measures. The input is the notification content from Step 7, and the output is the measures taken by the user. By the user taking action based on the notification, the problem can be resolved quickly.

[0199] 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.

[0200] The present invention relates to a corporate data management system that combines conversational artificial intelligence and an emotion engine. Specifically, the system uses conversational artificial intelligence to analyze and visually display data flow, as well as recognize user emotions and change responses to achieve more effective data management and user support. A specific embodiment of this system is described below.

[0201] Overall system overview

[0202] This system is composed of multiple parts, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users and passes them to the conversational AI. It then generates a data flow diagram based on the analysis results and sends it to the terminal. The emotion engine analyzes the user's emotional state and provides feedback to the conversational AI's response.

[0203] Data Entry and Analysis

[0204] Users input SQL code or Python programs to be used for data processing into the system via a terminal. The terminal sends the user-provided code to the server. The server passes the code to the API endpoint of the conversational AI for analysis. The conversational AI identifies database tables, fields, and their dependencies from the code.

[0205] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools, allowing users to intuitively understand the data flow and dependencies.

[0206] Emotion recognition and response regulation

[0207] The system incorporates an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's text and voice input to identify the user's emotional state. For example, emotions such as excitement, anger, fatigue, and confusion can be detected from the text entered by the user.

[0208] After the emotion engine identifies the user's emotional state, it feeds that information back to the conversational AI, which then adjusts its response based on the emotion engine's analysis results and provides information to the user in the most optimal way. This helps users manage their data efficiently and without stress.

[0209] Data flow visualization

[0210] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can view the generated data flow diagram through a browser and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[0211] Anomaly detection and response

[0212] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to the user. Based on feedback from the emotion engine, the system is designed to provide detailed explanations and reassure users about points of particular concern.

[0213] Specific examples

[0214] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined on the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages.

[0215] In this way, the system of the present invention combines the analytical capabilities of interactive artificial intelligence, the emotion recognition capabilities of an emotion engine, and advanced dialogue functions to efficiently support companies' complex data management and provide optimal responses based on the user's emotions.

[0216] The processing flow will be explained below.

[0217] Step 1:

[0218] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[0219] Step 2:

[0220] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[0221] Step 3:

[0222] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[0223] Step 4:

[0224] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[0225] Step 5:

[0226] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[0227] Step 6:

[0228] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[0229] Step 7:

[0230] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[0231] Step 8:

[0232] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[0233] Step 9:

[0234] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[0235] Step 10:

[0236] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[0237] Step 11:

[0238] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[0239] Step 12:

[0240] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[0241] Step 13:

[0242] The emotion engine analyzes the user's text and voice input to identify the user's emotional state, for example, detecting emotions such as excitement, anger, fatigue, and confusion from the text content entered by the user.

[0243] Step 14:

[0244] The server receives the analysis results from the emotion engine and feeds them back to the conversational AI, asking it to adjust its response based on the user's emotional state.

[0245] Step 15:

[0246] The conversational AI adjusts the response content based on the analysis results of the emotion engine to generate optimal answers, including information and support messages tailored to the user's emotional state.

[0247] Step 16:

[0248] The user sees the tailored response in a chat window and decides the next steps for data management based on the conversational AI's answers and supplemental information.

[0249] Step 17:

[0250] The server monitors data processing in real time and detects anomalies by monitoring logs and metrics and applying rules to detect anomalies.

[0251] Step 18:

[0252] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[0253] Step 19:

[0254] The interactive AI analyzes the scope and cause of the anomaly and returns the results to the server, providing detailed information for the user to take necessary measures.

[0255] Step 20:

[0256] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[0257] Specific examples

[0258] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined on the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages. In this way, the system can provide customized responses according to the user's emotional state.

[0259] Example 2

[0260] 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."

[0261] In modern organizations, the increasing complexity of data processing necessitates efficient data management and analysis methods. Furthermore, the lack of a system that can optimally respond to users' emotional states poses challenges in improving data management efficiency and user experience. In particular, if users misunderstand data dependencies or fail to respond appropriately when an abnormality occurs, this can cause delays in work and increased stress.

[0262] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0263] In this invention, the server includes means for analyzing data flow using an interactive AI, means for inputting data processing programs and queries used within an organization and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for analyzing the emotional state of the user and adjusting the response content of the interactive AI, thereby making it possible to streamline complex data management and provide optimal support according to the emotional state of the user.

[0264] "Conversational AI" is AI that has the ability to provide information and answer questions through conversation with the user.

[0265] "Data flow" is a structure that shows how data moves through a system and how it is processed.

[0266] "Data dependencies" refer to the interrelationships between different data sets or database tables, and how specific data affects other data.

[0267] "Visually displaying" means displaying data or information using visual means such as charts or graphs.

[0268] "Anomaly detection" is the process of detecting abnormal situations or errors within a system that deviate from normal operation.

[0269] "Emotional state" refers to analyzing emotions from a user's input or statements and identifying their emotions at that time.

[0270] "Adjusting the response content" means changing the appropriate information or response method based on the user's emotional state and input content.

[0271] "Program or Query" means the code or instructions used to process or analyze data.

[0272] A "structured data format" is a way of organizing and storing data in a consistent format, usually in a format such as JSON or XML.

[0273] The present invention relates to a data management system that combines a conversational AI and an emotion engine. This system is composed of a server, a terminal, a conversational AI, and an emotion engine.

[0274] Data Entry and Analysis

[0275] A user inputs SQL code or Python program related to data processing into the system from their own terminal. For example, a user may input the SQL code "SELECT customer_name FROM customers." The terminal sends this input to the server. The server then sends this code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the SQL code or Python program and identifies database tables, fields, and dependencies.

[0276] Data Visualization

[0277] The server receives the analysis results and generates a data flow diagram based on them. This data flow diagram is displayed visually using Mermaid notation or other graph drawing tools. For example, the interactive AI identifies the "customer_name field in the customers table," and the server draws the diagram based on this.

[0278] Emotion recognition and response regulation

[0279] When a user interacts with the system, the emotion engine analyzes the user's input text and speech to identify the user's emotional state. For example, if a user types, "Why does this query give me an error?", the emotion engine detects the user's "confusion" from the text. The emotion engine feeds the user's emotional state back to the conversational AI, which then adjusts the response based on the results.

[0280] Anomaly detection and response

[0281] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. For example, if a "connection error" or "grammar error" occurs during data processing, it will detect it and notify the conversational AI. The conversational AI will then analyze the cause and provide the user with a specific solution.

[0282] Examples and prompts

[0283] As a concrete example, consider the case where a user asks, "Which table does the customer_name retrieved by this SQL query come from?" The user enters this question on a terminal, which then sends the question to the server. The server passes the question to the conversational AI and requests an analysis. As a result of the analysis, the conversational AI determines that "customer_name comes from the customers table," and when the emotion engine detects the user's confusion, the conversational AI provides a detailed explanation (e.g., "The two tables are joined by the customer_id field in the sales table").

[0284] An example of a specific prompt for a generative AI model is as follows:

[0285] "Analyze the dependencies of the tables and fields used in this SQL query and generate a data flow diagram."

[0286] "Analyze the user's emotional state based on their input and tailor your response accordingly."

[0287] This allows the user to efficiently manage data and receive optimal support according to their emotions.

[0288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0289] Step 1:

[0290] Users input SQL code or Python programs for data processing into the system from the terminal. For example, if a user inputs the SQL code "SELECT customer_name FROM customers", this code is saved as input data in the terminal.

[0291] Step 2:

[0292] The terminal sends the SQL code or Python program entered by the user to the server. The input data is transferred to the server via an HTTP POST request, which specifically involves sending the data to the API endpoint " / data / parse".

[0293] Step 3:

[0294] The server passes the received SQL code or Python program to the conversational AI's API endpoint for analysis. The server sends a POST request to the conversational AI to transmit the input data. The conversational AI analyzes the SQL code or Python program and performs data calculations to identify database tables, fields, and dependencies.

[0295] Step 4:

[0296] The AI ​​sends the analysis results back to the server, including the identified database tables, fields, and dependencies, such as "customer_name comes from the customers table."

[0297] Step 5:

[0298] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The server processes the data using Mermaid notation and graph drawing tools to visually display the obtained data. The generated data flow diagram is saved as a concrete output.

[0299] Step 6:

[0300] As users interact with the system, the emotion engine analyzes their input text and speech to identify their emotional state. For example, if a user types, "Why is this query giving me an error?", the emotion engine performs a data calculation to identify "confused" from the text.

[0301] Step 7:

[0302] The emotion engine feeds the identified emotional information back to the conversational AI, which then adjusts its response based on this input information. For example, it processes the data to generate a support message such as, "This is probably an SQL syntax error. Specifically, is a comma missing?"

[0303] Step 8:

[0304] The server displays the generated data flow diagram to the user through a web interface. The user can view the data flow diagram through a browser and intuitively understand the data flow and dependencies. The displayed data flow diagram is provided to the user as a concrete output.

[0305] Step 9:

[0306] The system monitors data processing in real time, and if an abnormality occurs, it immediately notifies the conversational AI. For example, if a "connection error" or "grammar error" occurs, it detects it and notifies the conversational AI. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server.

[0307] Step 10:

[0308] The server notifies the user of the analysis results, and the user can use the chat function on the web interface to ask the conversational AI for more details about the anomaly. The conversational AI generates a quick response and, if necessary, takes specific action to provide a detailed explanation based on feedback from the emotion engine.

[0309] These steps allow users to efficiently manage their data and receive optimal support according to their emotions.

[0310] (Application example 2)

[0311] 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."

[0312] Conventional data management systems require users to have a high level of specialized knowledge to understand data flows, and they are slow to respond when an abnormality occurs. Furthermore, they are unable to respond in a way that takes into account the user's emotional state, which can lead to stress. Especially for online shopping sites, where appropriate responses to customer inquiries are required, support that takes into account the user's emotional state is important. Therefore, there is a need for a system that can recognize the user's emotions and adjust responses based on them, thereby achieving efficient and friendly data management and user support.

[0313] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing data flow using interactive artificial intelligence, means for inputting data processing programs and queries used in the company and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for using an emotion engine that analyzes the user's emotional state and adjusts the response. This allows the user to intuitively understand the data flow and dependencies and to receive emotionally sensitive support even when an abnormality occurs.

[0314] "Conversational artificial intelligence" refers to artificial intelligence that provides information through dialogue with users and generates appropriate answers to their questions.

[0315] "Analyzing data flow" means investigating the flow and dependencies of data and clarifying their structure and relationships.

[0316] An "emotion engine" is a technology that analyzes a user's emotional state from text and voice and adjusts the system's response based on that information.

[0317] "Data processing programs and queries used within an enterprise" refers to code and instructions used to operate on or query an enterprise's databases and information systems.

[0318] "Identifying data dependencies" means identifying how one piece of data is related to other data in a database.

[0319] "Visual display" means showing the relationships and structure of data in a visible form using graphs, charts, diagrams, etc.

[0320] "Abnormality detection" means detecting abnormal behavior or phenomena in real time, and discovering problems early and taking measures to address them.

[0321] "Responding to inquiries in a conversational manner" means answering questions from users through natural conversation.

[0322] A "graph drawing tool" is software or a library for visually displaying data.

[0323] A "structured data format" is a data format in which data items and attributes are clearly defined and organized.

[0324] The present invention is a method for applying a conversational artificial intelligence and an emotion engine to a data management system for a company. The embodiments of the present invention will be described in detail below.

[0325] Overall system configuration

[0326] The system consists of multiple components, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users, requests analysis from the conversational AI, and visually displays the results. The emotion engine also analyzes the user's emotional state and provides feedback to the conversational AI's response. Users access the system via their terminals to input and retrieve the necessary information.

[0327] Hardware and software used

[0328] TensorFlow: To train and run emotion recognition models.

[0329] Dialogflow: Implements conversational artificial intelligence to analyze and respond to user inquiries.

[0330] Matplotlib: Draws data flow diagrams.

[0331] Flask: For server-side implementation and API integration.

[0332] React Native: Building the front end of smartphone applications.

[0333] AWS EC2: Provides virtual machines for server hosting.

[0334] Data Entry and Analysis

[0335] Users make inquiries via voice or text via a smartphone app. For example, they might input a query such as, "How do I return this product?" The input from the device is sent to the Flask server, which then calls the Dialogflow API to analyze the inquiry. At the same time, the input voice and text data is analyzed for emotional state using TensorFlow.

[0336] Explanation and response

[0337] The analyzed data is used by the conversational AI to generate an appropriate response. For example, if you enter "Please tell me the shipping status of order number 12345," the conversational AI will provide the current shipping status and detailed tracking information. Furthermore, based on the analyzed emotional state, the conversational AI will adjust the response and provide detailed support or additional explanations as needed.

[0338] Data flow visualization

[0339] The server generates a data flow diagram using Mermaid notation and Matplotlib and displays it visually to the user, allowing the user to intuitively understand the data flow and dependencies.

[0340] Specific examples

[0341] Here are some examples of specific prompts:

[0342] "How do I return this product?"

[0343] "Please let me know the shipping status of order number 12345."

[0344] "I can't log into my account, please help"

[0345] This allows users to easily make inquiries and obtain the information they need in an easy-to-understand and fast manner through responses from conversational artificial intelligence and adjustments by the emotion engine.

[0346] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0347] Step 1:

[0348] The user inputs a query via voice or text via a smartphone app. For example, they might ask, "How do I return this product?" The input data is sent to the terminal.

[0349] Step 2:

[0350] The device sends the input data, which can include text and audio data, to the Flask server, which then begins analyzing the data.

[0351] Step 3:

[0352] The server first calls the Dialogflow API to analyze the user's inquiry. Specifically, it analyzes the input text and voice data and obtains information to generate a corresponding response. The input data is sent to the Dialogflow API as an analysis request, and an appropriate response is returned as the analysis result.

[0353] Step 4:

[0354] At the same time, the server uses TensorFlow to analyze the user's emotional state from the input voice and text data. Specifically, it uses an emotion recognition model to identify the user's emotions (e.g., anger, confusion, joy, etc.). Based on this, emotional state data is generated.

