System

Abstract

A system is provided.SOLUTION: A system comprising: means for connecting to different data storage destinations and analyzing metadata of each data storage destination; means for automatically collecting necessary data based on the analyzed metadata; means for integrating and shaping the collected data into a standardized format; means for allowing a user to give an instruction to correct or add data through a chat interface; and means for generating an output based on the shaped data.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 have data stored in a wide variety of formats and locations, but collecting this data and converting it into a form suitable for analysis and reporting requires a significant amount of time and effort. This hinders efficient business operations and prevents the effective use of data. Conventional methods require a wide range of manual tasks, such as collecting, integrating, and formatting data, and each step is prone to error and takes time, so a solution is needed. [Means for solving the problem]

[0005] The present invention is a system that includes a means for connecting to different data storage destinations and analyzing the metadata of each data storage destination, a means for automatically collecting necessary data based on the analyzed metadata, a means for integrating the collected data and formatting it into a standardized format, a means for users to give instructions for data corrections and additions through a chat interface, and a means for generating output based on the formatted data. This configuration streamlines the entire process from automatic data collection to output generation, allowing users to focus on data analysis and decision-making. Furthermore, the ability to check data and give instructions in real time enables quick and flexible responses and reduces the labor required for document creation.

[0006] "Data destination" refers to the physical or virtual storage system where data is stored, including, for example, organizational folders, cloud storage, and data warehouses (DWHs).

[0007] "Metadata" is data that indicates information about the data itself, such as the file extension, creation date, size, database table schema, and column information.

[0008] "Analysis" refers to the process of examining data to understand its structure and properties, such as analyzing data formats and understanding table schemas.

[0009] "Collection" refers to the act of retrieving and gathering the required data from a particular data store, including performing a data query or downloading a file.

[0010] "Integration" refers to the process of bringing together data collected from different formats and stores into one standardized format.

[0011] "Format" refers to the process of processing the integrated data to make it suitable for a specific purpose or presentation, such as aggregating, filtering, or formatting the data.

[0012] "User" refers to the person who operates the system and collects, analyzes, synthesizes, formats data, and generates output.

[0013] "Chat interface" refers to a text-based communication method for users to interact with the system, allowing users to check data and provide instructions in real time.

[0014] "Output" refers to the final reports, dashboards, graphs, and other information generated based on the formatted data.

[0015] "Parallel processing" refers to the technology of executing multiple processes simultaneously, which makes data collection and analysis more efficient. [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] This invention is a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, thereby significantly reducing the time and effort required to collect and format the data.

[0038] System Configuration

[0039] The system mainly consists of the following elements:

[0040] 1. Means of connection to the data storage destination

[0041] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[0042] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[0043] 2. Metadata Analysis Methods

[0044] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[0045] 3. Automatic collection of necessary data

[0046] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[0047] 4. Data integration methods

[0048] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[0049] 5. Data Formatting Methods

[0050] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[0051] 6. Chat Interface

[0052] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[0053] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[0054] 7. Output Generation Methods

[0055] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[0056] Specific examples

[0057] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[0058] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[0059] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[0060] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[0061] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[0062] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[0063] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[0064] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[0065] 8. The device presents the generated report to the user, offering options to download or share it.

[0066] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, enabling users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[0067] The processing flow will be explained below.

[0068] Step 1:

[0069] The user inputs information about the data storage destination to be used in the chat interface on the device (for example, the URL of the cloud storage, the API key, the connection information of the DWH, etc.) and provides it to the system.

[0070] Step 2:

[0071] The server establishes a connection to each data store based on the provided information, authenticates using an API or database client, and maintains the connection.

[0072] Step 3:

[0073] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[0074] Step 4:

[0075] The user instructs the chat interface on the device to "collect specific data and create a report."

[0076] Step 5:

[0077] The server identifies data that matches the conditions specified by the user based on the analyzed metadata, for example, files and table entries that match the condition "sales data for this month."

[0078] Step 6:

[0079] The server efficiently retrieves the data to be collected using parallel processing techniques (multi-threading or multi-processing) and aggregates the data.

[0080] Step 7:

[0081] The server aggregates the collected data into a standardized format (e.g., a data frame), resolving inconsistencies and missing values ​​between different formats to create a consistent dataset.

[0082] Step 8:

[0083] The server then formats the integrated data into a user-specified format. For example, it can aggregate sales data by day, month, or category and format it in a table or graph format.

[0084] Step 9:

[0085] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[0086] Step 10:

[0087] The user can issue instructions to correct or add data through a chat interface, such as "I want the data for a specific period to be changed and re-aggregated."

[0088] Step 11:

[0089] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[0090] Step 12:

[0091] The server generates the final reports and dashboards based on the corrected data, which can be PDF reports, Excel sheets, or web-based dashboards.

[0092] Step 13:

[0093] The device presents the generated report to the user and offers options to download or share it.

[0094] Step 14:

[0095] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[0096] Example 1

[0097] 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."

[0098] Many companies and organizations are faced with the need to integrate, analyze, and utilize data distributed across different data storage locations. Traditionally, manually collecting data and integrating and formatting it has required time and effort, and there is a high risk of manual error. Therefore, there is a need for a method to process data efficiently and accurately and generate output quickly. Furthermore, a user-friendly interface is required to correct data and provide additional instructions in real time, and a concrete solution for this is needed.

[0099] 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.

[0100] In this invention, the server includes means for connecting to different data storage locations and analyzing metadata from each data storage location, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for issuing instructions for data correction or addition through a user interface on a terminal, means for generating a report or dashboard based on the formatted data, means for making the generated report or dashboard downloadable or sharable, means for collecting data in parallel based on the analyzed metadata, means for accepting data processing instructions based on natural language prompts through a chat interface on the terminal using a generative AI model, and means for inputting and confirming data on the terminal in real time. This allows users to efficiently and accurately integrate and format data and quickly generate output. Furthermore, the ability to check and correct data in real time enables flexible and accurate data utilization.

[0101] A "data destination" is a storage service or database where different data is stored.

[0102] "Metadata" refers to additional information about data, including information about the data's structure, format, data type, and so on.

[0103] "Automatic collection means" refers to a system that uses a program to continuously and efficiently collect the necessary data based on analyzed metadata and in accordance with conditions specified by the user.

[0104] "Means of integration and standardization" refers to the process of converting data of different formats and structures into a single common format and unifying it.

[0105] A "user interface" refers to a screen or operation panel that allows a user to interact with and operate a system.

[0106] A "report" or "dashboard" is a document or screen that visually displays analytical results or information created based on collected and formatted data.

[0107] "Real-time" is a term that refers to a state in which processing results are obtained almost immediately after data is input.

[0108] "Parallel processing" refers to the technology of simultaneously executing multiple data processing tasks to efficiently collect and format data.

[0109] A "generative AI model" is an algorithm that has been trained to automatically analyze and process data using AI technology.

[0110] A "prompt sentence" is an instruction or question entered by a user in natural language.

[0111] This invention is a system that collects data from different data storage locations, integrates and formats the data based on user instructions, and generates output. This system is composed of multiple hardware and software elements.

[0112] Basic system configuration

[0113] 1. Means of connection to the data storage destination

[0114] The user inputs information about the data storage destination (such as an API key, a connection URL, and query conditions) through a user interface on the terminal. Any personal computer, smartphone, or tablet can be used as the terminal.

[0115] The server connects to the specified data storage location (such as a cloud storage service or data warehouse) based on the information provided by the user. The server software uses a programming language such as Python or Java, and connects to the API endpoint using an HTTP request and performs authentication.

[0116] 2. Metadata Analysis Methods

[0117] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format (for example, column information for JSON or CSV files). It obtains and analyzes the metadata using Python's Pandas library, etc.

[0118] 3. Automatic collection of necessary data

[0119] The server automatically collects the necessary data according to the conditions specified by the user based on the analyzed metadata, and efficiently retrieves the data using Python parallel processing libraries (such as multiprocessing and asyncio).

[0120] 4. Data integration methods

[0121] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data from different file formats and database tables into a single data frame.

[0122] 5. Data Formatting Methods

[0123] The server then formats the aggregated data according to user requirements, including categorical aggregations and conversions to specific formats, using the Python Pandas and NumPy libraries.

[0124] 6. Chat Interface

[0125] The terminal provides a chat interface that allows users to check data and input instructions in real time. This interface is implemented using a web application framework (e.g., Flask or Django).

[0126] Users can modify data or provide additional instructions through chat, including instructions in natural language.

[0127] 7. Output Generation Methods

[0128] The server generates reports and dashboards based on the formatted data using Python's Matplotlib and Seaborn libraries, and outputs PDF and Excel files.

[0129] 8. Real-time processing methods

[0130] The device provides real-time data entry and validation, allowing users to receive immediate feedback and confirm that their data reflects their intended purpose.

[0131] Specific examples

[0132] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[0133] 1. The user requests, via the chat interface on their device, that they "collect quarterly sales data and create a report." The prompt reads, "Collect quarterly sales data and create a PDF report. The data should be for the first quarter of 2023 and include breakdowns by sales category."

[0134] 2. The server connects to the cloud storage (e.g., Amazon S3) or data warehouse (e.g., Google BigQuery) where the sales data is stored and analyzes the metadata of the files and tables.

[0135] 3. The server collects data for the specified quarter from each data storage location and efficiently ingests the data using parallel processing using Python's asyncio.

[0136] 4. The server uses Python's Pandas library to convert the collected data into a unified data frame and format it into quarterly segments.

[0137] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[0138] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[0139] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[0140] 8. The device presents the generated report to the user, offering options to download or share it.

[0141] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, allowing users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Step 1:

[0144] The user logs in to the user interface on the device and enters information about the data storage destination (such as an API key, connection URL, query conditions, etc.). This input information is sent to the server.

[0145] Input: API key for data storage destination, connection URL, query conditions

[0146] Output: Request sent to server

[0147] Specific behavior:

[0148] A user types into the chat interface, "Please aggregate our quarterly sales data and create a PDF report," along with providing details of where the data will be stored (e.g., Google BigQuery API key XYZ123).