[0355] Step 5:

[0356] The server integrates the response obtained from Dialogflow with the emotional state data obtained from TensorFlow. This allows the response to be adjusted according to the user's emotional state. For example, if the user is confused, a more polite and detailed explanation is added. The input data is integrated as an analysis result and output as an adjusted response.

[0357] Step 6:

[0358] The server sends the final response to the terminal, which then displays the received response to the user, either in text format or as audio. The user can then obtain the adjusted response.

[0359] Step 7:

[0360] If necessary, the server generates a data flow diagram using Mermaid notation or Matplotlib and displays it visually to the user. Input data is sent to the server as a data analysis request, and the output is a visual data flow diagram, which the user can use to intuitively understand the data flow and dependencies.

[0361] In this way, each processing step analyzes and responds to user input, and further adjusts according to emotional state, resulting in more effective and friendly data management and user support.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] [Second embodiment]

[0366] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0367] 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.

[0368] 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).

[0369] 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.

[0370] 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.

[0371] 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).

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] In the smart glasses 214, 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.

[0377] 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."

[0378] The present invention relates to a system for streamlining the flow and management of large-scale corporate data using interactive artificial intelligence. Specific embodiments of this system are described below.

[0379] Overall system overview

[0380] This system consists of multiple components, including a server, a terminal, and an interactive AI. The server receives data processing programs and SQL queries from users and passes them to the interactive AI for analysis. The analysis results are used to visualize data flows and detect anomalies.

[0381] Data Entry and Analysis

[0382] Users upload SQL code or Python programs to process data to the system via a terminal. The terminal sends the user-provided code to the server, which passes the code to an API endpoint of the conversational AI for analysis. The conversational AI then identifies database tables, fields, and their dependencies from the code.

[0383] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is visually displayed using Mermaid notation and other graph drawing tools. The diagram is designed to help users intuitively understand data flows and dependencies.

[0384] Data flow visualization

[0385] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can use a browser to view the generated data flow diagram and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[0386] Anomaly detection and response

[0387] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to users.

[0388] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will answer, "The customer_name comes from the customers table. The two tables are joined on the customer_id field in the sales table."

[0389] As described above, the system of the present invention utilizes the analytical capabilities and interactive functions of interactive AI to efficiently manage complex data flows and quickly detect anomalies and respond to inquiries. This system allows companies to improve the efficiency and transparency of data management.

[0390] The processing flow will be explained below.

[0391] Step 1:

[0392] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[0393] Step 2:

[0394] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[0395] Step 3:

[0396] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[0397] Step 4:

[0398] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[0399] Step 5:

[0400] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[0401] Step 6:

[0402] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[0403] Step 7:

[0404] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[0405] Step 8:

[0406] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[0407] Step 9:

[0408] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[0409] Step 10:

[0410] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[0411] Step 11:

[0412] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[0413] Step 12:

[0414] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[0415] Step 13:

[0416] The server monitors data processing in real time and detects anomalies while it is running, monitoring logs and metrics and applying rules to detect anomalies.

[0417] Step 14:

[0418] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[0419] Step 15:

[0420] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[0421] Through these steps, the system achieves efficient data management and rapid response in the event of an abnormality.

[0422] Example 1

[0423] 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."

[0424] Data management in modern companies is becoming increasingly complex, requiring efficient analysis, visualization, anomaly detection, and rapid response to data flows. However, traditional data management systems make it difficult to intuitively understand the overall picture of data flows, and it is also difficult to respond quickly when an anomaly occurs. Furthermore, many systems rely on individual tools and manual processes, preventing integrated data management. This creates challenges that delay improvements in data management efficiency and transparency.

[0425] 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.

[0426] In this invention, the server includes: a means for analyzing data flow using an interactive AI; a means for inputting data processing programs and queries used within the company and identifying data dependencies; a means for transmitting the programs and queries from a terminal to the server; a means for the server to pass the received code to the interactive AI; a means for the interactive AI to analyze the code and return the results to the server; a means for visually displaying the identified data dependencies; a means for detecting anomalies and responding interactively to inquiries based on the visually displayed data flow; a means for notifying the interactive AI in real time when an anomaly occurs and returning the analysis results to the server; and a means for a user to make inquiries to the interactive AI through a web interface. This facilitates visualization and analysis of data flow, enabling rapid response when an anomaly occurs. Furthermore, interactive inquiry responses can improve the transparency and efficiency of data management.

[0427] "Conversational AI" is AI that understands input from a user and generates responses in natural language.

[0428] "Data flow" is a concept that indicates the sequence of events that data goes through, from input to processing, storage, and output.

[0429] A "data processing program" is code that contains a series of commands or algorithms for processing specific data.

[0430] A "query" is a statement expressing a question or request used to retrieve information from a database.

[0431] "Data dependency" refers to the interrelationships and dependencies that exist between multiple pieces of data.

[0432] A "server" is a computer dedicated to processing data and providing services to other computers and devices.

[0433] A "terminal" is a device that a user directly operates to input data or execute a program.

[0434] "Analysis" is the process of examining data in detail for a specific purpose to understand its structure and patterns.

[0435] "Visually displaying" means showing data flow and analysis results on a screen in a graphical format.

[0436] "Anomaly detection" refers to the automatic identification of abnormal conditions or errors that occur during normal data processing.

[0437] A "web interface" is a user interface that a user can access and operate via a web browser.

[0438] This invention relates to a system that uses interactive AI to streamline the flow and management of large amounts of data in a company. The system is primarily composed of a server, a terminal, and interactive AI.

[0439] First, the user sends the SQL code or Python program used for data processing to the system via the terminal. The terminal is responsible for sending the code received from the user as an HTTP request to the server. For example, the user may enter the following SQL query on the terminal: "SELECT customer_name FROM customers WHERE customer_id = 123".

[0440] The server passes the received code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the received SQL code or Python program to identify database tables, fields, and their dependencies. Specifically, it performs analysis based on the information extracted from the code and returns the results to the server in JSON or other data formats.

[0441] The server then receives the analysis results from the interactive AI and formats them to generate a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools. For example, if a "customers" table is related to a "sales" table through the "customer_id" field, this dependency is clearly visible.

[0442] The generated data flow diagram is displayed on a web interface via the server. Users can view it using a browser and intuitively understand the data flow and dependencies. The system also monitors data processing in real time, immediately notifying the interactive AI if an abnormality is detected. The interactive AI analyzes the scope of the abnormality and its cause, and sends the results back to the server.

[0443] Users can ask the conversational AI questions via the chat function of the web interface. For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will respond, "Customer_name comes from the customers table." This makes it quick and easy to understand abnormalities and complex data flows.

[0444] This system will make corporate data management more efficient, increase transparency, and enable rapid response in the event of an abnormality.

[0445] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0446] Step 1:

[0447] The user enters the data processing program or SQL code from the terminal.

[0448] Specifically, a user uses an SQL editor or programming IDE to write code for data management. For example, the user enters the SQL query "SELECT customer_name FROM customers WHERE customer_id = 123."

[0449] Input: The SQL code or program used to process the data.

[0450] Output: Input code data on the terminal.

[0451] Step 2:

[0452] The terminal sends the user's input to the server.

[0453] Specifically, the device generates an HTTP request, includes SQL code or a program in the request, and sends it to the server, for example, to send data using a RESTful API endpoint.

[0454] Input: SQL code or programs typed into a terminal by a user.

[0455] Output: The code data sent to the server.

[0456] Step 3:

[0457] The server passes the received code to an interactive artificial intelligence.

[0458] Specifically, the server sends an analysis request to the API endpoint of the conversational artificial intelligence and passes on the data containing the received SQL code or program.

[0459] Input: Code data sent from the terminal.

[0460] Output: The analysis request sent to the conversational artificial intelligence.

[0461] Step 4:

[0462] Conversational artificial intelligence analyzes the code.

[0463] Specifically, the conversational AI analyzes the received code to identify database tables, fields, and their dependencies, and generates the analysis results in a data format (e.g., JSON).

[0464] Input: Code data sent from the server.

[0465] Output: Analysis of database tables, fields, and dependencies.

[0466] Step 5:

[0467] The server generates a data flow diagram based on the analysis results.

[0468] Specifically, the server formats the analysis results obtained from the interactive AI and creates a graphical data flow diagram, using Mermaid notation for visualization.

[0469] Input: Analysis results obtained from interactive artificial intelligence.

[0470] Output: Graphical data flow diagram.

[0471] Step 6:

[0472] The server displays the generated data flow diagram to the user through a web interface.

[0473] Specifically, the server embeds the generated data flow diagram in a web page and displays it on the user's browser.

[0474] Input: The generated data flow diagram.

[0475] Output: A data flow diagram displayed in the user's browser.

[0476] Step 7:

[0477] The server monitors data processing in real time and notifies the conversational artificial intelligence if any abnormalities occur.

[0478] Specifically, the server monitors log files and real-time data streams, and if an anomaly is detected, it sends an analysis request to the interactive artificial intelligence.

[0479] Input: Real-time data and log files.

[0480] Output: Anomaly analysis request sent to the conversational artificial intelligence.

[0481] Step 8:

[0482] The interactive artificial intelligence analyzes the anomaly and sends the results back to the server.

[0483] Specifically, the interactive AI analyzes the scope and cause of the anomaly and returns the results to the server. The analysis results may also include recommended solutions.

[0484] Input: Anomaly analysis request sent from the server.

[0485] Output: Analysis of the anomaly's scope and cause, as well as recommended solutions.

[0486] Step 9:

[0487] Users use the chat function of the web interface to ask questions to the interactive artificial intelligence.

[0488] Specifically, a user opens the chat function on the web interface and asks a question such as, "Which table does the customer_name retrieved in this SQL query come from?" The conversational AI instantly generates an answer and provides it to the user.

[0489] Input: A query prompt from the user.

[0490] Output: Response from the conversational artificial intelligence.

[0491] (Application example 1)

[0492] 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."

[0493] Logistics facilities are required to manage large amounts of data in real time and detect and respond to abnormalities efficiently and quickly. However, to achieve this, advanced data analysis capabilities, intuitive visualization of data flow, and rapid notification and response in the event of an abnormality are required. Conventional systems have had difficulty meeting these requirements, and have faced the issue of the considerable time and effort required for data analysis and abnormality response.

[0494] 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.

[0495] In this invention, the server includes: means for analyzing data flow using an interactive artificial intelligence; means for inputting data processing programs and queries used within the company into the interactive artificial intelligence and identifying data dependencies; means for visually displaying the data dependencies together with real-time data from various sensors within the logistics facility; means for interactively responding to anomaly detections and inquiries in real time based on the visually displayed data flow; and means for notifying the user when an anomaly is detected, analyzing the cause, and automatically generating work instructions. This allows for efficient management of data flow within the logistics facility and enables rapid response when an anomaly occurs.

[0496] "Conversational artificial intelligence" is an artificial intelligence system that analyzes data and solves problems through natural language dialogue with users.

[0497] "Data flow" refers to the flow of how data flows and is processed within a system.

[0498] "Data dependency" refers to a relationship in which certain data is processed depending on other data, and includes relationships between tables in a database.

[0499] "Visual display means" refers to a method for displaying the results of data analysis in a visual format such as a graph or chart.

[0500] "Real-time data" is data that is constantly being updated from sensors and other data sources.

[0501] "Anomaly detection" is the automatic identification of unusual patterns and problems based on the analysis of data flows and data dependencies.

[0502] "Notification" refers to informing the user of an abnormality when it is detected.

[0503] "Work instructions" refer to specific action plans and instructions for dealing with detected abnormalities.

[0504] This system is designed to analyze large amounts of data from logistics facilities in real time, detect anomalies, and automatically generate related work instructions. A specific embodiment of the system is shown below.

[0505] Overall system overview

[0506] The system is composed of multiple components, including a server, terminals, and interactive AI. The server receives real-time data from sensors within the logistics facility and passes it to the interactive AI for analysis. The analysis results are used to visualize data flow and detect anomalies, and notify users as necessary.

[0507] Data Entry and Analysis

[0508] The terminals transmit real-time data from the sensors to a server, which then passes the data to an API endpoint for a conversational AI system to perform analysis. The conversational AI then uses the data to identify data flows and dependencies within the facility.

[0509] Data flow visualization

[0510] After the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram. This diagram is visually displayed using a graph drawing tool. The device (e.g., a smartphone or smart glasses) provides this visualized data flow diagram to the user, allowing them to view it in real time.

[0511] Anomaly detection and response

[0512] The server monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server. The user can receive the generated notification through their device and check specific work instructions to address the problem. This includes detailed analysis results and recommended countermeasures when an abnormality is detected.

[0513] Hardware and Software Used

[0514] Server: A high-performance data processing server, such as AWS EC2 or Google Cloud Compute Engine.

[0515] Device: User devices such as smartphones (iOS, Android), smart glasses, and head-mounted displays (HMD).

[0516] Conversational artificial intelligence: For example, "OpenAI GPT-3" and "Dialogflow."

[0517] Graph drawing tools: Visualization tools such as "Mermaid" and "D3.js".

[0518] Specific examples

[0519] Consider the example of monitoring the movement of large containers in a logistics facility in real time. Sensors send the container's location information to a server, which then uses an interactive AI to analyze the data. The analysis results are visualized as the container's movement path and displayed on a smartphone or smart glasses. If an abnormality is detected, for example, if the container moves to an unexpected location, the user is notified. At the same time, the interactive AI analyzes the cause of the abnormality and automatically generates recommended countermeasures as work instructions.

[0520] Example of input prompt for generative AI model:

[0521] "Generate a program to detect and visualize anomalies based on real-time data obtained from sensors in logistics facilities. The programming language used is Python, and the API endpoints are https: / / example.com / api / ai_endpoint and https: / / example.com / api / visualization. The sensor ID list is ['123', '456', '789']."

[0522] In this way, it is possible to build a system that improves the efficiency of data management within logistics facilities and supports rapid response in the event of an abnormality.

[0523] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0524] Step 1:

[0525] The terminal acquires real-time data from various sensors within the logistics facility and sends it to the server. The input includes the sensor ID and the acquired data (location, temperature, weight, etc.). The server receives this data and proceeds to the next analysis step.

[0526] Step 2:

[0527] The server passes the received real-time data to the API endpoint of the conversational AI to perform analysis. The input is the data from step 1, and the output is the analysis results of data flow and dependency. The server sends a request to the conversational AI and receives the analysis results.

[0528] Step 3:

[0529] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The input is the analysis results from step 2, and the output is a visualized data flow diagram. The data flow diagram is generated using a graph drawing tool such as Mermaid or D3.js.

[0530] Step 4:

[0531] The server sends the generated data flow diagram to the terminal, which then visually displays it to the user. The input is the data flow diagram from step 3, and the output is the information displayed on the terminal's display. The user can use this visualized data flow diagram to check the movement of data in real time.

[0532] Step 5:

[0533] The server monitors the data flow in real time and detects anomalies. If an anomaly is detected, it notifies the interactive AI. The input is real-time data, and the output is the anomaly detection result. Differences in data patterns are used to detect anomalies.

[0534] Step 6:

[0535] The interactive AI analyzes the scope of the anomaly's impact and its cause, and returns the results to the server. The input is the anomaly detection result from step 5, and the output is the detailed information about the anomaly and the analysis results of the scope of its impact. The interactive AI performs its analysis using a cause identification algorithm.

[0536] Step 7:

[0537] When an anomaly is detected, the server notifies the user and sends the cause and countermeasures to the terminal. The input is the analysis result from step 6, and the output is the notification to the user. The notification includes the cause of the anomaly and recommended countermeasures.

[0538] Step 8:

[0539] The user receives the notification and takes the necessary measures. Specifically, they check the details of the abnormality and implement the measures. The input is the notification content from Step 7, and the output is the measures taken by the user. By the user taking action based on the notification, the problem can be resolved quickly.

[0540] 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.

[0541] The present invention relates to a corporate data management system that combines conversational artificial intelligence and an emotion engine. Specifically, the system uses conversational artificial intelligence to analyze and visually display data flow, as well as recognize user emotions and change responses to achieve more effective data management and user support. A specific embodiment of this system is described below.

[0542] Overall system overview

[0543] This system is composed of multiple parts, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users and passes them to the conversational AI. It then generates a data flow diagram based on the analysis results and sends it to the terminal. The emotion engine analyzes the user's emotional state and provides feedback to the conversational AI's response.

[0544] Data Entry and Analysis

[0545] Users input SQL code or Python programs to be used for data processing into the system via a terminal. The terminal sends the user-provided code to the server. The server passes the code to the API endpoint of the conversational AI for analysis. The conversational AI identifies database tables, fields, and their dependencies from the code.

[0546] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools, allowing users to intuitively understand the data flow and dependencies.

[0547] Emotion recognition and response regulation

[0548] The system incorporates an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's text and voice input to identify the user's emotional state. For example, emotions such as excitement, anger, fatigue, and confusion can be detected from the text entered by the user.

[0549] After the emotion engine identifies the user's emotional state, it feeds that information back to the conversational AI, which then adjusts its response based on the emotion engine's analysis results and provides information to the user in the most optimal way. This helps users manage their data efficiently and without stress.

[0550] Data flow visualization

[0551] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can view the generated data flow diagram through a browser and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[0552] Anomaly detection and response

[0553] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to the user. Based on feedback from the emotion engine, the system is designed to provide detailed explanations and reassure users about points of particular concern.

[0554] Specific examples

[0555] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined on the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages.

[0556] In this way, the system of the present invention combines the analytical capabilities of interactive artificial intelligence, the emotion recognition capabilities of an emotion engine, and advanced dialogue functions to efficiently support companies' complex data management and provide optimal responses based on the user's emotions.

[0557] The processing flow will be explained below.

[0558] Step 1:

[0559] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[0560] Step 2:

[0561] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[0562] Step 3:

[0563] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[0564] Step 4:

[0565] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[0566] Step 5:

[0567] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[0568] Step 6:

[0569] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[0570] Step 7:

[0571] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[0572] Step 8:

[0573] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[0574] Step 9:

[0575] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[0576] Step 10:

[0577] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[0578] Step 11:

[0579] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[0580] Step 12:

[0581] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[0582] Step 13:

[0583] The emotion engine analyzes the user's text and voice input to identify the user's emotional state, for example, detecting emotions such as excitement, anger, fatigue, and confusion from the text content entered by the user.

[0584] Step 14:

[0585] The server receives the analysis results from the emotion engine and feeds them back to the conversational AI, asking it to adjust its response based on the user's emotional state.

[0586] Step 15:

[0587] The conversational AI adjusts the response content based on the analysis results of the emotion engine to generate optimal answers, including information and support messages tailored to the user's emotional state.

[0588] Step 16:

[0589] The user sees the tailored response in a chat window and decides the next steps for data management based on the conversational AI's answers and supplemental information.

[0590] Step 17:

[0591] The server monitors data processing in real time and detects anomalies by monitoring logs and metrics and applying rules to detect anomalies.

[0592] Step 18:

[0593] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[0594] Step 19:

[0595] The interactive AI analyzes the scope and cause of the anomaly and returns the results to the server, providing detailed information for the user to take necessary measures.

[0596] Step 20:

[0597] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[0598] Specific examples

[0599] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined on the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages. In this way, the system can provide customized responses according to the user's emotional state.

[0600] Example 2

[0601] 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."

[0602] In modern organizations, the increasing complexity of data processing necessitates efficient data management and analysis methods. Furthermore, the lack of a system that can optimally respond to users' emotional states poses challenges in improving data management efficiency and user experience. In particular, if users misunderstand data dependencies or fail to respond appropriately when an abnormality occurs, this can cause delays in work and increased stress.

[0603] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0604] In this invention, the server includes means for analyzing data flow using an interactive AI, means for inputting data processing programs and queries used within an organization and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for analyzing the emotional state of the user and adjusting the response content of the interactive AI, thereby making it possible to streamline complex data management and provide optimal support according to the emotional state of the user.

[0605] "Conversational AI" is AI that has the ability to provide information and answer questions through conversation with the user.

[0606] "Data flow" is a structure that shows how data moves through a system and how it is processed.

[0607] "Data dependencies" refer to the interrelationships between different data sets or database tables, and how specific data affects other data.

[0608] "Visually displaying" means displaying data or information using visual means such as charts or graphs.

[0609] "Anomaly detection" is the process of detecting abnormal situations or errors within a system that deviate from normal operation.

[0610] "Emotional state" refers to analyzing emotions from a user's input or statements and identifying their emotions at that time.

[0611] "Adjusting the response content" means changing the appropriate information or response method based on the user's emotional state and input content.

[0612] "Program or Query" means the code or instructions used to process or analyze data.

[0613] A "structured data format" is a way of organizing and storing data in a consistent format, usually in a format such as JSON or XML.

[0614] The present invention relates to a data management system that combines a conversational AI and an emotion engine. This system is composed of a server, a terminal, a conversational AI, and an emotion engine.

[0615] Data Entry and Analysis

[0616] A user inputs SQL code or Python program related to data processing into the system from their own terminal. For example, a user may input the SQL code "SELECT customer_name FROM customers." The terminal sends this input to the server. The server then sends this code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the SQL code or Python program and identifies database tables, fields, and dependencies.

[0617] Data Visualization

[0618] The server receives the analysis results and generates a data flow diagram based on them. This data flow diagram is displayed visually using Mermaid notation or other graph drawing tools. For example, the interactive AI identifies the "customer_name field in the customers table," and the server draws the diagram based on this.

[0619] Emotion recognition and response regulation

[0620] When a user interacts with the system, the emotion engine analyzes the user's input text and speech to identify the user's emotional state. For example, if a user types, "Why does this query give me an error?", the emotion engine detects the user's "confusion" from the text. The emotion engine feeds the user's emotional state back to the conversational AI, which then adjusts the response based on the results.

[0621] Anomaly detection and response

[0622] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. For example, if a "connection error" or "grammar error" occurs during data processing, it will detect it and notify the conversational AI. The conversational AI will then analyze the cause and provide the user with a specific solution.

[0623] Examples and prompts

[0624] As a concrete example, consider the case where a user asks, "Which table does the customer_name retrieved by this SQL query come from?" The user enters this question on a terminal, which then sends the question to the server. The server passes the question to the conversational AI and requests an analysis. As a result of the analysis, the conversational AI determines that "customer_name comes from the customers table," and when the emotion engine detects the user's confusion, the conversational AI provides a detailed explanation (e.g., "The two tables are joined by the customer_id field in the sales table").

[0625] An example of a specific prompt for a generative AI model is as follows:

[0626] "Analyze the dependencies of the tables and fields used in this SQL query and generate a data flow diagram."

[0627] "Analyze the user's emotional state based on their input and tailor your response accordingly."

[0628] This allows the user to efficiently manage data and receive optimal support according to their emotions.

[0629] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0630] Step 1:

[0631] Users input SQL code or Python programs for data processing into the system from the terminal. For example, if a user inputs the SQL code "SELECT customer_name FROM customers", this code is saved as input data in the terminal.

[0632] Step 2:

[0633] The terminal sends the SQL code or Python program entered by the user to the server. The input data is transferred to the server via an HTTP POST request, which specifically involves sending the data to the API endpoint " / data / parse".

[0634] Step 3:

[0635] The server passes the received SQL code or Python program to the conversational AI's API endpoint for analysis. The server sends a POST request to the conversational AI to transmit the input data. The conversational AI analyzes the SQL code or Python program and performs data calculations to identify database tables, fields, and dependencies.

[0636] Step 4:

[0637] The AI ​​sends the analysis results back to the server, including the identified database tables, fields, and dependencies, such as "customer_name comes from the customers table."

[0638] Step 5:

[0639] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The server processes the data using Mermaid notation and graph drawing tools to visually display the obtained data. The generated data flow diagram is saved as a concrete output.

[0640] Step 6:

[0641] As users interact with the system, the emotion engine analyzes their input text and speech to identify their emotional state. For example, if a user types, "Why is this query giving me an error?", the emotion engine performs a data calculation to identify "confused" from the text.

[0642] Step 7:

[0643] The emotion engine feeds the identified emotional information back to the conversational AI, which then adjusts its response based on this input information. For example, it processes the data to generate a support message such as, "This is probably an SQL syntax error. Specifically, is a comma missing?"

[0644] Step 8:

[0645] The server displays the generated data flow diagram to the user through a web interface. The user can view the data flow diagram through a browser and intuitively understand the data flow and dependencies. The displayed data flow diagram is provided to the user as a concrete output.

[0646] Step 9:

[0647] The system monitors data processing in real time, and if an abnormality occurs, it immediately notifies the conversational AI. For example, if a "connection error" or "grammar error" occurs, it detects it and notifies the conversational AI. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server.

[0648] Step 10:

[0649] The server notifies the user of the analysis results, and the user can use the chat function on the web interface to ask the conversational AI for more details about the anomaly. The conversational AI generates a quick response and, if necessary, takes specific action to provide a detailed explanation based on feedback from the emotion engine.

[0650] These steps allow users to efficiently manage their data and receive optimal support according to their emotions.

[0651] (Application example 2)

[0652] 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."

[0653] Conventional data management systems require users to have a high level of specialized knowledge to understand data flows, and they are slow to respond when an abnormality occurs. Furthermore, they are unable to respond in a way that takes into account the user's emotional state, which can lead to stress. Especially for online shopping sites, where appropriate responses to customer inquiries are required, support that takes into account the user's emotional state is important. Therefore, there is a need for a system that can recognize the user's emotions and adjust responses based on them, thereby achieving efficient and friendly data management and user support.

[0654] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing data flow using interactive artificial intelligence, means for inputting data processing programs and queries used in the company and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for using an emotion engine that analyzes the user's emotional state and adjusts the response. This allows the user to intuitively understand the data flow and dependencies and to receive emotionally sensitive support even when an abnormality occurs.

[0655] "Conversational artificial intelligence" refers to artificial intelligence that provides information through dialogue with users and generates appropriate answers to their questions.

[0656] "Analyzing data flow" means investigating the flow and dependencies of data and clarifying their structure and relationships.

[0657] An "emotion engine" is a technology that analyzes a user's emotional state from text and voice and adjusts the system's response based on that information.

[0658] "Data processing programs and queries used within an enterprise" refers to code and instructions used to operate on or query an enterprise's databases and information systems.

[0659] "Identifying data dependencies" means identifying how one piece of data is related to other data in a database.

[0660] "Visual display" means showing the relationships and structure of data in a visible form using graphs, charts, diagrams, etc.

[0661] "Abnormality detection" means detecting abnormal behavior or phenomena in real time, and discovering problems early and taking measures to address them.

[0662] "Responding to inquiries in a conversational manner" means answering questions from users through natural conversation.

[0663] A "graph drawing tool" is software or a library for visually displaying data.

[0664] A "structured data format" is a data format in which data items and attributes are clearly defined and organized.

[0665] The present invention is a method for applying a conversational artificial intelligence and an emotion engine to a data management system for a company. The embodiments of the present invention will be described in detail below.

[0666] Overall system configuration

[0667] The system consists of multiple components, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users, requests analysis from the conversational AI, and visually displays the results. The emotion engine also analyzes the user's emotional state and provides feedback to the conversational AI's response. Users access the system via their terminals to input and retrieve the necessary information.

[0668] Hardware and software used

[0669] TensorFlow: To train and run emotion recognition models.

[0670] Dialogflow: Implements conversational artificial intelligence to analyze and respond to user inquiries.

[0671] Matplotlib: Draws data flow diagrams.

[0672] Flask: For server-side implementation and API integration.

[0673] React Native: Building the front end of smartphone applications.

[0674] AWS EC2: Provides virtual machines for server hosting.

[0675] Data Entry and Analysis

[0676] Users make inquiries via voice or text via a smartphone app. For example, they might input a query such as, "How do I return this product?" The input from the device is sent to the Flask server, which then calls the Dialogflow API to analyze the inquiry. At the same time, the input voice and text data is analyzed for emotional state using TensorFlow.