[0149] Step 2:

[0150] The server connects to the specified data store based on the information provided by the user, connects to the API endpoint using an HTTP request, and performs authentication.

[0151] Input: User-provided data storage location information

[0152] Output: Authentication token, connection status

[0153] Specific behavior:

[0154] The server sends an authentication request to the Google BigQuery API, receives an authentication token in response, checks the connection status, and notifies the user.

[0155] Step 3:

[0156] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format using the Python Pandas library.

[0157] Input: Authentication token for data storage destination

[0158] Output: Metadata (column names, data types, etc.)

[0159] Specific behavior:

[0160] The server retrieves table information from BigQuery and lists the column names and data types. For example, it retrieves column information for the "sales" table.

[0161] Step 4:

[0162] The server automatically collects the necessary data according to the conditions (query conditions) specified by the user based on the analyzed metadata, and uses Python's asyncio to efficiently retrieve data through parallel processing.

[0163] Input: User query criteria, metadata

[0164] Output: Collected dataset

[0165] Specific behavior:

[0166] The server sends a query such as "SELECT FROM sales WHERE quarter='Q1'" to BigQuery and receives the results. Data is collected from multiple tables in parallel.

[0167] Step 5:

[0168] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data of different formats and structures into a single data frame.

[0169] Input: Collected dataset

[0170] Output: Unified data frame

[0171] Specific behavior:

[0172] The server converts the data from each table into a Pandas data frame, and then combines multiple data frames into a single dataset. For example, merging sales data with customer data.

[0173] Step 6:

[0174] The server then formats the integrated data according to user requests, such as by aggregating data by category or converting it into a specific format, using the Python Pandas and NumPy libraries.

[0175] Input: unified data frame

[0176] Output: Formatted data

[0177] Specific behavior:

[0178] The server aggregates the quarterly sales data using Pandas and adds a new calculated column. For example, a "total_sales" column is created to calculate the total sales for each quarter.

[0179] Step 7:

[0180] The terminal displays the formatted data as an intermediate result to the user and asks for confirmation.

[0181] Input: Formatted data

[0182] Output: Intermediate results that are displayed to the user

[0183] Specific behavior:

[0184] A data summary or sample of the intermediate results is displayed on the chat interface, along with a message asking, "Is this data okay?"

[0185] Step 8:

[0186] The user can modify or add data through the chat interface, using natural language prompts.

[0187] Input: User instructions

[0188] Output: Corrected or added data

[0189] Specific behavior:

[0190] The user enters instructions in the chat window, such as "Please also include column X in the calculation," and the server reprocesses the data based on those instructions.

[0191] Step 9:

[0192] The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[0193] Input: Corrected formatted data

[0194] Output: Final output (PDF or Excel)

[0195] Specific behavior:

[0196] The server-generated reports are visualized using Matplotlib and Seaborn, and an Excel file is created using Pandas' to_excel method.

[0197] Step 10:

[0198] The device presents the generated output to the user, offering options to download or share it.

[0199] Input: Final Output

[0200] Output: Download link or sharing option for the output

[0201] Specific behavior:

[0202] Display a link to the generated PDF report in the chat window and provide a "Download Report" button.

[0203] (Application example 1)

[0204] 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."

[0205] Modern logistics centers have a variety of data sources (inventory management systems, delivery management systems, order management systems, etc.), and there is a need to manage and operate each data in an integrated manner. However, manually collecting, analyzing, integrating, and displaying data from different sources in various output formats requires a great deal of time and effort. In addition, it is difficult to check data and respond to instructions in real time, making it difficult to achieve efficient logistics management.

[0206] 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.

[0207] In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata from each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for users to enter instructions for data corrections and additions via a chat interface on their smartphones, and means for generating output in real time based on the formatted data and displaying it in dashboard format, thereby enabling data integration from different data sources and real-time logistics management.

[0208] "Different data storage locations" refers to multiple locations where data is stored, such as cloud storage or databases.

[0209] "Metadata" refers to data that includes information about the data itself, such as the format, structure, and attribute information of the data.

[0210] "Analysis" refers to the process of deconstructing and interpreting collected metadata and other data to understand its structure and content.

[0211] "Automatic collection" refers to the act of collecting data by a system without human intervention.

[0212] "Integration" means bringing together different collected data into one standardized format.

[0213] "Formatting into a standardized format" means converting various data formats and structures into a unified format.

[0214] A "smartphone" refers to a multi-function mobile phone, a device capable of wireless communication and internet access.

[0215] A "chat interface" is an interface that allows users to interact with the system to check data, give instructions, etc.

[0216] "Instructions for correction or addition" refers to the act of a user issuing instructions to the system to change existing data or add new data.

[0217] "Real-time" refers to a situation in which user actions are reflected immediately without any time delay.

[0218] The "dashboard format" is a format in which data is visually organized and displayed so that the current situation can be grasped at a glance.

[0219] "Output" refers to the reports and data visualizations that are generated based on the formatted data.

[0220] MODE FOR CARRYING OUT THE INVENTION

[0221] This invention is a system that efficiently collects, integrates, and formats data from different data sources in logistics centers, allowing logistics managers to check and modify data in real time using their smartphones and make decisions quickly.

[0222] System Configuration

[0223] The system consists of the following elements:

[0224] 1. Server

[0225] The server receives data storage information provided by the user and connects to different data storage locations such as cloud storage or databases. For example, the user can enter an API key or connection URL, and the server uses that information to authenticate with the data storage location. The connection is established using the Python requests library.

[0226] 2. Metadata Analysis

[0227] The server analyzes the metadata of each data storage location to understand the data structure and format. Specifically, it uses the Python pandas library to retrieve and analyze the metadata.

[0228] 3. Automatic data collection

[0229] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata.To efficiently collect data using parallel processing techniques, the Python multiprocessing library is used.

[0230] 4. Data Integration

[0231] The server consolidates the collected data into a standardized format and converts data from different formats (e.g., CSV, JSON) into a single data frame. Again, this consolidation is done using the pandas library.

[0232] 5. Data Formatting

[0233] The server formats the integrated data into a format specified by the user, generating aggregated data for each category, for example.

[0234] 6. Generating Output

[0235] Based on the formatted data, the server generates dashboard-style output and provides it to users in real time. The dashboard is created using the Python matplotlib library.

[0236] 7. User Interface

[0237] The device (smartphone) provides a chat interface to the user, allowing them to check data and input instructions. The front end is implemented using React Native and the back end is implemented using Flask.

[0238] Program processing

[0239] Next, the details of the processing by the hardware and software of each element will be described.

[0240] Connecting and collecting data: The server uses the Python requests library to connect to each data store based on the API key and connection URL entered by the user. It then analyzes the metadata of the data store using the pandas library and automatically collects the required data.

[0241] Example: Enter the API key and URL of the inventory management system of the distribution center, and the server will connect based on that.

[0242] Example prompt sentence:

[0243] "Please enter the API key for your inventory management system."

[0244] Please enter the URL to connect to.

[0245] Data integration and shaping: The collected data is integrated into a single data frame using the pandas library, and then the data is shaped and converted into the required format based on the user's instructions.

[0246] Example: Taking inventory and order data in different formats and transforming it into a unified data frame.

[0247] Example prompt sentence:

[0248] "Standardize the format of your data."

[0249] "Generate aggregate data by category."

[0250] Output Generation: Based on the consolidated and formatted data, the server generates a dashboard using Python's matplotlib library, which is displayed in real time through the user interface.

[0251] Example: Generate a dashboard that visualizes the current inventory status based on formatted inventory and order data.

[0252] Example prompt sentence:

[0253] "Generate a dashboard based on inventory data."

[0254] User interface: The device (smartphone) is equipped with a chat interface developed with React Native, through which users can correct or add data in real time.Flask is used as the backend to ensure that data is updated in real time.

[0255] Example: A user issues a command such as "Please update the latest inventory information," and the server formats the data accordingly and displays an updated dashboard.

[0256] Example prompt sentence:

[0257] View the latest inventory information

[0258] Please update the delivery status

[0259] The system streamlines data collection, integration, formatting and output generation, and enables real-time data verification and correction, facilitating fast and accurate data management and decision-making in logistics centers.

[0260] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0261] Step 1:

[0262] When a user uses a device (smartphone) to enter the API key and connection URL of the data storage destination, the data storage destination information is sent to the server. Based on the entered data storage destination information, the server uses the Python requests library to establish a connection to each data storage destination. Specifically, by including the API key and URL in the request, authentication to the cloud storage or database is performed. This allows the server to access the data from each data storage destination.

[0263] Input: API key for data storage destination, connection URL

[0264] Output: Establish connection to each data storage destination

[0265] Step 2:

[0266] The server retrieves metadata from the connected data store and analyzes it using the Python pandas library. The metadata includes information about the data format, structure, and attributes, and analyzing this information provides an overall understanding of the data. Specifically, the server reads the file using the pandas read_json or read_csv method.

[0267] Input: Metadata for each data storage location

[0268] Output: Parsed metadata

[0269] Step 3:

[0270] The server automatically collects the necessary data based on the analyzed metadata. Here, the Python multiprocessing library is used to efficiently collect data using parallel processing techniques. Specifically, multiple processes are launched, and each process collects data from a different data storage location. This improves the speed at which data is collected.

[0271] Input: Parsed metadata

[0272] Output: Required data collected

[0273] Step 4:

[0274] The server consolidates the collected data and formats it into a standardized format. Because data collected from multiple data storage locations may have different formats and structures, it combines the data into a single data frame using the Python pandas library. Specifically, the data is consolidated using the pandas concat and merge methods.

[0275] Input: Required data collected

[0276] Output: Unified data frame

[0277] Step 5:

[0278] Users can use their smartphones to modify or add data via a chat interface. The chat interface is based on React Native, and the user's input is sent to the server. For example, a user might enter a command such as "Please update the latest inventory information."