[0677] Explanation and response

[0678] The analyzed data is used by the conversational AI to generate an appropriate response. For example, if you enter "Please tell me the shipping status of order number 12345," the conversational AI will provide the current shipping status and detailed tracking information. Furthermore, based on the analyzed emotional state, the conversational AI will adjust the response and provide detailed support or additional explanations as needed.

[0679] Data flow visualization

[0680] The server generates a data flow diagram using Mermaid notation and Matplotlib and displays it visually to the user, allowing the user to intuitively understand the data flow and dependencies.

[0681] Specific examples

[0682] Here are some examples of specific prompts:

[0683] "How do I return this product?"

[0684] "Please let me know the shipping status of order number 12345."

[0685] "I can't log into my account, please help"

[0686] This allows users to easily make inquiries and obtain the information they need in an easy-to-understand and fast manner through responses from conversational artificial intelligence and adjustments by the emotion engine.

[0687] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0688] Step 1:

[0689] The user inputs a query via voice or text via a smartphone app. For example, they might ask, "How do I return this product?" The input data is sent to the terminal.

[0690] Step 2:

[0691] The device sends the input data, which can include text and audio data, to the Flask server, which then begins analyzing the data.

[0692] Step 3:

[0693] The server first calls the Dialogflow API to analyze the user's inquiry. Specifically, it analyzes the input text and voice data and obtains information to generate a corresponding response. The input data is sent to the Dialogflow API as an analysis request, and an appropriate response is returned as the analysis result.

[0694] Step 4:

[0695] At the same time, the server uses TensorFlow to analyze the user's emotional state from the input voice and text data. Specifically, it uses an emotion recognition model to identify the user's emotions (e.g., anger, confusion, joy, etc.). Based on this, emotional state data is generated.

[0696] Step 5:

[0697] The server integrates the response obtained from Dialogflow with the emotional state data obtained from TensorFlow. This allows the response to be adjusted according to the user's emotional state. For example, if the user is confused, a more polite and detailed explanation is added. The input data is integrated as an analysis result and output as an adjusted response.

[0698] Step 6:

[0699] The server sends the final response to the terminal, which then displays the received response to the user, either in text format or as audio. The user can then obtain the adjusted response.

[0700] Step 7:

[0701] If necessary, the server generates a data flow diagram using Mermaid notation or Matplotlib and displays it visually to the user. Input data is sent to the server as a data analysis request, and the output is a visual data flow diagram, which the user can use to intuitively understand the data flow and dependencies.

[0702] In this way, each processing step analyzes and responds to user input, and further adjusts according to emotional state, resulting in more effective and friendly data management and user support.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] [Third embodiment]

[0707] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0708] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0709] 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).

[0710] 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.

[0711] 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.

[0712] 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).

[0713] 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.

[0714] 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.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] 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."

[0719] The present invention relates to a system for streamlining the flow and management of large-scale corporate data using interactive artificial intelligence. Specific embodiments of this system are described below.

[0720] Overall system overview

[0721] This system consists of multiple components, including a server, a terminal, and an interactive AI. The server receives data processing programs and SQL queries from users and passes them to the interactive AI for analysis. The analysis results are used to visualize data flows and detect anomalies.

[0722] Data Entry and Analysis

[0723] Users upload SQL code or Python programs to process data to the system via a terminal. The terminal sends the user-provided code to the server, which passes the code to an API endpoint of the conversational AI for analysis. The conversational AI then identifies database tables, fields, and their dependencies from the code.

[0724] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is visually displayed using Mermaid notation and other graph drawing tools. The diagram is designed to help users intuitively understand data flows and dependencies.

[0725] Data flow visualization

[0726] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can use a browser to view the generated data flow diagram and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[0727] Anomaly detection and response

[0728] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to users.

[0729] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will answer, "The customer_name comes from the customers table. The two tables are joined on the customer_id field in the sales table."

[0730] As described above, the system of the present invention utilizes the analytical capabilities and interactive functions of interactive AI to efficiently manage complex data flows and quickly detect anomalies and respond to inquiries. This system allows companies to improve the efficiency and transparency of data management.

[0731] The processing flow will be explained below.

[0732] Step 1:

[0733] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[0734] Step 2:

[0735] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[0736] Step 3:

[0737] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[0738] Step 4:

[0739] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[0740] Step 5:

[0741] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[0742] Step 6:

[0743] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[0744] Step 7:

[0745] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[0746] Step 8:

[0747] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[0748] Step 9:

[0749] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[0750] Step 10:

[0751] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[0752] Step 11:

[0753] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[0754] Step 12:

[0755] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[0756] Step 13:

[0757] The server monitors data processing in real time and detects anomalies while it is running, monitoring logs and metrics and applying rules to detect anomalies.

[0758] Step 14:

[0759] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[0760] Step 15:

[0761] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[0762] Through these steps, the system achieves efficient data management and rapid response in the event of an abnormality.

[0763] Example 1

[0764] 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."

[0765] Data management in modern companies is becoming increasingly complex, requiring efficient analysis, visualization, anomaly detection, and rapid response to data flows. However, traditional data management systems make it difficult to intuitively understand the overall picture of data flows, and it is also difficult to respond quickly when an anomaly occurs. Furthermore, many systems rely on individual tools and manual processes, preventing integrated data management. This creates challenges that delay improvements in data management efficiency and transparency.

[0766] 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.

[0767] In this invention, the server includes: a means for analyzing data flow using an interactive AI; a means for inputting data processing programs and queries used within the company and identifying data dependencies; a means for transmitting the programs and queries from a terminal to the server; a means for the server to pass the received code to the interactive AI; a means for the interactive AI to analyze the code and return the results to the server; a means for visually displaying the identified data dependencies; a means for detecting anomalies and responding interactively to inquiries based on the visually displayed data flow; a means for notifying the interactive AI in real time when an anomaly occurs and returning the analysis results to the server; and a means for a user to make inquiries to the interactive AI through a web interface. This facilitates visualization and analysis of data flow, enabling rapid response when an anomaly occurs. Furthermore, interactive inquiry responses can improve the transparency and efficiency of data management.

[0768] "Conversational AI" is AI that understands input from a user and generates responses in natural language.

[0769] "Data flow" is a concept that indicates the sequence of events that data goes through, from input to processing, storage, and output.

[0770] A "data processing program" is code that contains a series of commands or algorithms for processing specific data.

[0771] A "query" is a statement expressing a question or request used to retrieve information from a database.

[0772] "Data dependency" refers to the interrelationships and dependencies that exist between multiple pieces of data.

[0773] A "server" is a computer dedicated to processing data and providing services to other computers and devices.

[0774] A "terminal" is a device that a user directly operates to input data or execute a program.

[0775] "Analysis" is the process of examining data in detail for a specific purpose to understand its structure and patterns.

[0776] "Visually displaying" means showing data flow and analysis results on a screen in a graphical format.

[0777] "Anomaly detection" refers to the automatic identification of abnormal conditions or errors that occur during normal data processing.

[0778] A "web interface" is a user interface that a user can access and operate via a web browser.

[0779] This invention relates to a system that uses interactive AI to streamline the flow and management of large amounts of data in a company. The system is primarily composed of a server, a terminal, and interactive AI.

[0780] First, the user sends the SQL code or Python program used for data processing to the system via the terminal. The terminal is responsible for sending the code received from the user as an HTTP request to the server. For example, the user may enter the following SQL query on the terminal: "SELECT customer_name FROM customers WHERE customer_id = 123".

[0781] The server passes the received code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the received SQL code or Python program to identify database tables, fields, and their dependencies. Specifically, it performs analysis based on the information extracted from the code and returns the results to the server in JSON or other data formats.

[0782] The server then receives the analysis results from the interactive AI and formats them to generate a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools. For example, if a "customers" table is related to a "sales" table through the "customer_id" field, this dependency is clearly visible.

[0783] The generated data flow diagram is displayed on a web interface via the server. Users can view it using a browser and intuitively understand the data flow and dependencies. The system also monitors data processing in real time, immediately notifying the interactive AI if an abnormality is detected. The interactive AI analyzes the scope of the abnormality and its cause, and sends the results back to the server.

[0784] Users can ask the conversational AI questions via the chat function of the web interface. For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will respond, "Customer_name comes from the customers table." This makes it quick and easy to understand abnormalities and complex data flows.

[0785] This system will make corporate data management more efficient, increase transparency, and enable rapid response in the event of an abnormality.

[0786] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0787] Step 1:

[0788] The user enters the data processing program or SQL code from the terminal.

[0789] Specifically, a user uses an SQL editor or programming IDE to write code for data management. For example, the user enters the SQL query "SELECT customer_name FROM customers WHERE customer_id = 123."

[0790] Input: The SQL code or program used to process the data.

[0791] Output: Input code data on the terminal.

[0792] Step 2:

[0793] The terminal sends the user's input to the server.

[0794] Specifically, the device generates an HTTP request, includes SQL code or a program in the request, and sends it to the server, for example, to send data using a RESTful API endpoint.

[0795] Input: SQL code or programs typed into a terminal by a user.

[0796] Output: The code data sent to the server.

[0797] Step 3:

[0798] The server passes the received code to an interactive artificial intelligence.

[0799] Specifically, the server sends an analysis request to the API endpoint of the conversational artificial intelligence and passes on the data containing the received SQL code or program.

[0800] Input: Code data sent from the terminal.

[0801] Output: The analysis request sent to the conversational artificial intelligence.

[0802] Step 4:

[0803] Conversational artificial intelligence analyzes the code.

[0804] Specifically, the conversational AI analyzes the received code to identify database tables, fields, and their dependencies, and generates the analysis results in a data format (e.g., JSON).

[0805] Input: Code data sent from the server.

[0806] Output: Analysis of database tables, fields, and dependencies.

[0807] Step 5:

[0808] The server generates a data flow diagram based on the analysis results.

[0809] Specifically, the server formats the analysis results obtained from the interactive AI and creates a graphical data flow diagram, using Mermaid notation for visualization.

[0810] Input: Analysis results obtained from interactive artificial intelligence.

[0811] Output: Graphical data flow diagram.

[0812] Step 6:

[0813] The server displays the generated data flow diagram to the user through a web interface.

[0814] Specifically, the server embeds the generated data flow diagram in a web page and displays it on the user's browser.

[0815] Input: The generated data flow diagram.

[0816] Output: A data flow diagram displayed in the user's browser.

[0817] Step 7:

[0818] The server monitors data processing in real time and notifies the conversational artificial intelligence if any abnormalities occur.

[0819] Specifically, the server monitors log files and real-time data streams, and if an anomaly is detected, it sends an analysis request to the interactive artificial intelligence.

[0820] Input: Real-time data and log files.

[0821] Output: Anomaly analysis request sent to the conversational artificial intelligence.

[0822] Step 8:

[0823] The interactive artificial intelligence analyzes the anomaly and sends the results back to the server.

[0824] Specifically, the interactive AI analyzes the scope and cause of the anomaly and returns the results to the server. The analysis results may also include recommended solutions.

[0825] Input: Anomaly analysis request sent from the server.

[0826] Output: Analysis of the anomaly's scope and cause, as well as recommended solutions.

[0827] Step 9:

[0828] Users use the chat function of the web interface to ask questions to the interactive artificial intelligence.

[0829] Specifically, a user opens the chat function on the web interface and asks a question such as, "Which table does the customer_name retrieved in this SQL query come from?" The conversational AI instantly generates an answer and provides it to the user.

[0830] Input: A query prompt from the user.

[0831] Output: Response from the conversational artificial intelligence.

[0832] (Application example 1)

[0833] 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."

[0834] Logistics facilities are required to manage large amounts of data in real time and detect and respond to abnormalities efficiently and quickly. However, to achieve this, advanced data analysis capabilities, intuitive visualization of data flow, and rapid notification and response in the event of an abnormality are required. Conventional systems have had difficulty meeting these requirements, and have faced the issue of the considerable time and effort required for data analysis and abnormality response.

[0835] 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.

[0836] In this invention, the server includes: means for analyzing data flow using an interactive artificial intelligence; means for inputting data processing programs and queries used within the company into the interactive artificial intelligence and identifying data dependencies; means for visually displaying the data dependencies together with real-time data from various sensors within the logistics facility; means for interactively responding to anomaly detections and inquiries in real time based on the visually displayed data flow; and means for notifying the user when an anomaly is detected, analyzing the cause, and automatically generating work instructions. This allows for efficient management of data flow within the logistics facility and enables rapid response when an anomaly occurs.

[0837] "Conversational artificial intelligence" is an artificial intelligence system that analyzes data and solves problems through natural language dialogue with users.

[0838] "Data flow" refers to the flow of how data flows and is processed within a system.

[0839] "Data dependency" refers to a relationship in which certain data is processed depending on other data, and includes relationships between tables in a database.

[0840] "Visual display means" refers to a method for displaying the results of data analysis in a visual format such as a graph or chart.

[0841] "Real-time data" is data that is constantly being updated from sensors and other data sources.

[0842] "Anomaly detection" is the automatic identification of unusual patterns and problems based on the analysis of data flows and data dependencies.

[0843] "Notification" refers to informing the user of an abnormality when it is detected.

[0844] "Work instructions" refer to specific action plans and instructions for dealing with detected abnormalities.

[0845] This system is designed to analyze large amounts of data from logistics facilities in real time, detect anomalies, and automatically generate related work instructions. A specific embodiment of the system is shown below.

[0846] Overall system overview

[0847] The system is composed of multiple components, including a server, terminals, and interactive AI. The server receives real-time data from sensors within the logistics facility and passes it to the interactive AI for analysis. The analysis results are used to visualize data flow and detect anomalies, and notify users as necessary.

[0848] Data Entry and Analysis

[0849] The terminals transmit real-time data from the sensors to a server, which then passes the data to an API endpoint for a conversational AI system to perform analysis. The conversational AI then uses the data to identify data flows and dependencies within the facility.

[0850] Data flow visualization

[0851] After the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram. This diagram is visually displayed using a graph drawing tool. The device (e.g., a smartphone or smart glasses) provides this visualized data flow diagram to the user, allowing them to view it in real time.

[0852] Anomaly detection and response

[0853] The server monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server. The user can receive the generated notification through their device and check specific work instructions to address the problem. This includes detailed analysis results and recommended countermeasures when an abnormality is detected.

[0854] Hardware and Software Used

[0855] Server: A high-performance data processing server, such as AWS EC2 or Google Cloud Compute Engine.

[0856] Device: User devices such as smartphones (iOS, Android), smart glasses, and head-mounted displays (HMD).

[0857] Conversational artificial intelligence: For example, "OpenAI GPT-3" and "Dialogflow."

[0858] Graph drawing tools: Visualization tools such as "Mermaid" and "D3.js".

[0859] Specific examples

[0860] Consider the example of monitoring the movement of large containers in a logistics facility in real time. Sensors send the container's location information to a server, which then uses an interactive AI to analyze the data. The analysis results are visualized as the container's movement path and displayed on a smartphone or smart glasses. If an abnormality is detected, for example, if the container moves to an unexpected location, the user is notified. At the same time, the interactive AI analyzes the cause of the abnormality and automatically generates recommended countermeasures as work instructions.

[0861] Example of input prompt for generative AI model:

[0862] "Generate a program to detect and visualize anomalies based on real-time data obtained from sensors in logistics facilities. The programming language used is Python, and the API endpoints are https: / / example.com / api / ai_endpoint and https: / / example.com / api / visualization. The sensor ID list is ['123', '456', '789']."

[0863] In this way, it is possible to build a system that improves the efficiency of data management within logistics facilities and supports rapid response in the event of an abnormality.

[0864] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0865] Step 1:

[0866] The terminal acquires real-time data from various sensors within the logistics facility and sends it to the server. The input includes the sensor ID and the acquired data (location, temperature, weight, etc.). The server receives this data and proceeds to the next analysis step.

[0867] Step 2:

[0868] The server passes the received real-time data to the API endpoint of the conversational AI to perform analysis. The input is the data from step 1, and the output is the analysis results of data flow and dependency. The server sends a request to the conversational AI and receives the analysis results.

[0869] Step 3:

[0870] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The input is the analysis results from step 2, and the output is a visualized data flow diagram. The data flow diagram is generated using a graph drawing tool such as Mermaid or D3.js.

[0871] Step 4:

[0872] The server sends the generated data flow diagram to the terminal, which then visually displays it to the user. The input is the data flow diagram from step 3, and the output is the information displayed on the terminal's display. The user can use this visualized data flow diagram to check the movement of data in real time.

[0873] Step 5:

[0874] The server monitors the data flow in real time and detects anomalies. If an anomaly is detected, it notifies the interactive AI. The input is real-time data, and the output is the anomaly detection result. Differences in data patterns are used to detect anomalies.

[0875] Step 6:

[0876] The interactive AI analyzes the scope of the anomaly's impact and its cause, and returns the results to the server. The input is the anomaly detection result from step 5, and the output is the detailed information about the anomaly and the analysis results of the scope of its impact. The interactive AI performs its analysis using a cause identification algorithm.

[0877] Step 7:

[0878] When an anomaly is detected, the server notifies the user and sends the cause and countermeasures to the terminal. The input is the analysis result from step 6, and the output is the notification to the user. The notification includes the cause of the anomaly and recommended countermeasures.

[0879] Step 8:

[0880] The user receives the notification and takes the necessary measures. Specifically, they check the details of the abnormality and implement the measures. The input is the notification content from Step 7, and the output is the measures taken by the user. By the user taking action based on the notification, the problem can be resolved quickly.

[0881] 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.

[0882] The present invention relates to a corporate data management system that combines conversational artificial intelligence and an emotion engine. Specifically, the system uses conversational artificial intelligence to analyze and visually display data flow, as well as recognize user emotions and change responses to achieve more effective data management and user support. A specific embodiment of this system is described below.

[0883] Overall system overview

[0884] This system is composed of multiple parts, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users and passes them to the conversational AI. It then generates a data flow diagram based on the analysis results and sends it to the terminal. The emotion engine analyzes the user's emotional state and provides feedback to the conversational AI's response.

[0885] Data Entry and Analysis

[0886] Users input SQL code or Python programs to be used for data processing into the system via a terminal. The terminal sends the user-provided code to the server. The server passes the code to the API endpoint of the conversational AI for analysis. The conversational AI identifies database tables, fields, and their dependencies from the code.

[0887] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools, allowing users to intuitively understand the data flow and dependencies.

[0888] Emotion recognition and response regulation

[0889] The system incorporates an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's text and voice input to identify the user's emotional state. For example, emotions such as excitement, anger, fatigue, and confusion can be detected from the text entered by the user.

[0890] After the emotion engine identifies the user's emotional state, it feeds that information back to the conversational AI, which then adjusts its response based on the emotion engine's analysis results and provides information to the user in the most optimal way. This helps users manage their data efficiently and without stress.

[0891] Data flow visualization

[0892] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can view the generated data flow diagram through a browser and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[0893] Anomaly detection and response

[0894] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to the user. Based on feedback from the emotion engine, the system is designed to provide detailed explanations and reassure users about points of particular concern.

[0895] Specific examples

[0896] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined on the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages.

[0897] In this way, the system of the present invention combines the analytical capabilities of interactive artificial intelligence, the emotion recognition capabilities of an emotion engine, and advanced dialogue functions to efficiently support companies' complex data management and provide optimal responses based on the user's emotions.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[0901] Step 2:

[0902] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[0903] Step 3:

[0904] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[0905] Step 4:

[0906] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[0907] Step 5:

[0908] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[0909] Step 6:

[0910] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[0911] Step 7:

[0912] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[0913] Step 8:

[0914] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[0915] Step 9:

[0916] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[0917] Step 10:

[0918] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[0919] Step 11:

[0920] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[0921] Step 12:

[0922] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[0923] Step 13:

[0924] The emotion engine analyzes the user's text and voice input to identify the user's emotional state, for example, detecting emotions such as excitement, anger, fatigue, and confusion from the text content entered by the user.

[0925] Step 14:

[0926] The server receives the analysis results from the emotion engine and feeds them back to the conversational AI, asking it to adjust its response based on the user's emotional state.

[0927] Step 15:

[0928] The conversational AI adjusts the response content based on the analysis results of the emotion engine to generate optimal answers, including information and support messages tailored to the user's emotional state.

[0929] Step 16:

[0930] The user sees the tailored response in a chat window and decides the next steps for data management based on the conversational AI's answers and supplemental information.

[0931] Step 17:

[0932] The server monitors data processing in real time and detects anomalies by monitoring logs and metrics and applying rules to detect anomalies.

[0933] Step 18:

[0934] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[0935] Step 19:

[0936] The interactive AI analyzes the scope and cause of the anomaly and returns the results to the server, providing detailed information for the user to take necessary measures.

[0937] Step 20:

[0938] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[0939] Specific examples

[0940] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined on the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages. In this way, the system can provide customized responses according to the user's emotional state.

[0941] Example 2

[0942] 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."

[0943] In modern organizations, the increasing complexity of data processing necessitates efficient data management and analysis methods. Furthermore, the lack of a system that can optimally respond to users' emotional states poses challenges in improving data management efficiency and user experience. In particular, if users misunderstand data dependencies or fail to respond appropriately when an abnormality occurs, this can cause delays in work and increased stress.

[0944] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0945] In this invention, the server includes means for analyzing data flow using an interactive AI, means for inputting data processing programs and queries used within an organization and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for analyzing the emotional state of the user and adjusting the response content of the interactive AI, thereby making it possible to streamline complex data management and provide optimal support according to the emotional state of the user.

[0946] "Conversational AI" is AI that has the ability to provide information and answer questions through conversation with the user.

[0947] "Data flow" is a structure that shows how data moves through a system and how it is processed.

[0948] "Data dependencies" refer to the interrelationships between different data sets or database tables, and how specific data affects other data.

[0949] "Visually displaying" means displaying data or information using visual means such as charts or graphs.

[0950] "Anomaly detection" is the process of detecting abnormal situations or errors within a system that deviate from normal operation.

[0951] "Emotional state" refers to analyzing emotions from a user's input or statements and identifying their emotions at that time.

[0952] "Adjusting the response content" means changing the appropriate information or response method based on the user's emotional state and input content.

[0953] "Program or Query" means the code or instructions used to process or analyze data.

[0954] A "structured data format" is a way of organizing and storing data in a consistent format, usually in a format such as JSON or XML.

[0955] The present invention relates to a data management system that combines a conversational AI and an emotion engine. This system is composed of a server, a terminal, a conversational AI, and an emotion engine.

[0956] Data Entry and Analysis

[0957] A user inputs SQL code or Python program related to data processing into the system from their own terminal. For example, a user may input the SQL code "SELECT customer_name FROM customers." The terminal sends this input to the server. The server then sends this code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the SQL code or Python program and identifies database tables, fields, and dependencies.

[0958] Data Visualization

[0959] The server receives the analysis results and generates a data flow diagram based on them. This data flow diagram is displayed visually using Mermaid notation or other graph drawing tools. For example, the interactive AI identifies the "customer_name field in the customers table," and the server draws the diagram based on this.

[0960] Emotion recognition and response regulation

[0961] When a user interacts with the system, the emotion engine analyzes the user's input text and speech to identify the user's emotional state. For example, if a user types, "Why does this query give me an error?", the emotion engine detects the user's "confusion" from the text. The emotion engine feeds the user's emotional state back to the conversational AI, which then adjusts the response based on the results.

[0962] Anomaly detection and response

[0963] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. For example, if a "connection error" or "grammar error" occurs during data processing, it will detect it and notify the conversational AI. The conversational AI will then analyze the cause and provide the user with a specific solution.

[0964] Examples and prompts

[0965] As a concrete example, consider the case where a user asks, "Which table does the customer_name retrieved by this SQL query come from?" The user enters this question on a terminal, which then sends the question to the server. The server passes the question to the conversational AI and requests an analysis. As a result of the analysis, the conversational AI determines that "customer_name comes from the customers table," and when the emotion engine detects the user's confusion, the conversational AI provides a detailed explanation (e.g., "The two tables are joined by the customer_id field in the sales table").

[0966] An example of a specific prompt for a generative AI model is as follows:

[0967] "Analyze the dependencies of the tables and fields used in this SQL query and generate a data flow diagram."

[0968] "Analyze the user's emotional state based on their input and tailor your response accordingly."

[0969] This allows the user to efficiently manage data and receive optimal support according to their emotions.

[0970] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0971] Step 1:

[0972] Users input SQL code or Python programs for data processing into the system from the terminal. For example, if a user inputs the SQL code "SELECT customer_name FROM customers", this code is saved as input data in the terminal.

[0973] Step 2:

[0974] The terminal sends the SQL code or Python program entered by the user to the server. The input data is transferred to the server via an HTTP POST request, which specifically involves sending the data to the API endpoint " / data / parse".

[0975] Step 3:

[0976] The server passes the received SQL code or Python program to the conversational AI's API endpoint for analysis. The server sends a POST request to the conversational AI to transmit the input data. The conversational AI analyzes the SQL code or Python program and performs data calculations to identify database tables, fields, and dependencies.

[0977] Step 4:

[0978] The AI ​​sends the analysis results back to the server, including the identified database tables, fields, and dependencies, such as "customer_name comes from the customers table."

[0979] Step 5:

[0980] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The server processes the data using Mermaid notation and graph drawing tools to visually display the obtained data. The generated data flow diagram is saved as a concrete output.

[0981] Step 6:

[0982] As users interact with the system, the emotion engine analyzes their input text and speech to identify their emotional state. For example, if a user types, "Why is this query giving me an error?", the emotion engine performs a data calculation to identify "confused" from the text.

[0983] Step 7:

[0984] The emotion engine feeds the identified emotional information back to the conversational AI, which then adjusts its response based on this input information. For example, it processes the data to generate a support message such as, "This is probably an SQL syntax error. Specifically, is a comma missing?"

[0985] Step 8:

[0986] The server displays the generated data flow diagram to the user through a web interface. The user can view the data flow diagram through a browser and intuitively understand the data flow and dependencies. The displayed data flow diagram is provided to the user as a concrete output.

[0987] Step 9:

[0988] The system monitors data processing in real time, and if an abnormality occurs, it immediately notifies the conversational AI. For example, if a "connection error" or "grammar error" occurs, it detects it and notifies the conversational AI. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server.

[0989] Step 10:

[0990] The server notifies the user of the analysis results, and the user can use the chat function on the web interface to ask the conversational AI for more details about the anomaly. The conversational AI generates a quick response and, if necessary, takes specific action to provide a detailed explanation based on feedback from the emotion engine.

[0991] These steps allow users to efficiently manage their data and receive optimal support according to their emotions.

[0992] (Application example 2)

[0993] 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."

[0994] Conventional data management systems require users to have a high level of specialized knowledge to understand data flows, and they are slow to respond when an abnormality occurs. Furthermore, they are unable to respond in a way that takes into account the user's emotional state, which can lead to stress. Especially for online shopping sites, where appropriate responses to customer inquiries are required, support that takes into account the user's emotional state is important. Therefore, there is a need for a system that can recognize the user's emotions and adjust responses based on them, thereby achieving efficient and friendly data management and user support.

[0995] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing data flow using interactive artificial intelligence, means for inputting data processing programs and queries used in the company and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for using an emotion engine that analyzes the user's emotional state and adjusts the response. This allows the user to intuitively understand the data flow and dependencies and to receive emotionally sensitive support even when an abnormality occurs.

[0996] "Conversational artificial intelligence" refers to artificial intelligence that provides information through dialogue with users and generates appropriate answers to their questions.

[0997] "Analyzing data flow" means investigating the flow and dependencies of data and clarifying their structure and relationships.

[0998] An "emotion engine" is a technology that analyzes a user's emotional state from text and voice and adjusts the system's response based on that information.

[0999] "Data processing programs and queries used within an enterprise" refers to code and instructions used to operate on or query an enterprise's databases and information systems.

[1000] "Identifying data dependencies" means identifying how one piece of data is related to other data in a database.

[1001] "Visual display" means showing the relationships and structure of data in a visible form using graphs, charts, diagrams, etc.

[1002] "Abnormality detection" means detecting abnormal behavior or phenomena in real time, and discovering problems early and taking measures to address them.