[0279] Input: Corrections and additional instructions from the user

[0280] Output: Instructions sent to the server

[0281] Step 6:

[0282] The server modifies or adds data based on user instructions. It uses the Python pandas library to reprocess data according to the instructions. For example, if a user requests that the inventory quantity of a specific product be updated, the server searches for the relevant data and performs the update process.

[0283] Input: User corrections and additional instructions

[0284] Output: Corrected and added data

[0285] Step 7:

[0286] The server generates dashboard-style output based on the formatted data. It uses the Python matplotlib library to visualize the data and display it in a dashboard format. Specifically, it generates graphs and charts and creates a visual representation of them.

[0287] Input: Corrected and added data

[0288] Output: Dashboard-style output

[0289] Step 8:

[0290] The device (smartphone) provides the generated dashboard to the user in real time, allowing the user to view it and provide additional instructions as needed. The front end, implemented using React Native, immediately reflects data updates from the server.

[0291] Input: Dashboard output

[0292] Output: The dashboard as seen by the user

[0293] The above processing steps make data management at logistics centers more efficient and enable real-time data checking and decision-making.

[0294] 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.

[0295] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. This not only improves the efficiency of data collection, formatting, and output, but also enables more appropriate responses by taking the user's emotional state into consideration.

[0296] System Configuration

[0297] The system mainly consists of the following elements:

[0298] 1. Means of connection to the data storage destination

[0299] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[0300] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[0301] 2. Metadata Analysis Methods

[0302] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[0303] 3. Automatic collection of necessary data

[0304] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[0305] 4. Data integration methods

[0306] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[0307] 5. Data Formatting Methods

[0308] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[0309] 6. Chat Interface

[0310] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[0311] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[0312] 7. Emotion Engine

[0313] The device is equipped with an emotion engine that performs emotion analysis based on user input and behavior, such as text context, input speed, and typing intensity, to determine the user's emotional state.

[0314] The server automatically adjusts data collection and processing procedures based on the emotional data obtained by the emotion engine, including simplifying operations if the user is feeling stressed.

[0315] 8. Output Generation Methods

[0316] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[0317] Specific examples

[0318] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[0319] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[0320] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[0321] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[0322] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[0323] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[0324] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[0325] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[0326] 8. The device presents the generated report to the user, offering options to download or share it.

[0327] 9. The device will analyze the user's emotional state in real time through an emotion engine, and will automatically adjust operations and data presentation methods if the user is feeling stressed or dissatisfied.

[0328] 10. The server performs flexible data processing based on the results of emotion analysis to improve the user experience.

[0329] This system significantly improves the efficiency of the previously manual process from data collection to output generation, enabling users to analyze data and make decisions more quickly.In addition, the introduction of an emotion engine enables flexible and optimal data manipulation that takes into account the user's emotional state.

[0330] The processing flow will be explained below.

[0331] Step 1:

[0332] The user uses the chat interface on the device to input information about the data storage destination (e.g., cloud storage URL, API key, DWH connection information, etc.) and provides it to the system.

[0333] Step 2:

[0334] The server establishes a connection to each data store based on the provided data store information, authenticates using an API or database client, and completes the connection.

[0335] Step 3:

[0336] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[0337] Step 4:

[0338] The user issues a command via the chat interface on the device saying, "I want you to compile quarterly sales data and create a report."

[0339] Step 5:

[0340] The server uses the parsed metadata to identify the required data based on user-specified criteria, such as files and table entries that match the criteria "sales data for the first quarter of last year."

[0341] Step 6:

[0342] The server efficiently retrieves the data to be collected using parallel processing techniques (for example, multi-threading or multi-processing) and aggregates the data.

[0343] Step 7:

[0344] The server aggregates the collected data into a standardized format (e.g., data frames or statistical data), and converts data from different formats into a consistent form.

[0345] Step 8:

[0346] The server then formats the integrated data into a user-specified format, for example, by aggregating the data by quarter and converting it into a table or graph format.

[0347] Step 9:

[0348] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[0349] Step 10:

[0350] Through the chat interface, users can give instructions to correct or add necessary data, such as "Please change the data for a specific period and recalculate it."

[0351] Step 11:

[0352] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[0353] Step 12:

[0354] The device runs an emotion engine that performs emotion analysis based on the user's input and behavior, for example, by determining the user's emotional state from input speed and context analysis.

[0355] Step 13:

[0356] The server automatically adjusts data collection and processing procedures based on the analysis results of the emotion engine. For example, if the user is feeling stressed, it will simplify the operation procedures.

[0357] Step 14:

[0358] The server generates reports and dashboards based on the final formatted data, which can include PDF reports, Excel sheets, and web-based dashboards.

[0359] Step 15:

[0360] The device displays the generated report to the user and provides options for downloading and sharing.

[0361] Step 16:

[0362] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[0363] These are the specific processing steps of a system incorporating the emotion engine of the present invention. This system streamlines the process from data collection to output generation, and also enables flexible responses tailored to the user's emotional state.

[0364] Example 2

[0365] 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."

[0366] In conventional data collection and processing systems, collecting data from different data storage locations and integrating the collected data takes time and effort, making it difficult for users to analyze data efficiently. Furthermore, data manipulation that ignores the user's emotional state causes operational complexity and stress, ultimately resulting in a poor user experience. This has led to a demand for more efficient data processing and improved user experience.

[0367] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata of each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for a user to issue instructions for data correction or addition through a chat interface, means for generating output based on the formatted data, means for adjusting data processing procedures by performing sentiment analysis on user inputs and actions, and means for simplifying user operations based on the sentiment analysis results. This enables efficient data collection and formatting, as well as flexible data manipulation that takes into account the user's emotional state and an improved user experience.

[0368] A "data destination" is a physical or virtual location where data is stored, such as cloud storage, a database, or a data warehouse.

[0369] "Metadata" refers to information about the attributes and structure of data, including the type of data, format, size, creation date, and so on.

[0370] "Analyzing" refers to breaking down data and metadata and converting them into an understandable form, thereby understanding the structure and content of the data.

[0371] "Collect" refers to extracting data based on specified conditions and gathering it in one place.

[0372] "Integrate" refers to combining multiple data sets into one standardized format.

[0373] "Format" refers to converting collected and integrated data into a specific form or format, and processing the data in accordance with the user's request.

[0374] "Chat interface" refers to an interactive user interface that allows a user to issue text-based instructions to a system and receive responses from the system.

[0375] "Output" refers to the results generated based on formatted data, including reports, dashboards, graphs, PDF files, etc.

[0376] "Emotion analysis" refers to identifying and analyzing a user's emotional state based on their input and behavior.

[0377] "Tuning" refers to changing the system's behavior based on the information obtained to achieve optimal results.

[0378] "Simplifying operations" refers to techniques for simplifying the process of users collecting, formatting, checking, and correcting data, thereby reducing the burden on users.

[0379] The present invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. A specific embodiment of the present invention will be described below.

[0380] Hardware and Software Use

[0381] This system mainly consists of a server and a terminal. The server is located on a cloud infrastructure, and the terminal is a personal computer or mobile device operated by a user. The server uses the following main software components:

[0382] Data Collection and Analysis: Data collection and analysis will be performed using Python programs and the Pandas library.

[0383] Concurrency: Use Python's multithreading library to collect data efficiently.

[0384] Data integration and shaping: Use Pandas to standardize data in different formats and shape it as needed.

[0385] Output generation: Creating reports and dashboards using Matplotlib or other data visualization libraries.

[0386] The device uses the following main software components:

[0387] Chat interface: Provides a front-end application using React.js to receive user instructions in real time.

[0388] Sentiment analysis: Analyze the user's input text using an NLP library (e.g., NLTK or SpaCy).

[0389] Specific examples

[0390] For example, a specific flow will be described in which a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report."

[0391] 1. The user instructs the chat interface on their device to "aggregate quarterly sales data and create a report."

[0392] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[0393] 3. The server collects the data for the specified quarter using parallel processing and integrates it into a Pandas data frame.

[0394] 4. The server groups the consolidated data by quarter and performs aggregations.

[0395] 5. The terminal displays a preview of the intermediate results in the chat interface and asks for the user's confirmation.

[0396] 6. The user communicates data corrections and additions to the server through the chat interface.

[0397] 7. The server reprocesses the data based on the correction instructions and generates a PDF report as the final output.

[0398] 8. The device will display a download link for the generated PDF report in the chat interface.

[0399] 9. The device uses an emotion analysis engine to analyze user input and simplify operations if the user is feeling stressed.

[0400] 10. The server adjusts the priority of data processing based on the emotion data to optimize the user experience.

[0401] Specific examples of prompts are as follows:

[0402] "I want you to compile quarterly sales data and create a report."

[0403] In this way, the present invention not only improves the efficiency of data collection and shaping, but also enables flexible data manipulation that takes into account the emotional state of the user.

[0404] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0405] Step 1:

[0406] The user inputs the command "I want you to compile the sales data for each quarter and create a report" into the chat interface on the device. The input data becomes "I want you to compile the sales data for each quarter and create a report." Based on this input, the next data collection step is initiated.

[0407] Step 2:

[0408] The server connects to the cloud storage (e.g., AWS S3) or data warehouse where the sales data is stored and analyzes the metadata of the files and tables. The input data is the authentication information for the data storage destination (API key, URL, etc.) and the structure information of the storage destination. By analyzing the metadata, the structure and format of the data are understood and the information necessary for the next data collection is obtained.

[0409] Step 3:

[0410] The server efficiently collects data for the specified quarter from each data repository using parallel processing based on the parsed metadata. The input data is the metadata information and quarter specification, and the output data is the collected raw sales data. Parallel processing speeds up data collection, ingesting data from multiple API endpoints simultaneously.

[0411] Step 4:

[0412] The server consolidates the collected data into a standardized format. Specifically, it converts different file formats (e.g., CSV, JSON) into a data frame using Pandas. The input data is the collected raw data, and the output data is the consolidated data frame. This allows data from different sources to be converted into a consistent format.