[1003] "Responding to inquiries in a conversational manner" means answering questions from users through natural conversation.

[1004] A "graph drawing tool" is software or a library for visually displaying data.

[1005] A "structured data format" is a data format in which data items and attributes are clearly defined and organized.

[1006] The present invention is a method for applying a conversational artificial intelligence and an emotion engine to a data management system for a company. The embodiments of the present invention will be described in detail below.

[1007] Overall system configuration

[1008] The system consists of multiple components, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users, requests analysis from the conversational AI, and visually displays the results. The emotion engine also analyzes the user's emotional state and provides feedback to the conversational AI's response. Users access the system via their terminals to input and retrieve the necessary information.

[1009] Hardware and software used

[1010] TensorFlow: To train and run emotion recognition models.

[1011] Dialogflow: Implements conversational artificial intelligence to analyze and respond to user inquiries.

[1012] Matplotlib: Draws data flow diagrams.

[1013] Flask: For server-side implementation and API integration.

[1014] React Native: Building the front end of smartphone applications.

[1015] AWS EC2: Provides virtual machines for server hosting.

[1016] Data Entry and Analysis

[1017] Users make inquiries via voice or text via a smartphone app. For example, they might input a query such as, "How do I return this product?" The input from the device is sent to the Flask server, which then calls the Dialogflow API to analyze the inquiry. At the same time, the input voice and text data is analyzed for emotional state using TensorFlow.

[1018] Explanation and response

[1019] The analyzed data is used by the conversational AI to generate an appropriate response. For example, if you enter "Please tell me the shipping status of order number 12345," the conversational AI will provide the current shipping status and detailed tracking information. Furthermore, based on the analyzed emotional state, the conversational AI will adjust the response and provide detailed support or additional explanations as needed.

[1020] Data flow visualization

[1021] The server generates a data flow diagram using Mermaid notation and Matplotlib and displays it visually to the user, allowing the user to intuitively understand the data flow and dependencies.

[1022] Specific examples

[1023] Here are some examples of specific prompts:

[1024] "How do I return this product?"

[1025] "Please let me know the shipping status of order number 12345."

[1026] "I can't log into my account, please help"

[1027] This allows users to easily make inquiries and obtain the information they need in an easy-to-understand and fast manner through responses from conversational artificial intelligence and adjustments by the emotion engine.

[1028] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1029] Step 1:

[1030] The user inputs a query via voice or text via a smartphone app. For example, they might ask, "How do I return this product?" The input data is sent to the terminal.

[1031] Step 2:

[1032] The device sends the input data, which can include text and audio data, to the Flask server, which then begins analyzing the data.

[1033] Step 3:

[1034] The server first calls the Dialogflow API to analyze the user's inquiry. Specifically, it analyzes the input text and voice data and obtains information to generate a corresponding response. The input data is sent to the Dialogflow API as an analysis request, and an appropriate response is returned as the analysis result.

[1035] Step 4:

[1036] At the same time, the server uses TensorFlow to analyze the user's emotional state from the input voice and text data. Specifically, it uses an emotion recognition model to identify the user's emotions (e.g., anger, confusion, joy, etc.). Based on this, emotional state data is generated.

[1037] Step 5:

[1038] The server integrates the response obtained from Dialogflow with the emotional state data obtained from TensorFlow. This allows the response to be adjusted according to the user's emotional state. For example, if the user is confused, a more polite and detailed explanation is added. The input data is integrated as an analysis result and output as an adjusted response.

[1039] Step 6:

[1040] The server sends the final response to the terminal, which then displays the received response to the user, either in text format or as audio. The user can then obtain the adjusted response.

[1041] Step 7:

[1042] If necessary, the server generates a data flow diagram using Mermaid notation or Matplotlib and displays it visually to the user. Input data is sent to the server as a data analysis request, and the output is a visual data flow diagram, which the user can use to intuitively understand the data flow and dependencies.

[1043] In this way, each processing step analyzes and responds to user input, and further adjusts according to emotional state, resulting in more effective and friendly data management and user support.

[1044] 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.

[1045] 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.

[1046] 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.

[1047] [Fourth embodiment]

[1048] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1049] 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.

[1050] 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).

[1051] 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.

[1052] 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.

[1053] 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).

[1054] 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.

[1055] 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.

[1056] 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.

[1057] 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.

[1058] 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.

[1059] 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.

[1060] 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."

[1061] The present invention relates to a system for streamlining the flow and management of large-scale corporate data using interactive artificial intelligence. Specific embodiments of this system are described below.

[1062] Overall system overview

[1063] This system consists of multiple components, including a server, a terminal, and an interactive AI. The server receives data processing programs and SQL queries from users and passes them to the interactive AI for analysis. The analysis results are used to visualize data flows and detect anomalies.

[1064] Data Entry and Analysis

[1065] Users upload SQL code or Python programs to process data to the system via a terminal. The terminal sends the user-provided code to the server, which passes the code to an API endpoint of the conversational AI for analysis. The conversational AI then identifies database tables, fields, and their dependencies from the code.

[1066] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is visually displayed using Mermaid notation and other graph drawing tools. The diagram is designed to help users intuitively understand data flows and dependencies.

[1067] Data flow visualization

[1068] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can use a browser to view the generated data flow diagram and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[1069] Anomaly detection and response

[1070] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to users.

[1071] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will answer, "The customer_name comes from the customers table. The two tables are joined on the customer_id field in the sales table."

[1072] As described above, the system of the present invention utilizes the analytical capabilities and interactive functions of interactive AI to efficiently manage complex data flows and quickly detect anomalies and respond to inquiries. This system allows companies to improve the efficiency and transparency of data management.

[1073] The processing flow will be explained below.

[1074] Step 1:

[1075] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[1076] Step 2:

[1077] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[1078] Step 3:

[1079] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[1080] Step 4:

[1081] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[1082] Step 5:

[1083] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[1084] Step 6:

[1085] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[1086] Step 7:

[1087] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[1088] Step 8:

[1089] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[1090] Step 9:

[1091] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[1092] Step 10:

[1093] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[1094] Step 11:

[1095] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[1096] Step 12:

[1097] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[1098] Step 13:

[1099] The server monitors data processing in real time and detects anomalies while it is running, monitoring logs and metrics and applying rules to detect anomalies.

[1100] Step 14:

[1101] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[1102] Step 15:

[1103] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[1104] Through these steps, the system achieves efficient data management and rapid response in the event of an abnormality.

[1105] Example 1

[1106] 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."

[1107] Data management in modern companies is becoming increasingly complex, requiring efficient analysis, visualization, anomaly detection, and rapid response to data flows. However, traditional data management systems make it difficult to intuitively understand the overall picture of data flows, and it is also difficult to respond quickly when an anomaly occurs. Furthermore, many systems rely on individual tools and manual processes, preventing integrated data management. This creates challenges that delay improvements in data management efficiency and transparency.

[1108] 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.

[1109] In this invention, the server includes: a means for analyzing data flow using an interactive AI; a means for inputting data processing programs and queries used within the company and identifying data dependencies; a means for transmitting the programs and queries from a terminal to the server; a means for the server to pass the received code to the interactive AI; a means for the interactive AI to analyze the code and return the results to the server; a means for visually displaying the identified data dependencies; a means for detecting anomalies and responding interactively to inquiries based on the visually displayed data flow; a means for notifying the interactive AI in real time when an anomaly occurs and returning the analysis results to the server; and a means for a user to make inquiries to the interactive AI through a web interface. This facilitates visualization and analysis of data flow, enabling rapid response when an anomaly occurs. Furthermore, interactive inquiry responses can improve the transparency and efficiency of data management.

[1110] "Conversational AI" is AI that understands input from a user and generates responses in natural language.

[1111] "Data flow" is a concept that indicates the sequence of events that data goes through, from input to processing, storage, and output.

[1112] A "data processing program" is code that contains a series of commands or algorithms for processing specific data.

[1113] A "query" is a statement expressing a question or request used to retrieve information from a database.

[1114] "Data dependency" refers to the interrelationships and dependencies that exist between multiple pieces of data.

[1115] A "server" is a computer dedicated to processing data and providing services to other computers and devices.

[1116] A "terminal" is a device that a user directly operates to input data or execute a program.

[1117] "Analysis" is the process of examining data in detail for a specific purpose to understand its structure and patterns.

[1118] "Visually displaying" means showing data flow and analysis results on a screen in a graphical format.

[1119] "Anomaly detection" refers to the automatic identification of abnormal conditions or errors that occur during normal data processing.

[1120] A "web interface" is a user interface that a user can access and operate via a web browser.

[1121] This invention relates to a system that uses interactive AI to streamline the flow and management of large amounts of data in a company. The system is primarily composed of a server, a terminal, and interactive AI.

[1122] First, the user sends the SQL code or Python program used for data processing to the system via the terminal. The terminal is responsible for sending the code received from the user as an HTTP request to the server. For example, the user may enter the following SQL query on the terminal: "SELECT customer_name FROM customers WHERE customer_id = 123".

[1123] The server passes the received code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the received SQL code or Python program to identify database tables, fields, and their dependencies. Specifically, it performs analysis based on the information extracted from the code and returns the results to the server in JSON or other data formats.

[1124] The server then receives the analysis results from the interactive AI and formats them to generate a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools. For example, if a "customers" table is related to a "sales" table through the "customer_id" field, this dependency is clearly visible.

[1125] The generated data flow diagram is displayed on a web interface via the server. Users can view it using a browser and intuitively understand the data flow and dependencies. The system also monitors data processing in real time, immediately notifying the interactive AI if an abnormality is detected. The interactive AI analyzes the scope of the abnormality and its cause, and sends the results back to the server.

[1126] Users can ask the conversational AI questions via the chat function of the web interface. For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI will respond, "Customer_name comes from the customers table." This makes it quick and easy to understand abnormalities and complex data flows.

[1127] This system will make corporate data management more efficient, increase transparency, and enable rapid response in the event of an abnormality.

[1128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1129] Step 1:

[1130] The user enters the data processing program or SQL code from the terminal.

[1131] Specifically, a user uses an SQL editor or programming IDE to write code for data management. For example, the user enters the SQL query "SELECT customer_name FROM customers WHERE customer_id = 123."

[1132] Input: The SQL code or program used to process the data.

[1133] Output: Input code data on the terminal.

[1134] Step 2:

[1135] The terminal sends the user's input to the server.

[1136] Specifically, the device generates an HTTP request, includes SQL code or a program in the request, and sends it to the server, for example, to send data using a RESTful API endpoint.

[1137] Input: SQL code or programs typed into a terminal by a user.

[1138] Output: The code data sent to the server.

[1139] Step 3:

[1140] The server passes the received code to an interactive artificial intelligence.

[1141] Specifically, the server sends an analysis request to the API endpoint of the conversational artificial intelligence and passes on the data containing the received SQL code or program.

[1142] Input: Code data sent from the terminal.

[1143] Output: The analysis request sent to the conversational artificial intelligence.

[1144] Step 4:

[1145] Conversational artificial intelligence analyzes the code.

[1146] Specifically, the conversational AI analyzes the received code to identify database tables, fields, and their dependencies, and generates the analysis results in a data format (e.g., JSON).

[1147] Input: Code data sent from the server.

[1148] Output: Analysis of database tables, fields, and dependencies.

[1149] Step 5:

[1150] The server generates a data flow diagram based on the analysis results.

[1151] Specifically, the server formats the analysis results obtained from the interactive AI and creates a graphical data flow diagram, using Mermaid notation for visualization.

[1152] Input: Analysis results obtained from interactive artificial intelligence.

[1153] Output: Graphical data flow diagram.

[1154] Step 6:

[1155] The server displays the generated data flow diagram to the user through a web interface.

[1156] Specifically, the server embeds the generated data flow diagram in a web page and displays it on the user's browser.

[1157] Input: The generated data flow diagram.

[1158] Output: A data flow diagram displayed in the user's browser.

[1159] Step 7:

[1160] The server monitors data processing in real time and notifies the conversational artificial intelligence if any abnormalities occur.

[1161] Specifically, the server monitors log files and real-time data streams, and if an anomaly is detected, it sends an analysis request to the interactive artificial intelligence.

[1162] Input: Real-time data and log files.

[1163] Output: Anomaly analysis request sent to the conversational artificial intelligence.

[1164] Step 8:

[1165] The interactive artificial intelligence analyzes the anomaly and sends the results back to the server.

[1166] Specifically, the interactive AI analyzes the scope and cause of the anomaly and returns the results to the server. The analysis results may also include recommended solutions.

[1167] Input: Anomaly analysis request sent from the server.

[1168] Output: Analysis of the anomaly's scope and cause, as well as recommended solutions.

[1169] Step 9:

[1170] Users use the chat function of the web interface to ask questions to the interactive artificial intelligence.

[1171] Specifically, a user opens the chat function on the web interface and asks a question such as, "Which table does the customer_name retrieved in this SQL query come from?" The conversational AI instantly generates an answer and provides it to the user.

[1172] Input: A query prompt from the user.

[1173] Output: Response from the conversational artificial intelligence.

[1174] (Application example 1)

[1175] 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."

[1176] Logistics facilities are required to manage large amounts of data in real time and detect and respond to abnormalities efficiently and quickly. However, to achieve this, advanced data analysis capabilities, intuitive visualization of data flow, and rapid notification and response in the event of an abnormality are required. Conventional systems have had difficulty meeting these requirements, and have faced the issue of the considerable time and effort required for data analysis and abnormality response.

[1177] 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.

[1178] In this invention, the server includes: means for analyzing data flow using an interactive artificial intelligence; means for inputting data processing programs and queries used within the company into the interactive artificial intelligence and identifying data dependencies; means for visually displaying the data dependencies together with real-time data from various sensors within the logistics facility; means for interactively responding to anomaly detections and inquiries in real time based on the visually displayed data flow; and means for notifying the user when an anomaly is detected, analyzing the cause, and automatically generating work instructions. This allows for efficient management of data flow within the logistics facility and enables rapid response when an anomaly occurs.

[1179] "Conversational artificial intelligence" is an artificial intelligence system that analyzes data and solves problems through natural language dialogue with users.

[1180] "Data flow" refers to the flow of how data flows and is processed within a system.

[1181] "Data dependency" refers to a relationship in which certain data is processed depending on other data, and includes relationships between tables in a database.

[1182] "Visual display means" refers to a method for displaying the results of data analysis in a visual format such as a graph or chart.

[1183] "Real-time data" is data that is constantly being updated from sensors and other data sources.

[1184] "Anomaly detection" is the automatic identification of unusual patterns and problems based on the analysis of data flows and data dependencies.

[1185] "Notification" refers to informing the user of an abnormality when it is detected.

[1186] "Work instructions" refer to specific action plans and instructions for dealing with detected abnormalities.

[1187] This system is designed to analyze large amounts of data from logistics facilities in real time, detect anomalies, and automatically generate related work instructions. A specific embodiment of the system is shown below.

[1188] Overall system overview

[1189] The system is composed of multiple components, including a server, terminals, and interactive AI. The server receives real-time data from sensors within the logistics facility and passes it to the interactive AI for analysis. The analysis results are used to visualize data flow and detect anomalies, and notify users as necessary.

[1190] Data Entry and Analysis

[1191] The terminals transmit real-time data from the sensors to a server, which then passes the data to an API endpoint for a conversational AI system to perform analysis. The conversational AI then uses the data to identify data flows and dependencies within the facility.

[1192] Data flow visualization

[1193] After the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram. This diagram is visually displayed using a graph drawing tool. The device (e.g., a smartphone or smart glasses) provides this visualized data flow diagram to the user, allowing them to view it in real time.

[1194] Anomaly detection and response

[1195] The server monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server. The user can receive the generated notification through their device and check specific work instructions to address the problem. This includes detailed analysis results and recommended countermeasures when an abnormality is detected.

[1196] Hardware and Software Used

[1197] Server: A high-performance data processing server, such as AWS EC2 or Google Cloud Compute Engine.

[1198] Device: User devices such as smartphones (iOS, Android), smart glasses, and head-mounted displays (HMD).

[1199] Conversational artificial intelligence: For example, "OpenAI GPT-3" and "Dialogflow."

[1200] Graph drawing tools: Visualization tools such as "Mermaid" and "D3.js".

[1201] Specific examples

[1202] Consider the example of monitoring the movement of large containers in a logistics facility in real time. Sensors send the container's location information to a server, which then uses an interactive AI to analyze the data. The analysis results are visualized as the container's movement path and displayed on a smartphone or smart glasses. If an abnormality is detected, for example, if the container moves to an unexpected location, the user is notified. At the same time, the interactive AI analyzes the cause of the abnormality and automatically generates recommended countermeasures as work instructions.

[1203] Example of input prompt for generative AI model:

[1204] "Generate a program to detect and visualize anomalies based on real-time data obtained from sensors in logistics facilities. The programming language used is Python, and the API endpoints are https: / / example.com / api / ai_endpoint and https: / / example.com / api / visualization. The sensor ID list is ['123', '456', '789']."

[1205] In this way, it is possible to build a system that improves the efficiency of data management within logistics facilities and supports rapid response in the event of an abnormality.

[1206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1207] Step 1:

[1208] The terminal acquires real-time data from various sensors within the logistics facility and sends it to the server. The input includes the sensor ID and the acquired data (location, temperature, weight, etc.). The server receives this data and proceeds to the next analysis step.

[1209] Step 2:

[1210] The server passes the received real-time data to the API endpoint of the conversational AI to perform analysis. The input is the data from step 1, and the output is the analysis results of data flow and dependency. The server sends a request to the conversational AI and receives the analysis results.

[1211] Step 3:

[1212] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The input is the analysis results from step 2, and the output is a visualized data flow diagram. The data flow diagram is generated using a graph drawing tool such as Mermaid or D3.js.

[1213] Step 4:

[1214] The server sends the generated data flow diagram to the terminal, which then visually displays it to the user. The input is the data flow diagram from step 3, and the output is the information displayed on the terminal's display. The user can use this visualized data flow diagram to check the movement of data in real time.

[1215] Step 5:

[1216] The server monitors the data flow in real time and detects anomalies. If an anomaly is detected, it notifies the interactive AI. The input is real-time data, and the output is the anomaly detection result. Differences in data patterns are used to detect anomalies.

[1217] Step 6:

[1218] The interactive AI analyzes the scope of the anomaly's impact and its cause, and returns the results to the server. The input is the anomaly detection result from step 5, and the output is the detailed information about the anomaly and the analysis results of the scope of its impact. The interactive AI performs its analysis using a cause identification algorithm.

[1219] Step 7:

[1220] When an anomaly is detected, the server notifies the user and sends the cause and countermeasures to the terminal. The input is the analysis result from step 6, and the output is the notification to the user. The notification includes the cause of the anomaly and recommended countermeasures.

[1221] Step 8:

[1222] The user receives the notification and takes the necessary measures. Specifically, they check the details of the abnormality and implement the measures. The input is the notification content from Step 7, and the output is the measures taken by the user. By the user taking action based on the notification, the problem can be resolved quickly.

[1223] 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.

[1224] The present invention relates to a corporate data management system that combines conversational artificial intelligence and an emotion engine. Specifically, the system uses conversational artificial intelligence to analyze and visually display data flow, as well as recognize user emotions and change responses to achieve more effective data management and user support. A specific embodiment of this system is described below.

[1225] Overall system overview

[1226] This system is composed of multiple parts, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users and passes them to the conversational AI. It then generates a data flow diagram based on the analysis results and sends it to the terminal. The emotion engine analyzes the user's emotional state and provides feedback to the conversational AI's response.

[1227] Data Entry and Analysis

[1228] Users input SQL code or Python programs to be used for data processing into the system via a terminal. The terminal sends the user-provided code to the server. The server passes the code to the API endpoint of the conversational AI for analysis. The conversational AI identifies database tables, fields, and their dependencies from the code.

[1229] Once the analysis is complete, the server formats the information obtained from the interactive AI and generates a data flow diagram, which is then visually displayed using Mermaid notation or other graph drawing tools, allowing users to intuitively understand the data flow and dependencies.

[1230] Emotion recognition and response regulation

[1231] The system incorporates an emotion engine that analyzes the user's emotions. The emotion engine analyzes the user's text and voice input to identify the user's emotional state. For example, emotions such as excitement, anger, fatigue, and confusion can be detected from the text entered by the user.

[1232] After the emotion engine identifies the user's emotional state, it feeds that information back to the conversational AI, which then adjusts its response based on the emotion engine's analysis results and provides information to the user in the most optimal way. This helps users manage their data efficiently and without stress.

[1233] Data flow visualization

[1234] The server generates a data flow diagram based on the formatted analysis results and displays it to the user through a web interface. The user can view the generated data flow diagram through a browser and visually evaluate the analysis results. The graph drawing using Mermaid notation clearly shows the relationships between tables and data dependencies.

[1235] Anomaly detection and response

[1236] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. The conversational AI analyzes the scope of the abnormality's impact and cause and returns the results to the server. Users can use the chat function on the web interface to inquire about the details of the abnormality to the conversational AI. The conversational AI quickly generates answers to questions and provides them to the user. Based on feedback from the emotion engine, the system is designed to provide detailed explanations and reassure users about points of particular concern.

[1237] Specific examples

[1238] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined on the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages.

[1239] In this way, the system of the present invention combines the analytical capabilities of interactive artificial intelligence, the emotion recognition capabilities of an emotion engine, and advanced dialogue functions to efficiently support companies' complex data management and provide optimal responses based on the user's emotions.

[1240] The processing flow will be explained below.

[1241] Step 1:

[1242] Users input SQL code or Python programs to be used for data processing into the system via a terminal. They enter the necessary code in a text area on the terminal's web interface and click the "Start Analysis" button.

[1243] Step 2:

[1244] The terminal sends the code entered by the user to the server by generating an HTTP POST request and sending the entered program code as a payload to the server.

[1245] Step 3:

[1246] The server sends the received code to the API endpoint of the conversational AI for analysis, generates an API request, and sends the program code.

[1247] Step 4:

[1248] Conversational artificial intelligence analyzes incoming code to identify used database tables, fields, and their dependencies, and uses natural language processing and syntactic analysis to extract database structure and data flow.

[1249] Step 5:

[1250] The server formats the analysis results obtained from the conversational AI, converting the received data into structured data such as JSON format, making it easy to use within the system.

[1251] Step 6:

[1252] The server generates a data flow diagram based on the formatted analysis results. It uses a graph drawing library to create a data flow diagram that visually represents the relationships between tables.

[1253] Step 7:

[1254] The server generates a web page for displaying the generated data flow diagram to the user, dynamically generating HTML and JavaScript to construct the web page with the data flow diagram embedded.

[1255] Step 8:

[1256] The user checks the data flow diagram through a browser, accesses the web page, and visually evaluates the displayed data flow diagram.

[1257] Step 9:

[1258] Users can discover questions or anomalies in the data flow diagram and interactively seek further information by entering questions in natural language using the chat function in the web interface.

[1259] Step 10:

[1260] The server forwards the user's question to the conversational AI and waits for a response. It generates an API request and sends the user's question.

[1261] Step 11:

[1262] The conversational AI generates answers to questions and sends them back to the server. It uses natural language processing to analyze information related to the question and generate appropriate answers.

[1263] Step 12:

[1264] The server displays the answer from the conversational artificial intelligence to the user, and displays the received answer in a chat window so that the user can check it.

[1265] Step 13:

[1266] The emotion engine analyzes the user's text and voice input to identify the user's emotional state, for example, detecting emotions such as excitement, anger, fatigue, and confusion from the text content entered by the user.

[1267] Step 14:

[1268] The server receives the analysis results from the emotion engine and feeds them back to the conversational AI, asking it to adjust its response based on the user's emotional state.

[1269] Step 15:

[1270] The conversational AI adjusts the response content based on the analysis results of the emotion engine to generate optimal answers, including information and support messages tailored to the user's emotional state.

[1271] Step 16:

[1272] The user sees the tailored response in a chat window and decides the next steps for data management based on the conversational AI's answers and supplemental information.

[1273] Step 17:

[1274] The server monitors data processing in real time and detects anomalies by monitoring logs and metrics and applying rules to detect anomalies.

[1275] Step 18:

[1276] If the server detects an abnormality, it notifies the conversational AI and requests a detailed analysis. Information about the abnormal event is sent to the conversational AI, which then identifies the scope of the impact and the cause.

[1277] Step 19:

[1278] The interactive AI analyzes the scope and cause of the anomaly and returns the results to the server, providing detailed information for the user to take necessary measures.

[1279] Step 20:

[1280] The server notifies the user of the analysis results from the interactive AI, and presents the details of the anomaly and recommended countermeasures to the user via a web interface.

[1281] Specific examples

[1282] For example, if a user asks, "Which table does the customer_name retrieved in this SQL query come from?", the conversational AI can answer, "The customer_name comes from the customers table. Both tables are joined by the customer_id field in the sales table." If the user expresses confusion or anxiety, the emotion engine can identify that state and the conversational AI can provide additional detailed explanations or support messages. In this way, the system can provide customized responses according to the user's emotional state.

[1283] Example 2

[1284] 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."

[1285] In modern organizations, the increasing complexity of data processing necessitates efficient data management and analysis methods. Furthermore, the lack of a system that can optimally respond to users' emotional states poses challenges in improving data management efficiency and user experience. In particular, if users misunderstand data dependencies or fail to respond appropriately when an abnormality occurs, this can cause delays in work and increased stress.

[1286] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1287] In this invention, the server includes means for analyzing data flow using an interactive AI, means for inputting data processing programs and queries used within an organization and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for analyzing the emotional state of the user and adjusting the response content of the interactive AI, thereby making it possible to streamline complex data management and provide optimal support according to the emotional state of the user.

[1288] "Conversational AI" is AI that has the ability to provide information and answer questions through conversation with the user.

[1289] "Data flow" is a structure that shows how data moves through a system and how it is processed.

[1290] "Data dependencies" refer to the interrelationships between different data sets or database tables, and how specific data affects other data.

[1291] "Visually displaying" means displaying data or information using visual means such as charts or graphs.

[1292] "Anomaly detection" is the process of detecting abnormal situations or errors within a system that deviate from normal operation.

[1293] "Emotional state" refers to analyzing emotions from a user's input or statements and identifying their emotions at that time.

[1294] "Adjusting the response content" means changing the appropriate information or response method based on the user's emotional state and input content.

[1295] "Program or Query" means the code or instructions used to process or analyze data.

[1296] A "structured data format" is a way of organizing and storing data in a consistent format, usually in a format such as JSON or XML.

[1297] The present invention relates to a data management system that combines a conversational AI and an emotion engine. This system is composed of a server, a terminal, a conversational AI, and an emotion engine.

[1298] Data Entry and Analysis

[1299] A user inputs SQL code or Python program related to data processing into the system from their own terminal. For example, a user may input the SQL code "SELECT customer_name FROM customers." The terminal sends this input to the server. The server then sends this code to the API endpoint of the conversational AI for analysis. The conversational AI analyzes the SQL code or Python program and identifies database tables, fields, and dependencies.

[1300] Data Visualization

[1301] The server receives the analysis results and generates a data flow diagram based on them. This data flow diagram is displayed visually using Mermaid notation or other graph drawing tools. For example, the interactive AI identifies the "customer_name field in the customers table," and the server draws the diagram based on this.

[1302] Emotion recognition and response regulation

[1303] When a user interacts with the system, the emotion engine analyzes the user's input text and speech to identify the user's emotional state. For example, if a user types, "Why does this query give me an error?", the emotion engine detects the user's "confusion" from the text. The emotion engine feeds the user's emotional state back to the conversational AI, which then adjusts the response based on the results.

[1304] Anomaly detection and response

[1305] The system monitors data processing in real time and immediately notifies the conversational AI if an abnormality occurs. For example, if a "connection error" or "grammar error" occurs during data processing, it will detect it and notify the conversational AI. The conversational AI will then analyze the cause and provide the user with a specific solution.