[0413] Step 5:

[0414] The server groups the consolidated data by quarter and performs the necessary aggregation operations to reshape it. Specifically, it uses the grouping and aggregation functions of Pandas. The input data is a consolidated data frame, and the output data is data reshaped by quarter. This allows for efficient analysis of data for a specific period.

[0415] Step 6:

[0416] The terminal displays the intermediate results of the formatted data on the chat interface and requests user confirmation. The displayed information includes a preview of the quarterly summary results. The input data is the formatted data, and the output data is a data preview displayed to the user for confirmation.

[0417] Step 7:

[0418] The user sends instructions to the server via the chat interface to correct or add data. For example, the user might say, "Please correct the data for the second quarter." The input data is the user's correction instruction, and the output data is the correction instruction.

[0419] Step 8:

[0420] The server reprocesses the data in response to the user's correction instructions. Specifically, it uses Pandas to correct the data frame and perform recalculation. The input data is the correction instructions and the data to be corrected, and the output data is the corrected data frame.

[0421] Step 9:

[0422] The server generates the quarterly sales report as the final output and outputs it in PDF or other specified format. Specifically, it generates a graph from the data frame using Matplotlib and embeds it in a PDF. The input data is the modified data frame, and the output data is the final report file.

[0423] Step 10:

[0424] The terminal displays a download link for the generated PDF report on the chat interface and presents it to the user. The input data is the generated report file, and the output data is the download link.

[0425] Step 11:

[0426] The device uses an emotion analysis engine to analyze the user's input and simplifies the operation if the user is feeling stressed or dissatisfied. Specifically, it performs text analysis and simplifies the next step based on the results. The input data is the user's input text, and the output data is the emotion analysis result.

[0427] Step 12:

[0428] The server modifies the data processing procedures and user interface based on the emotion analysis results, simplifying user operations. The input data is the emotion analysis results, and the output data is the adjusted processing procedures and user interface settings. This process optimizes the user experience and improves work efficiency.

[0429] The above are the specific processing steps and operations of this system.

[0430] (Application example 2)

[0431] 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."

[0432] On modern online shopping sites, it is difficult for users to find the right product for them from the vast number of products available. Furthermore, typical recommendation systems are based on the user's recent behavior and purchase history, and are unable to suggest products that take into account the user's emotional state. Furthermore, data collection, formatting, and output generation are often done manually, which can often be perceived as inefficient. To solve these problems, a data processing system that also takes into account the user's emotional state is needed.

[0433] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0434] In this invention, the server includes a means for connecting to different data storage locations and analyzing the metadata of each data storage location, a means for automatically collecting necessary data based on the analyzed metadata, and a means for integrating the collected data and formatting it into a standardized format, which enables product recommendations based on the user's emotional state and efficient data collection, formatting, and output generation.

[0435] "Data storage" refers to the system or storage that stores data stored in different locations.

[0436] "Metadata" is additional data that contains information about data and describes the structure and attributes of the data.

[0437] An "automatic collection means" is a method or device for automatically obtaining necessary data from a designated data storage location without user intervention.

[0438] A "means for converting data into a standardized format" is a method or device for converting data stored in different formats into a single unified format.

[0439] A "chat interface" is an interactive user interface through which a user can enter text and interact with the system.

[0440] An "emotion engine" is software or hardware that analyzes a user's input and actions to determine their emotional state at that time.

[0441] An "output generating means" is a method or device that generates reports or visualizations based on the formatted data.

[0442] A "means for generating product recommendations" is a method or device that suggests suitable products based on the user's emotional state and past data.

[0443] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. Specific embodiments for realizing this system are described below.

[0444] System Configuration

[0445] The system mainly consists of the following elements:

[0446] 1. How to connect to the data storage location:

[0447] The server connects to the data storage destination using information such as an API key and connection URL provided by the user. For example, it authenticates and establishes a connection to different data storage destinations such as cloud storage services and data warehouses.

[0448] 2. Metadata analysis methods:

[0449] The server analyzes the metadata of the connected data storage destination to understand the data structure and format, and identifies the required data based on the analysis results.

[0450] 3. Automated means of collecting required data:

[0451] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[0452] 4. Data integration methods:

[0453] The server consolidates the collected data into a single standardized format, for example by converting data from different file formats into a data frame.

[0454] 5. Data Formatting Methods:

[0455] The server then processes the combined data in a user-specified format, such as by aggregating it by category or converting it into a specific format.

[0456] 6. Chat Interface:

[0457] The terminal provides the user with a chat interface, allowing the user to check data and input instructions in real time. The user can correct data or give additional instructions through the chat.

[0458] 7. Emotion Engine:

[0459] The device is equipped with an emotion engine that performs emotion analysis based on the user's input and behavior. For example, it analyzes the user's emotional state based on the context of the text, input speed, and typing intensity. The server automatically adjusts data collection and formatting procedures based on the emotion data obtained by the emotion engine.

[0460] 8. Output Generation Means:

[0461] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[0462] 9. Product recommendation generation method:

[0463] The server suggests suitable products based on the user's emotional state and past data, utilizing algorithms based on emotion engines and data refinement methods.

[0464] Example

[0465] For example, there is a smartphone application called "Smart Shopping Assistant" for an online shopping site. This application works as follows:

[0466] 1. The user types "I'm looking for soothing products" into the chat interface on their device.

[0467] 2. The server collects data from different product data APIs and parses the metadata to extract the required data.

[0468] 3. The analyzed data is collected in parallel and formatted into a standardized format.

[0469] 4. The emotion engine analyzes the user's input and determines that it is a negative state.

[0470] 5. Based on this emotional data, relaxation goods and aroma products are recommended preferentially.

[0471] 6. Present product recommendations to users through the chat interface and offer purchasing options.

[0472] In this way, it becomes possible to recommend products based on the user's emotional state, as well as to efficiently collect, format, and generate output from data.

[0473] Prompt Sentence Examples

[0474] How are you feeling right now? What products are you looking for?

[0475] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0476] Step 1:

[0477] Connecting to a data storage location

[0478] The server receives the API key and connection URL information provided by the user as input and connects to each data storage destination. Specifically, it authenticates and establishes a connection with different data storage destinations such as cloud storage services and data warehouses. This prepares the server to retrieve the required data from the data storage destination.

[0479] Step 2:

[0480] Metadata analysis

[0481] The server analyzes the metadata of the connected data store, which includes file structure, database schema, data format, etc. It takes the metadata as input and understands the overall structure of the data, which forms the basis for identifying what data is needed.

[0482] Step 3:

[0483] Collection of necessary data

[0484] The server automatically collects the necessary data based on the analyzed metadata. It receives condition settings as input and efficiently collects the necessary data from the data storage location using parallel processing technology. The collected data is converted into a standardized format, allowing data in a unified format to be obtained from diverse data sources.

[0485] Step 4:

[0486] Data integration and formatting

[0487] The server aggregates the collected data and formats it into a standardized format. The input is the raw data collected, and the output is a unified data frame. During this process, the data is aggregated by category and converted into a specific format to ensure consistency.

[0488] Step 5:

[0489] Emotion analysis

[0490] The device performs emotion analysis based on the user's input and behavior. For example, it displays prompts such as "How are you feeling right now? What kind of product are you looking for?" and receives user input. The input is text data, which the emotion engine analyzes and outputs the user's emotional state. This includes analyzing the context of the text and the speed of input.

[0491] Step 6:

[0492] Generate product recommendations

[0493] The server generates product recommendations based on the analysis results of the emotion engine according to the user's emotional state. The input is the results of the emotion analysis and formatted data, and the output is a product list presented to the user. For example, if the user is feeling stressed, relaxation goods and aroma products will be recommended first.

[0494] Step 7:

[0495] Output through the chat interface

[0496] The terminal displays the generated product recommendations to the user through a chat interface. The input is the generated product list, and the output is the display to the user on the terminal. The user can provide further instructions through this interface, and the system will reprocess the data accordingly.

[0497] Step 8:

[0498] Generating the final output

[0499] The server generates the final output and provides it to the user as needed, such as a report or dashboard. The input is the formatted data and additional user instructions, and the output is a PDF report or a web-based dashboard, allowing the user to see the results of the data processing in a tangible way.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] [Second embodiment]

[0504] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0505] 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.

[0506] 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).

[0507] 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.

[0508] 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.

[0509] 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).

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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.

[0514] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0515] 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."

[0516] This invention is a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, thereby significantly reducing the time and effort required to collect and format the data.

[0517] System Configuration

[0518] The system mainly consists of the following elements:

[0519] 1. Means of connection to the data storage destination

[0520] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[0521] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[0522] 2. Metadata Analysis Methods

[0523] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[0524] 3. Automatic collection of necessary data

[0525] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[0526] 4. Data integration methods

[0527] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[0528] 5. Data Formatting Methods

[0529] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[0530] 6. Chat Interface

[0531] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[0532] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[0533] 7. Output Generation Methods

[0534] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[0535] Specific examples

[0536] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[0537] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[0538] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[0539] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[0540] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[0541] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[0542] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[0543] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[0544] 8. The device presents the generated report to the user, offering options to download or share it.

[0545] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, enabling users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[0546] The processing flow will be explained below.

[0547] Step 1:

[0548] The user inputs information about the data storage destination to be used in the chat interface on the device (for example, the URL of the cloud storage, the API key, the connection information of the DWH, etc.) and provides it to the system.

[0549] Step 2:

[0550] The server establishes a connection to each data store based on the provided information, authenticates using an API or database client, and maintains the connection.

[0551] Step 3:

[0552] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[0553] Step 4:

[0554] The user instructs the chat interface on the device to "collect specific data and create a report."

[0555] Step 5:

[0556] The server identifies data that matches the conditions specified by the user based on the analyzed metadata, for example, files and table entries that match the condition "sales data for this month."

[0557] Step 6:

[0558] The server efficiently retrieves the data to be collected using parallel processing techniques (multi-threading or multi-processing) and aggregates the data.

[0559] Step 7:

[0560] The server aggregates the collected data into a standardized format (e.g., a data frame), resolving inconsistencies and missing values ​​between different formats to create a consistent dataset.

[0561] Step 8:

[0562] The server then formats the integrated data into a user-specified format. For example, it can aggregate sales data by day, month, or category and format it in a table or graph format.

[0563] Step 9:

[0564] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[0565] Step 10:

[0566] The user can issue instructions to correct or add data through a chat interface, such as "I want the data for a specific period to be changed and re-aggregated."

[0567] Step 11:

[0568] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[0569] Step 12:

[0570] The server generates the final reports and dashboards based on the corrected data, which can be PDF reports, Excel sheets, or web-based dashboards.

[0571] Step 13:

[0572] The device presents the generated report to the user and offers options to download or share it.

[0573] Step 14:

[0574] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[0575] Example 1

[0576] 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."

[0577] Many companies and organizations are faced with the need to integrate, analyze, and utilize data distributed across different data storage locations. Traditionally, manually collecting data and integrating and formatting it has required time and effort, and there is a high risk of manual error. Therefore, there is a need for a method to process data efficiently and accurately and generate output quickly. Furthermore, a user-friendly interface is required to correct data and provide additional instructions in real time, and a concrete solution for this is needed.

[0578] 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.

[0579] In this invention, the server includes means for connecting to different data storage locations and analyzing metadata from each data storage location, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for issuing instructions for data correction or addition through a user interface on a terminal, means for generating a report or dashboard based on the formatted data, means for making the generated report or dashboard downloadable or sharable, means for collecting data in parallel based on the analyzed metadata, means for accepting data processing instructions based on natural language prompts through a chat interface on the terminal using a generative AI model, and means for inputting and confirming data on the terminal in real time. This allows users to efficiently and accurately integrate and format data and quickly generate output. Furthermore, the ability to check and correct data in real time enables flexible and accurate data utilization.

[0580] A "data destination" is a storage service or database where different data is stored.

[0581] "Metadata" refers to additional information about data, including information about the data's structure, format, data type, and so on.

[0582] "Automatic collection means" refers to a system that uses a program to continuously and efficiently collect the necessary data based on analyzed metadata and in accordance with conditions specified by the user.

[0583] "Means of integration and standardization" refers to the process of converting data of different formats and structures into a single common format and unifying it.

[0584] A "user interface" refers to a screen or operation panel that allows a user to interact with and operate a system.

[0585] A "report" or "dashboard" is a document or screen that visually displays analytical results or information created based on collected and formatted data.

[0586] "Real-time" is a term that refers to a state in which processing results are obtained almost immediately after data is input.

[0587] "Parallel processing" refers to the technology of simultaneously executing multiple data processing tasks to efficiently collect and format data.

[0588] A "generative AI model" is an algorithm that has been trained to automatically analyze and process data using AI technology.

[0589] A "prompt sentence" is an instruction or question entered by a user in natural language.

[0590] This invention is a system that collects data from different data storage locations, integrates and formats the data based on user instructions, and generates output. This system is composed of multiple hardware and software elements.

[0591] Basic system configuration

[0592] 1. Means of connection to the data storage destination

[0593] The user inputs information about the data storage destination (such as an API key, a connection URL, and query conditions) through a user interface on the terminal. Any personal computer, smartphone, or tablet can be used as the terminal.

[0594] The server connects to the specified data storage location (such as a cloud storage service or data warehouse) based on the information provided by the user. The server software uses a programming language such as Python or Java, and connects to the API endpoint using an HTTP request and performs authentication.

[0595] 2. Metadata Analysis Methods

[0596] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format (for example, column information for JSON or CSV files). It obtains and analyzes the metadata using Python's Pandas library, etc.

[0597] 3. Automatic collection of necessary data

[0598] The server automatically collects the necessary data according to the conditions specified by the user based on the analyzed metadata, and efficiently retrieves the data using Python parallel processing libraries (such as multiprocessing and asyncio).

[0599] 4. Data integration methods

[0600] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data from different file formats and database tables into a single data frame.

[0601] 5. Data Formatting Methods

[0602] The server then formats the aggregated data according to user requirements, including categorical aggregations and conversion to specific formats, using Python's Pandas and NumPy libraries.

[0603] 6. Chat Interface

[0604] The terminal provides a chat interface that allows users to check data and input instructions in real time. This interface is implemented using a web application framework (e.g., Flask or Django).

[0605] Users can modify data or provide additional instructions through chat, including instructions in natural language.

[0606] 7. Output Generation Methods

[0607] The server generates reports and dashboards based on the formatted data using Python's Matplotlib and Seaborn libraries, and outputs PDF and Excel files.

[0608] 8. Real-time processing methods

[0609] The device provides real-time data entry and validation, allowing users to receive immediate feedback and confirm that their data reflects their intended purpose.

[0610] Specific examples

[0611] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[0612] 1. The user requests, via the chat interface on their device, that they "collect quarterly sales data and create a report." The prompt reads, "Collect quarterly sales data and create a PDF report. The data should be for the first quarter of 2023 and include breakdowns by sales category."

[0613] 2. The server connects to the cloud storage (e.g., Amazon S3) or data warehouse (e.g., Google BigQuery) where the sales data is stored and analyzes the metadata of the files and tables.

[0614] 3. The server collects data for the specified quarter from each data storage location and efficiently ingests the data using parallel processing using Python's asyncio.

[0615] 4. The server uses Python's Pandas library to convert the collected data into a unified data frame and format it into quarterly segments.

[0616] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[0617] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[0618] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[0619] 8. The device presents the generated report to the user, offering options to download or share it.

[0620] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, allowing users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[0621] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0622] Step 1:

[0623] The user logs in to the user interface on the device and enters information about the data storage destination (such as an API key, connection URL, query conditions, etc.). This input information is sent to the server.

[0624] Input: API key for data storage destination, connection URL, query conditions

[0625] Output: Request sent to server

[0626] Specific behavior:

[0627] A user types into the chat interface, "Please aggregate our quarterly sales data and create a PDF report," along with details of where the data will be stored (e.g., Google BigQuery API key XYZ123).

[0628] Step 2:

[0629] The server connects to the specified data store based on the information provided by the user, and uses an HTTP request to connect to the API endpoint and perform authentication.

[0630] Input: User-provided data storage location information

[0631] Output: Authentication token, connection status

[0632] Specific behavior:

[0633] The server sends an authentication request to the Google BigQuery API, receives an authentication token in response, checks the connection status, and notifies the user.

[0634] Step 3:

[0635] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format using the Python Pandas library.

[0636] Input: Authentication token for data storage destination

[0637] Output: Metadata (column names, data types, etc.)

[0638] Specific behavior:

[0639] The server retrieves table information from BigQuery and lists the column names and data types. For example, it retrieves column information for the "sales" table.

[0640] Step 4:

[0641] The server automatically collects the necessary data according to the conditions (query conditions) specified by the user based on the analyzed metadata, and uses Python's asyncio to efficiently retrieve data through parallel processing.

[0642] Input: User query criteria, metadata

[0643] Output: Collected dataset

[0644] Specific behavior:

[0645] The server sends a query such as "SELECT FROM sales WHERE quarter='Q1'" to BigQuery and receives the results. Data is collected from multiple tables in parallel.

[0646] Step 5:

[0647] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data of different formats and structures into a single data frame.

[0648] Input: Collected dataset

[0649] Output: Unified data frame

[0650] Specific behavior:

[0651] The server converts the data from each table into a Pandas data frame, and then combines multiple data frames into a single dataset. For example, merging sales data with customer data.

[0652] Step 6:

[0653] The server then formats the integrated data according to user requests, such as by aggregating data by category or converting it into a specific format, using the Python Pandas and NumPy libraries.

[0654] Input: unified data frame

[0655] Output: Formatted data

[0656] Specific behavior:

[0657] The server aggregates the quarterly sales data using Pandas and adds a new calculated column. For example, a "total_sales" column is created to calculate the total sales for each quarter.

[0658] Step 7:

[0659] The terminal displays the formatted data as an intermediate result to the user and asks for confirmation.

[0660] Input: Formatted data

[0661] Output: Intermediate results that are displayed to the user

[0662] Specific behavior:

[0663] A data summary or sample of the intermediate results is displayed on the chat interface, along with a message asking, "Is this data okay?"

[0664] Step 8:

[0665] The user can modify or add data through the chat interface, using natural language prompts.

[0666] Input: User instructions

[0667] Output: Corrected or added data

[0668] Specific behavior:

[0669] The user enters instructions in the chat window, such as "Please also include column X in the calculation," and the server reprocesses the data based on those instructions.

[0670] Step 9:

[0671] The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[0672] Input: Corrected formatted data

[0673] Output: Final output (PDF or Excel)

[0674] Specific behavior:

[0675] The server-generated reports are visualized using Matplotlib and Seaborn, and an Excel file is created using Pandas' to_excel method.

[0676] Step 10:

[0677] The device presents the generated output to the user, offering options to download or share it.

[0678] Input: Final Output

[0679] Output: Download link or sharing option for the output

[0680] Specific behavior:

[0681] Display a link to the generated PDF report in the chat window and provide a "Download Report" button.

[0682] (Application example 1)

[0683] 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."

[0684] Modern logistics centers have a variety of data sources (inventory management systems, delivery management systems, order management systems, etc.), and there is a need to manage and operate each data in an integrated manner. However, manually collecting, analyzing, integrating, and displaying data from different sources in various output formats requires a great deal of time and effort. In addition, it is difficult to check data and respond to instructions in real time, making it difficult to achieve efficient logistics management.

[0685] 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.

[0686] In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata from each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for users to enter instructions for data corrections and additions via a chat interface on their smartphones, and means for generating output in real time based on the formatted data and displaying it in dashboard format, thereby enabling data integration from different data sources and real-time logistics management.