[1306] Examples and prompts

[1307] As a concrete example, consider the case where a user asks, "Which table does the customer_name retrieved by this SQL query come from?" The user enters this question on a terminal, which then sends the question to the server. The server passes the question to the conversational AI and requests an analysis. As a result of the analysis, the conversational AI determines that "customer_name comes from the customers table," and when the emotion engine detects the user's confusion, the conversational AI provides a detailed explanation (e.g., "The two tables are joined by the customer_id field in the sales table").

[1308] An example of a specific prompt for a generative AI model is as follows:

[1309] "Analyze the dependencies of the tables and fields used in this SQL query and generate a data flow diagram."

[1310] "Analyze the user's emotional state based on their input and tailor your response accordingly."

[1311] This allows the user to efficiently manage data and receive optimal support according to their emotions.

[1312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1313] Step 1:

[1314] Users input SQL code or Python programs for data processing into the system from the terminal. For example, if a user inputs the SQL code "SELECT customer_name FROM customers", this code is saved as input data in the terminal.

[1315] Step 2:

[1316] The terminal sends the SQL code or Python program entered by the user to the server. The input data is transferred to the server via an HTTP POST request, which specifically involves sending the data to the API endpoint " / data / parse".

[1317] Step 3:

[1318] The server passes the received SQL code or Python program to the conversational AI's API endpoint for analysis. The server sends a POST request to the conversational AI to transmit the input data. The conversational AI analyzes the SQL code or Python program and performs data calculations to identify database tables, fields, and dependencies.

[1319] Step 4:

[1320] The AI ​​sends the analysis results back to the server, including the identified database tables, fields, and dependencies, such as "customer_name comes from the customers table."

[1321] Step 5:

[1322] The server formats the analysis results obtained from the interactive AI and generates a data flow diagram. The server processes the data using Mermaid notation and graph drawing tools to visually display the obtained data. The generated data flow diagram is saved as a concrete output.

[1323] Step 6:

[1324] As users interact with the system, the emotion engine analyzes their input text and speech to identify their emotional state. For example, if a user types, "Why is this query giving me an error?", the emotion engine performs a data calculation to identify "confused" from the text.

[1325] Step 7:

[1326] The emotion engine feeds the identified emotional information back to the conversational AI, which then adjusts its response based on this input information. For example, it processes the data to generate a support message such as, "This is probably an SQL syntax error. Specifically, is a comma missing?"

[1327] Step 8:

[1328] The server displays the generated data flow diagram to the user through a web interface. The user can view the data flow diagram through a browser and intuitively understand the data flow and dependencies. The displayed data flow diagram is provided to the user as a concrete output.

[1329] Step 9:

[1330] The system monitors data processing in real time, and if an abnormality occurs, it immediately notifies the conversational AI. For example, if a "connection error" or "grammar error" occurs, it detects it and notifies the conversational AI. The conversational AI analyzes the scope and cause of the abnormality and returns the results to the server.

[1331] Step 10:

[1332] The server notifies the user of the analysis results, and the user can use the chat function on the web interface to ask the conversational AI for more details about the anomaly. The conversational AI generates a quick response and, if necessary, takes specific action to provide a detailed explanation based on feedback from the emotion engine.

[1333] These steps allow users to efficiently manage their data and receive optimal support according to their emotions.

[1334] (Application example 2)

[1335] 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."

[1336] Conventional data management systems require users to have a high level of specialized knowledge to understand data flows, and they are slow to respond when an abnormality occurs. Furthermore, they are unable to respond in a way that takes into account the user's emotional state, which can lead to stress. Especially for online shopping sites, where appropriate responses to customer inquiries are required, support that takes into account the user's emotional state is important. Therefore, there is a need for a system that can recognize the user's emotions and adjust responses based on them, thereby achieving efficient and friendly data management and user support.

[1337] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing data flow using interactive artificial intelligence, means for inputting data processing programs and queries used in the company and identifying data dependencies, means for visually displaying the identified data dependencies, means for detecting anomalies and responding to inquiries in an interactive format based on the visually displayed data flow, and means for using an emotion engine that analyzes the user's emotional state and adjusts the response. This allows the user to intuitively understand the data flow and dependencies and to receive emotionally sensitive support even when an abnormality occurs.

[1338] "Conversational artificial intelligence" refers to artificial intelligence that provides information through dialogue with users and generates appropriate answers to their questions.

[1339] "Analyzing data flow" means investigating the flow and dependencies of data and clarifying their structure and relationships.

[1340] An "emotion engine" is a technology that analyzes a user's emotional state from text and voice and adjusts the system's response based on that information.

[1341] "Data processing programs and queries used within an enterprise" refers to code and instructions used to operate on or query an enterprise's databases and information systems.

[1342] "Identifying data dependencies" means identifying how one piece of data is related to other data in a database.

[1343] "Visual display" means showing the relationships and structure of data in a visible form using graphs, charts, diagrams, etc.

[1344] "Abnormality detection" means detecting abnormal behavior or phenomena in real time, and discovering problems early and taking measures to address them.

[1345] "Responding to inquiries in a conversational manner" means answering questions from users through natural conversation.

[1346] A "graph drawing tool" is software or a library for visually displaying data.

[1347] A "structured data format" is a data format in which data items and attributes are clearly defined and organized.

[1348] The present invention is a method for applying a conversational artificial intelligence and an emotion engine to a data management system for a company. The embodiments of the present invention will be described in detail below.

[1349] Overall system configuration

[1350] The system consists of multiple components, including a server, a terminal, a conversational AI, and an emotion engine. The server receives data processing programs and queries from users, requests analysis from the conversational AI, and visually displays the results. The emotion engine also analyzes the user's emotional state and provides feedback to the conversational AI's response. Users access the system via their terminals to input and retrieve the necessary information.

[1351] Hardware and software used

[1352] TensorFlow: To train and run emotion recognition models.

[1353] Dialogflow: Implements conversational artificial intelligence to analyze and respond to user inquiries.

[1354] Matplotlib: Draws data flow diagrams.

[1355] Flask: For server-side implementation and API integration.

[1356] React Native: Building the front end of smartphone applications.

[1357] AWS EC2: Provides virtual machines for server hosting.

[1358] Data Entry and Analysis

[1359] Users make inquiries via voice or text via a smartphone app. For example, they might input a query such as, "How do I return this product?" The input from the device is sent to the Flask server, which then calls the Dialogflow API to analyze the inquiry. At the same time, the input voice and text data is analyzed for emotional state using TensorFlow.

[1360] Explanation and response

[1361] The analyzed data is used by the conversational AI to generate an appropriate response. For example, if you enter "Please tell me the shipping status of order number 12345," the conversational AI will provide the current shipping status and detailed tracking information. Furthermore, based on the analyzed emotional state, the conversational AI will adjust the response and provide detailed support or additional explanations as needed.

[1362] Data flow visualization

[1363] The server generates a data flow diagram using Mermaid notation and Matplotlib and displays it visually to the user, allowing the user to intuitively understand the data flow and dependencies.

[1364] Specific examples

[1365] Here are some examples of specific prompts:

[1366] "How do I return this product?"

[1367] "Please let me know the shipping status of order number 12345."

[1368] "I can't log into my account, please help"

[1369] This allows users to easily make inquiries and obtain the information they need in an easy-to-understand and fast manner through responses from conversational artificial intelligence and adjustments by the emotion engine.

[1370] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1371] Step 1:

[1372] The user inputs a query via voice or text via a smartphone app. For example, they might ask, "How do I return this product?" The input data is sent to the terminal.

[1373] Step 2:

[1374] The device sends the input data, which can include text and audio data, to the Flask server, which then begins analyzing the data.

[1375] Step 3:

[1376] The server first calls the Dialogflow API to analyze the user's inquiry. Specifically, it analyzes the input text and voice data and obtains information to generate a corresponding response. The input data is sent to the Dialogflow API as an analysis request, and an appropriate response is returned as the analysis result.

[1377] Step 4:

[1378] At the same time, the server uses TensorFlow to analyze the user's emotional state from the input voice and text data. Specifically, it uses an emotion recognition model to identify the user's emotions (e.g., anger, confusion, joy, etc.). Based on this, emotional state data is generated.

[1379] Step 5:

[1380] The server integrates the response obtained from Dialogflow with the emotional state data obtained from TensorFlow. This allows the response to be adjusted according to the user's emotional state. For example, if the user is confused, a more polite and detailed explanation is added. The input data is integrated as an analysis result and output as an adjusted response.

[1381] Step 6:

[1382] The server sends the final response to the terminal, which then displays the received response to the user, either in text format or as audio. The user can then obtain the adjusted response.

[1383] Step 7:

[1384] If necessary, the server generates a data flow diagram using Mermaid notation or Matplotlib and displays it visually to the user. Input data is sent to the server as a data analysis request, and the output is a visual data flow diagram, which the user can use to intuitively understand the data flow and dependencies.

[1385] In this way, each processing step analyzes and responds to user input, and further adjusts according to emotional state, resulting in more effective and friendly data management and user support.

[1386] 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.

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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).

[1393] 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.

[1394] 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."

[1395] 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.

[1396] 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).

[1397] 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.

[1398] 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.

[1399] 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.

[1400] 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.

[1401] 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.

[1402] 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.

[1403] 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.

[1404] 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.

[1405] 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.

[1406] 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.

[1407] The following is further disclosed regarding the above embodiment.

[1408] (Claim 1)

[1409] a means for analyzing data flows using interactive artificial intelligence;

[1410] A means for inputting data processing programs and queries used in the enterprise into the interactive artificial intelligence and identifying data dependencies;

[1411] means for visually displaying the identified data dependencies;

[1412] means for interactively responding to anomaly detection and inquiries based on the visually displayed data flow;

[1413] A system including:

[1414] (Claim 2)

[1415] 2. The system according to claim 1, wherein the means for visually displaying the data flow uses Mermaid notation or other graph drawing tools.

[1416] (Claim 3)

[1417] The system according to claim 1, characterized in that the interactive artificial intelligence extracts data relationships based on program analysis and outputs the results in JSON format.

[1418] "Example 1"

[1419] (Claim 1)

[1420] a means for analyzing data flows using interactive artificial intelligence;

[1421] A means for inputting data processing programs and queries used in the enterprise into the interactive artificial intelligence and identifying data dependencies;

[1422] means for transmitting the program or query from a terminal to a server;

[1423] means for passing the received code to an interactive artificial intelligence by the server;

[1424] means for the interactive artificial intelligence to analyze the code and return the results to a server;

[1425] means for visually displaying the identified data dependencies;

[1426] means for interactively responding to anomaly detection and inquiries based on the visually displayed data flow;

[1427] means for notifying the interactive artificial intelligence in real time when an abnormality occurs and returning the analysis result to the server;

[1428] means for the user to query the interactive artificial intelligence through a web interface;

[1429] A system including:

[1430] (Claim 2)

[1431] 10. The system of claim 1, wherein the means for visually displaying the data flow uses a graph drawing notation or other visualization tool.

[1432] (Claim 3)

[1433] The system according to claim 1, characterized in that the interactive artificial intelligence extracts data relationships based on program analysis and outputs the results in a data format.

[1434] "Application Example 1"

[1435] (Claim 1)

[1436] a means for analyzing data flows using interactive artificial intelligence;

[1437] A means for inputting data processing programs and queries used in the enterprise into the interactive artificial intelligence and identifying data dependencies;

[1438] a means for visually displaying the data dependencies together with real-time data from various sensors within the logistics facility;

[1439] means for interactively responding to real-time anomaly detection and inquiries based on the visually displayed data flow;

[1440] A means to notify the user when an abnormality is detected, analyze the cause, and automatically generate work instructions;

[1441] A system including:

[1442] (Claim 2)

[1443] 2. The system according to claim 1, wherein the means for visually displaying the data flow uses a graph drawing tool or notation.

[1444] (Claim 3)

[1445] 2. The system according to claim 1, wherein the interactive artificial intelligence extracts data relationships based on program analysis and outputs the results in a structured data format.

[1446] "Example 2: Combining Emotion Engines"

[1447] (Claim 1)

[1448] a means for analyzing data flows using interactive artificial intelligence;

[1449] A means for inputting data processing programs and queries used within the organization into the interactive artificial intelligence and identifying data dependencies;

[1450] a means for visually displaying the identified data dependencies;

[1451] A means of detecting anomalies and responding to queries interactively based on the visually displayed data flow;

[1452] A means for analyzing the emotional state of the user and adjusting the response content of the conversational artificial intelligence;

[1453] A system including:

[1454] (Claim 2)

[1455] 2. The system according to claim 1, wherein the means for visually displaying the data flow uses a graph drawing tool.

[1456] (Claim 3)

[1457] The system according to claim 1, characterized in that the interactive artificial intelligence extracts data relationships based on program analysis and outputs the results in a structured data format.

[1458] "Application example 2 when combining emotion engines"

[1459] (Claim 1)

[1460] a means for analyzing data flows using interactive artificial intelligence;

[1461] A means for inputting data processing programs and queries used in the enterprise into the interactive artificial intelligence and identifying data dependencies;

[1462] means for visually displaying the identified data dependencies;

[1463] means for interactively responding to anomaly detection and inquiries based on the visually displayed data flow;

[1464] means for using an emotion engine to analyze the user's emotional state and adjust responses;

[1465] A system including:

[1466] (Claim 2)

[1467] 2. The system according to claim 1, wherein the means for visually displaying the data flow uses a graph drawing tool.

[1468] (Claim 3)

[1469] 2. The system according to claim 1, wherein the interactive artificial intelligence extracts data relationships based on program analysis and outputs the results in a structured data format. [Explanation of symbols]

[1470] 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 for analyzing data flows using interactive artificial intelligence; A means for inputting data processing programs and queries used in the enterprise into the interactive artificial intelligence and identifying data dependencies; means for visually displaying the identified data dependencies; means for interactively responding to anomaly detection and inquiries based on the visually displayed data flow; A system including:

2. 2. The system of claim 1, wherein the means for visually displaying the data flow uses Mermaid notation or other graph drawing tools.

3. The system according to claim 1, wherein the interactive artificial intelligence extracts data relationships based on program analysis and outputs the results in JSON format.

Images