[0687] "Different data storage locations" refers to multiple locations where data is stored, such as cloud storage or databases.

[0688] "Metadata" refers to data that includes information about the data itself, such as the format, structure, and attribute information of the data.

[0689] "Analysis" refers to the process of deconstructing and interpreting collected metadata and other data to understand its structure and content.

[0690] "Automatic collection" refers to the act of collecting data by a system without human intervention.

[0691] "Integration" means bringing together different collected data into one standardized format.

[0692] "Formatting into a standardized format" means converting various data formats and structures into a unified format.

[0693] A "smartphone" refers to a multi-function mobile phone, a device capable of wireless communication and internet access.

[0694] A "chat interface" is an interface that allows users to interact with the system to check data, give instructions, etc.

[0695] "Instructions for correction or addition" refers to the act of a user issuing instructions to the system to change existing data or add new data.

[0696] "Real-time" refers to a situation in which user actions are reflected immediately without any time delay.

[0697] The "dashboard format" is a format in which data is visually organized and displayed so that the current situation can be grasped at a glance.

[0698] "Output" refers to the reports and data visualizations that are generated based on the formatted data.

[0699] MODE FOR CARRYING OUT THE INVENTION

[0700] This invention is a system that efficiently collects, integrates, and formats data from different data sources in logistics centers, allowing logistics managers to check and modify data in real time using their smartphones and make decisions quickly.

[0701] System Configuration

[0702] The system consists of the following elements:

[0703] 1. Server

[0704] The server receives data storage information provided by the user and connects to different data storage locations such as cloud storage or databases. For example, the user can enter an API key or connection URL, and the server uses that information to authenticate with the data storage location. The connection is established using the Python requests library.

[0705] 2. Metadata Analysis

[0706] The server analyzes the metadata of each data storage location to understand the data structure and format. Specifically, it uses the Python pandas library to retrieve and analyze the metadata.

[0707] 3. Automatic data collection

[0708] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata.To efficiently collect data using parallel processing techniques, the Python multiprocessing library is used.

[0709] 4. Data integration

[0710] The server consolidates the collected data into a standardized format and converts data from different formats (e.g., CSV, JSON) into a single data frame. Again, this consolidation is performed using the pandas library.

[0711] 5. Data Formatting

[0712] The server formats the integrated data into a format specified by the user, generating aggregated data for each category, for example.

[0713] 6. Generating Output

[0714] Based on the formatted data, the server generates dashboard-style output and provides it to users in real time. The dashboard is created using the Python matplotlib library.

[0715] 7. User Interface

[0716] The device (smartphone) provides a chat interface to the user, allowing them to check data and input instructions. The front end is implemented using React Native and the back end is implemented using Flask.

[0717] Program processing

[0718] Next, the details of the processing by the hardware and software of each element will be described.

[0719] Connecting and collecting data: The server uses the Python requests library to connect to each data store based on the API key and connection URL entered by the user. It then analyzes the metadata of the data store using the pandas library and automatically collects the required data.

[0720] Example: Enter the API key and URL of the inventory management system of the distribution center, and the server will connect based on that.

[0721] Example prompt sentence:

[0722] "Please enter the API key for your inventory management system."

[0723] Please enter the URL to connect to.

[0724] Data integration and transformation: The collected data is integrated into a single data frame using the pandas library. The data is then transformed and converted into the required format based on the user's instructions.

[0725] Example: Taking inventory and order data in different formats and transforming it into a unified data frame.

[0726] Example prompt sentence:

[0727] "Standardize the format of your data."

[0728] "Generate aggregate data by category."

[0729] Output Generation: Based on the consolidated and formatted data, the server generates a dashboard using Python's matplotlib library, which is displayed in real time through the user interface.

[0730] Example: Generate a dashboard that visualizes the current inventory status based on formatted inventory and order data.

[0731] Example prompt sentence:

[0732] "Generate a dashboard based on inventory data."

[0733] User interface: The device (smartphone) is equipped with a chat interface developed with React Native, through which users can correct or add data in real time.Flask is used as the backend to ensure that data is updated in real time.

[0734] Example: A user issues a command such as "Please update the latest inventory information," and the server formats the data accordingly and displays an updated dashboard.

[0735] Example prompt sentence:

[0736] View the latest inventory information

[0737] Please update the delivery status

[0738] The system streamlines data collection, integration, formatting and output generation, and enables real-time data verification and correction, facilitating fast and accurate data management and decision-making in logistics centers.

[0739] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0740] Step 1:

[0741] When a user uses a device (smartphone) to enter the API key and connection URL of the data storage destination, the data storage destination information is sent to the server. Based on the entered data storage destination information, the server uses the Python requests library to establish a connection to each data storage destination. Specifically, by including the API key and URL in the request, authentication to the cloud storage or database is performed. This allows the server to access the data from each data storage destination.

[0742] Input: API key for data storage destination, connection URL

[0743] Output: Establish connection to each data storage location

[0744] Step 2:

[0745] The server retrieves metadata from the connected data store and analyzes it using the Python pandas library. The metadata includes information about the data format, structure, and attributes, and analyzing this information provides an overall understanding of the data. Specifically, the server reads the file using the pandas read_json or read_csv method.

[0746] Input: Metadata for each data storage location

[0747] Output: Parsed metadata

[0748] Step 3:

[0749] The server automatically collects the necessary data based on the analyzed metadata. Here, the Python multiprocessing library is used to efficiently collect data using parallel processing techniques. Specifically, multiple processes are launched, and each process collects data from a different data storage location. This improves the speed at which data is collected.

[0750] Input: Parsed metadata

[0751] Output: Required data collected

[0752] Step 4:

[0753] The server consolidates the collected data and formats it into a standardized format. Because data collected from multiple data storage locations may have different formats and structures, it combines the data into a single data frame using the Python pandas library. Specifically, the data is consolidated using the pandas concat and merge methods.

[0754] Input: Required data collected

[0755] Output: Unified data frame

[0756] Step 5:

[0757] Users can use their smartphones to modify or add data via a chat interface. The chat interface is based on React Native, and the user's input is sent to the server. For example, a user might enter a command such as "Please update the latest inventory information."

[0758] Input: Corrections and additional instructions from the user

[0759] Output: Instructions sent to the server

[0760] Step 6:

[0761] The server modifies or adds data based on user instructions. It uses the Python pandas library to reprocess data according to the instructions. For example, if a user requests that the inventory quantity of a specific product be updated, the server searches for the relevant data and performs the update process.

[0762] Input: User corrections and additional instructions

[0763] Output: Corrected and added data

[0764] Step 7:

[0765] The server generates dashboard-style output based on the formatted data. It uses the Python matplotlib library to visualize the data and display it in a dashboard format. Specifically, it generates graphs and charts and creates a visual representation of them.

[0766] Input: Corrected and added data

[0767] Output: Dashboard-style output

[0768] Step 8:

[0769] The device (smartphone) provides the generated dashboard to the user in real time, allowing the user to view it and provide additional instructions as needed. The front end, implemented using React Native, immediately reflects data updates from the server.

[0770] Input: Dashboard output

[0771] Output: The dashboard as seen by the user

[0772] The above processing steps make data management at logistics centers more efficient and enable real-time data checking and decision-making.

[0773] 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.

[0774] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. This not only improves the efficiency of data collection, formatting, and output, but also enables more appropriate responses by taking the user's emotional state into consideration.

[0775] System Configuration

[0776] The system mainly consists of the following elements:

[0777] 1. Means of connection to the data storage destination

[0778] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[0779] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[0780] 2. Metadata Analysis Methods

[0781] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[0782] 3. Automatic collection of necessary data

[0783] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[0784] 4. Data integration methods

[0785] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[0786] 5. Data Formatting Methods

[0787] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[0788] 6. Chat Interface

[0789] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[0790] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[0791] 7. Emotion Engine

[0792] The device is equipped with an emotion engine that performs emotion analysis based on user input and behavior, such as text context, input speed, and typing intensity, to determine the user's emotional state.

[0793] The server automatically adjusts data collection and processing procedures based on the emotional data obtained by the emotion engine, including simplifying operations if the user is feeling stressed.

[0794] 8. Output Generation Methods

[0795] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[0796] Specific examples

[0797] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[0798] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[0799] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[0800] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[0801] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[0802] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[0803] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[0804] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[0805] 8. The device presents the generated report to the user, offering options to download or share it.

[0806] 9. The device will analyze the user's emotional state in real time through an emotion engine, and automatically adjust operations and data presentation methods if the user is feeling stressed or dissatisfied.

[0807] 10. The server performs flexible data processing based on the results of emotion analysis to improve the user experience.

[0808] This system significantly improves the efficiency of the previously manual process from data collection to output generation, enabling users to analyze data and make decisions more quickly.In addition, the introduction of an emotion engine enables flexible and optimal data manipulation that takes into account the user's emotional state.

[0809] The processing flow will be explained below.

[0810] Step 1:

[0811] The user uses the chat interface on the device to input information about the data storage destination (e.g., cloud storage URL, API key, DWH connection information, etc.) and provides it to the system.

[0812] Step 2:

[0813] The server establishes a connection to each data store based on the provided data store information, authenticates using an API or database client, and completes the connection.

[0814] Step 3:

[0815] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[0816] Step 4:

[0817] The user issues a command via the chat interface on the device saying, "I want you to compile quarterly sales data and create a report."

[0818] Step 5:

[0819] The server uses the parsed metadata to identify the required data based on user-specified criteria, such as files and table entries that match the criteria "sales data for the first quarter of last year."

[0820] Step 6:

[0821] The server efficiently retrieves the data to be collected using parallel processing techniques (for example, multi-threading or multi-processing) and aggregates the data.

[0822] Step 7:

[0823] The server aggregates the collected data into a standardized format (e.g., data frames or statistical data), and converts data from different formats into a consistent form.

[0824] Step 8:

[0825] The server then formats the integrated data into a user-specified format, for example, by aggregating the data by quarter and converting it into a table or graph format.

[0826] Step 9:

[0827] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[0828] Step 10:

[0829] Through the chat interface, users can give instructions to correct or add necessary data, such as "Please change the data for a specific period and recalculate it."

[0830] Step 11:

[0831] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[0832] Step 12:

[0833] The device runs an emotion engine that performs emotion analysis based on the user's input and behavior, for example, by determining the user's emotional state from input speed and context analysis.

[0834] Step 13:

[0835] The server automatically adjusts data collection and processing procedures based on the analysis results of the emotion engine. For example, if the user is feeling stressed, it will simplify the operation procedures.

[0836] Step 14:

[0837] The server generates reports and dashboards based on the final formatted data, which can include PDF reports, Excel sheets, and web-based dashboards.

[0838] Step 15:

[0839] The device displays the generated report to the user and provides options for downloading and sharing.

[0840] Step 16:

[0841] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[0842] These are the specific processing steps of a system incorporating the emotion engine of the present invention. This system streamlines the process from data collection to output generation, and also enables flexible responses tailored to the user's emotional state.

[0843] Example 2

[0844] 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."

[0845] In conventional data collection and processing systems, collecting data from different data storage locations and integrating the collected data takes time and effort, making it difficult for users to analyze data efficiently. Furthermore, data manipulation that ignores the user's emotional state causes operational complexity and stress, ultimately resulting in a poor user experience. This has led to a demand for more efficient data processing and improved user experience.

[0846] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata of each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for a user to issue instructions for data correction or addition through a chat interface, means for generating output based on the formatted data, means for adjusting data processing procedures by performing sentiment analysis on user inputs and actions, and means for simplifying user operations based on the sentiment analysis results. This enables efficient data collection and formatting, as well as flexible data manipulation that takes into account the user's emotional state and an improved user experience.

[0847] A "data destination" is a physical or virtual location where data is stored, such as cloud storage, a database, or a data warehouse.

[0848] "Metadata" refers to information about the attributes and structure of data, including the type of data, format, size, creation date, and so on.

[0849] "Analyzing" refers to breaking down data and metadata and converting them into an understandable form, thereby understanding the structure and content of the data.

[0850] "Collect" refers to extracting data based on specified conditions and gathering it in one place.

[0851] "Integrate" refers to combining multiple data sets into one standardized format.

[0852] "Format" refers to converting collected and integrated data into a specific form or format, and processing the data in accordance with the user's request.

[0853] "Chat interface" refers to an interactive user interface that allows a user to issue text-based instructions to a system and receive responses from the system.

[0854] "Output" refers to the results generated based on formatted data, including reports, dashboards, graphs, PDF files, etc.

[0855] "Emotion analysis" refers to identifying and analyzing a user's emotional state based on their input and behavior.

[0856] "Tuning" refers to changing the system's behavior based on the information obtained to achieve optimal results.

[0857] "Simplifying operations" refers to techniques for simplifying the process of users collecting, formatting, checking, and correcting data, thereby reducing the burden on users.

[0858] The present invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. A specific embodiment of the present invention will be described below.

[0859] Hardware and Software Use

[0860] This system mainly consists of a server and a terminal. The server is located on a cloud infrastructure, and the terminal is a personal computer or mobile device operated by a user. The server uses the following main software components:

[0861] Data Collection and Analysis: Data collection and analysis will be performed using Python programs and the Pandas library.

[0862] Concurrency: Use Python's multithreading library to collect data efficiently.

[0863] Data integration and shaping: Use Pandas to standardize data in different formats and shape it as needed.

[0864] Output generation: Creating reports and dashboards using Matplotlib or other data visualization libraries.

[0865] The device uses the following main software components:

[0866] Chat interface: Provides a front-end application using React.js to receive user instructions in real time.

[0867] Sentiment analysis: Analyze the user's input text using an NLP library (e.g., NLTK or SpaCy).

[0868] Specific examples

[0869] For example, a specific flow will be described in which a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report."

[0870] 1. The user instructs the chat interface on their device to "aggregate quarterly sales data and create a report."

[0871] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[0872] 3. The server collects the data for the specified quarter using parallel processing and integrates it into a Pandas data frame.

[0873] 4. The server groups the consolidated data by quarter and performs aggregations.

[0874] 5. The terminal displays a preview of the intermediate results in the chat interface and asks for the user's confirmation.

[0875] 6. The user communicates data corrections and additions to the server through the chat interface.

[0876] 7. The server reprocesses the data based on the correction instructions and generates a PDF report as the final output.

[0877] 8. The device will display a download link for the generated PDF report in the chat interface.

[0878] 9. The device uses an emotion analysis engine to analyze user input and simplify operations if the user is feeling stressed.

[0879] 10. The server adjusts the priority of data processing based on the emotion data to optimize the user experience.

[0880] Specific examples of prompts are as follows:

[0881] "I want you to compile quarterly sales data and create a report."

[0882] In this way, the present invention not only improves the efficiency of data collection and shaping, but also enables flexible data manipulation that takes into account the emotional state of the user.

[0883] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0884] Step 1:

[0885] The user inputs the command "I want you to compile the sales data for each quarter and create a report" into the chat interface on the device. The input data becomes "I want you to compile the sales data for each quarter and create a report." Based on this input, the next data collection step is initiated.

[0886] Step 2:

[0887] The server connects to the cloud storage (e.g., AWS S3) or data warehouse where the sales data is stored and analyzes the metadata of the files and tables. The input data is the authentication information for the data storage destination (API key, URL, etc.) and the structure information of the storage destination. By analyzing the metadata, the structure and format of the data are understood and the information necessary for the next data collection is obtained.

[0888] Step 3:

[0889] The server efficiently collects data for the specified quarter from each data repository using parallel processing based on the parsed metadata. The input data is the metadata information and quarter specification, and the output data is the collected raw sales data. Parallel processing speeds up data collection, ingesting data from multiple API endpoints simultaneously.

[0890] Step 4:

[0891] The server consolidates the collected data into a standardized format. Specifically, it converts different file formats (e.g., CSV, JSON) into a data frame using Pandas. The input data is the collected raw data, and the output data is the consolidated data frame. This allows data from different sources to be converted into a consistent format.

[0892] Step 5:

[0893] The server groups the consolidated data by quarter and performs the necessary aggregation operations to reshape it. Specifically, it uses the grouping and aggregation functions of Pandas. The input data is a consolidated data frame, and the output data is data reshaped by quarter. This allows for efficient analysis of data for a specific period.

[0894] Step 6:

[0895] The terminal displays the intermediate results of the formatted data on the chat interface and requests the user's confirmation. The displayed information includes a preview of the quarterly summary results. The input data is the formatted data, and the output data is a data preview displayed to the user for confirmation.

[0896] Step 7:

[0897] The user sends instructions to the server via the chat interface to correct or add data. For example, the user might say, "Please correct the data for the second quarter." The input data is the user's correction instruction, and the output data is the correction instruction itself.

[0898] Step 8:

[0899] The server reprocesses the data in response to the user's correction instructions. Specifically, it uses Pandas to correct the data frame and perform recalculation. The input data is the correction instructions and the data to be corrected, and the output data is the corrected data frame.

[0900] Step 9:

[0901] The server generates the quarterly sales report as the final output and outputs it in PDF or other specified format. Specifically, it generates a graph from the data frame using Matplotlib and embeds it in a PDF. The input data is the modified data frame, and the output data is the final report file.

[0902] Step 10:

[0903] The terminal displays a download link for the generated PDF report on the chat interface and presents it to the user. The input data is the generated report file, and the output data is the download link.

[0904] Step 11:

[0905] The device uses an emotion analysis engine to analyze the user's input and simplifies the operation if the user is feeling stressed or dissatisfied. Specifically, it performs text analysis and simplifies the next step based on the results. The input data is the user's input text, and the output data is the emotion analysis result.

[0906] Step 12:

[0907] The server modifies the data processing procedures and user interface based on the emotion analysis results, simplifying user operations. The input data is the emotion analysis results, and the output data is the adjusted processing procedures and user interface settings. This process optimizes the user experience and improves work efficiency.

[0908] The above are the specific processing steps and operations of this system.

[0909] (Application example 2)

[0910] 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."

[0911] On modern online shopping sites, it is difficult for users to find the right product for them from the vast number of products available. Furthermore, typical recommendation systems are based on the user's recent behavior and purchase history, and are unable to suggest products that take into account the user's emotional state. Furthermore, data collection, formatting, and output generation are often done manually, which can often be perceived as inefficient. To solve these problems, a data processing system that also takes into account the user's emotional state is needed.

[0912] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0913] In this invention, the server includes a means for connecting to different data storage locations and analyzing the metadata of each data storage location, a means for automatically collecting necessary data based on the analyzed metadata, and a means for integrating the collected data and formatting it into a standardized format, which enables product recommendations based on the user's emotional state and efficient data collection, formatting, and output generation.

[0914] "Data storage" refers to the system or storage that stores data stored in different locations.

[0915] "Metadata" is additional data that contains information about data and describes the structure and attributes of the data.

[0916] An "automatic collection means" is a method or device for automatically obtaining necessary data from a designated data storage location without user intervention.

[0917] A "means for converting data into a standardized format" is a method or device for converting data stored in different formats into a single unified format.

[0918] A "chat interface" is an interactive user interface through which a user can enter text and interact with the system.

[0919] An "emotion engine" is software or hardware that analyzes a user's input and actions to determine their emotional state at that time.

[0920] An "output generating means" is a method or device that generates reports or visualizations based on the formatted data.

[0921] A "means for generating product recommendations" is a method or device that suggests suitable products based on the user's emotional state and past data.

[0922] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. Specific embodiments for realizing this system are described below.

[0923] System Configuration

[0924] The system mainly consists of the following elements:

[0925] 1. How to connect to the data storage location:

[0926] The server connects to the data storage destination using information such as an API key and connection URL provided by the user. For example, it authenticates and establishes a connection to different data storage destinations such as cloud storage services and data warehouses.

[0927] 2. Metadata analysis methods:

[0928] The server analyzes the metadata of the connected data storage destination to understand the data structure and format, and identifies the required data based on the analysis results.

[0929] 3. Automated collection of required data:

[0930] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[0931] 4. Data integration methods:

[0932] The server consolidates the collected data into a single standardized format, for example by converting data from different file formats into a data frame.

[0933] 5. Data Formatting Methods:

[0934] The server then processes the combined data in a user-specified format, such as by aggregating it by category or converting it into a specific format.

[0935] 6. Chat Interface:

[0936] The terminal provides a chat interface to the user, allowing the user to check data and input instructions in real time. The user can correct data or give additional instructions through the chat.

[0937] 7. Emotion Engine:

[0938] The device is equipped with an emotion engine that performs emotion analysis based on the user's input and behavior. For example, it analyzes the user's emotional state based on the context of the text, input speed, typing intensity, etc. The server automatically adjusts data collection and formatting procedures based on the emotion data obtained by the emotion engine.

[0939] 8. Output Generation Means:

[0940] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[0941] 9. Product recommendation generation method:

[0942] The server suggests suitable products based on the user's emotional state and past data, utilizing algorithms based on emotion engines and data refinement methods.

[0943] Example

[0944] For example, there is a smartphone application called "Smart Shopping Assistant" for an online shopping site. This application works as follows:

[0945] 1. The user types "I'm looking for soothing products" into the chat interface on their device.

[0946] 2. The server collects data from different product data APIs and parses the metadata to extract the required data.

[0947] 3. The analyzed data is collected in parallel and formatted into a standardized format.

[0948] 4. The emotion engine analyzes the user's input and determines that it is a negative state.

[0949] 5. Based on this emotional data, relaxation goods and aroma products are recommended preferentially.

[0950] 6. Present product recommendations to users through the chat interface and offer purchasing options.

[0951] In this way, it becomes possible to recommend products based on the user's emotional state, as well as to efficiently collect, format, and generate output from data.

[0952] Prompt Sentence Examples

[0953] How are you feeling right now? What products are you looking for?

[0954] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0955] Step 1:

[0956] Connecting to a data storage location

[0957] The server receives the API key and connection URL information provided by the user as input and connects to each data storage destination. Specifically, it authenticates and establishes a connection with different data storage destinations such as cloud storage services and data warehouses. This prepares the server to retrieve the required data from the data storage destination.

[0958] Step 2:

[0959] Metadata analysis

[0960] The server analyzes the metadata of the connected data store, which includes file structure, database schema, data format, etc. It takes the metadata as input and understands the overall structure of the data, which forms the basis for identifying what data is needed.

[0961] Step 3:

[0962] Collection of necessary data

[0963] The server automatically collects the necessary data based on the analyzed metadata. It receives condition settings as input and efficiently collects the necessary data from the data storage location using parallel processing technology. The collected data is converted into a standardized format, allowing data in a unified format to be obtained from diverse data sources.

[0964] Step 4:

[0965] Data integration and formatting

[0966] The server aggregates the collected data and formats it into a standardized format. The input is the raw data collected, and the output is a unified data frame. During this process, data is aggregated by category and converted into a specific format to ensure consistency.

[0967] Step 5:

[0968] Emotion analysis

[0969] The device performs emotion analysis based on the user's input and behavior. For example, it displays prompts such as "How are you feeling right now? What kind of product are you looking for?" and receives user input. The input is text data, which the emotion engine analyzes and outputs the user's emotional state. This includes analyzing the context of the text and the speed of input.

[0970] Step 6:

[0971] Generate product recommendations

[0972] The server generates product recommendations based on the analysis results of the emotion engine according to the user's emotional state. The input is the results of the emotion analysis and formatted data, and the output is a product list presented to the user. For example, if the user is feeling stressed, relaxation goods and aroma products will be recommended first.

[0973] Step 7:

[0974] Output through the chat interface

[0975] The terminal displays the generated product recommendations to the user through a chat interface. The input is the generated product list, and the output is the display to the user on the terminal. The user can provide further instructions through this interface, and the system will reprocess the data accordingly.

[0976] Step 8:

[0977] Generating the final output

[0978] The server generates the final output and provides it to the user as needed, such as a report or dashboard. The input is the formatted data and additional user instructions, and the output is a PDF report or a web-based dashboard, allowing the user to see the results of the data processing in a tangible way.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] [Third embodiment]

[0983] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0984] 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.

[0985] 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).

[0986] 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.

[0987] 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.

[0988] 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).

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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.

[0993] 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.

[0994] 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."

[0995] This invention is a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, thereby significantly reducing the time and effort required to collect and format the data.

[0996] System Configuration

[0997] The system mainly consists of the following elements:

[0998] 1. Means of connection to the data storage destination

[0999] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[1000] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[1001] 2. Metadata Analysis Methods

[1002] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[1003] 3. Automatic collection of necessary data

[1004] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[1005] 4. Data integration methods

[1006] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[1007] 5. Data Formatting Methods

[1008] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[1009] 6. Chat Interface

[1010] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[1011] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[1012] 7. Output Generation Methods

[1013] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[1014] Specific examples

[1015] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[1016] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[1017] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[1018] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[1019] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[1020] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[1021] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[1022] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[1023] 8. The device presents the generated report to the user, offering options to download or share it.

[1024] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, enabling users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[1025] The processing flow will be explained below.

[1026] Step 1:

[1027] The user inputs information about the data storage destination to be used in the chat interface on the device (for example, the URL of the cloud storage, the API key, the connection information of the DWH, etc.) and provides it to the system.

[1028] Step 2:

[1029] The server establishes a connection to each data store based on the provided information, authenticates using an API or database client, and maintains the connection.

[1030] Step 3:

[1031] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[1032] Step 4:

[1033] The user instructs the chat interface on the device to "collect specific data and create a report."

[1034] Step 5:

[1035] The server identifies data that matches the conditions specified by the user based on the analyzed metadata, for example, files and table entries that match the condition "sales data for this month."

[1036] Step 6:

[1037] The server efficiently retrieves the data to be collected using parallel processing techniques (multi-threading or multi-processing) and aggregates the data.

[1038] Step 7:

[1039] The server aggregates the collected data into a standardized format (e.g., a data frame), resolving inconsistencies and missing values ​​between different formats to create a consistent dataset.

[1040] Step 8:

[1041] The server then formats the integrated data into a user-specified format. For example, it can aggregate sales data by day, month, or category and format it in a table or graph format.

[1042] Step 9:

[1043] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[1044] Step 10:

[1045] The user can issue instructions to correct or add data through a chat interface, such as "I want the data for a specific period to be changed and re-aggregated."

[1046] Step 11:

[1047] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[1048] Step 12:

[1049] The server generates the final reports and dashboards based on the corrected data, which can be PDF reports, Excel sheets, or web-based dashboards.

[1050] Step 13:

[1051] The device presents the generated report to the user and offers options to download or share it.

[1052] Step 14:

[1053] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[1054] Example 1

[1055] 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."

[1056] Many companies and organizations are faced with the need to integrate, analyze, and utilize data distributed across different data storage locations. Traditionally, manually collecting data and integrating and formatting it has required time and effort, and there is a high risk of manual error. Therefore, there is a need for a method to process data efficiently and accurately and generate output quickly. Furthermore, a user-friendly interface is required to correct data and provide additional instructions in real time, and a concrete solution for this is needed.

[1057] 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.

[1058] In this invention, the server includes means for connecting to different data storage locations and analyzing metadata from each data storage location, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for issuing instructions for data correction or addition through a user interface on a terminal, means for generating a report or dashboard based on the formatted data, means for making the generated report or dashboard downloadable or sharable, means for collecting data in parallel based on the analyzed metadata, means for accepting data processing instructions based on natural language prompts through a chat interface on the terminal using a generative AI model, and means for inputting and confirming data on the terminal in real time. This allows users to efficiently and accurately integrate and format data and quickly generate output. Furthermore, the ability to check and correct data in real time enables flexible and accurate data utilization.

[1059] A "data destination" is a storage service or database where different data is stored.

[1060] "Metadata" refers to additional information about data, including information about the data's structure, format, data type, and so on.

[1061] "Automatic collection means" refers to a system that uses a program to continuously and efficiently collect the necessary data based on analyzed metadata and in accordance with conditions specified by the user.

[1062] "Means of integration and standardization" refers to the process of converting data of different formats and structures into a single common format and unifying it.

[1063] A "user interface" refers to a screen or operation panel that allows a user to interact with and operate a system.

[1064] A "report" or "dashboard" is a document or screen that visually displays analytical results or information created based on collected and formatted data.

[1065] "Real-time" is a term that refers to a state in which processing results are obtained almost immediately after data is input.

[1066] "Parallel processing" refers to the technology of simultaneously executing multiple data processing tasks to efficiently collect and format data.

[1067] A "generative AI model" is an algorithm that has been trained to automatically analyze and process data using AI technology.

[1068] A "prompt sentence" is an instruction or question entered by a user in natural language.

[1069] This invention is a system that collects data from different data storage locations, integrates and formats the data based on user instructions, and generates output. This system is composed of multiple hardware and software elements.

[1070] Basic system configuration

[1071] 1. Means of connection to the data storage destination

[1072] The user inputs information about the data storage destination (such as an API key, a connection URL, and query conditions) through a user interface on the terminal. Any personal computer, smartphone, or tablet can be used as the terminal.

[1073] The server connects to the specified data storage location (such as a cloud storage service or data warehouse) based on the information provided by the user. The server software uses a programming language such as Python or Java, and connects to the API endpoint using an HTTP request and performs authentication.

[1074] 2. Metadata Analysis Methods

[1075] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format (for example, column information for JSON or CSV files). It obtains and analyzes the metadata using Python's Pandas library, etc.

[1076] 3. Automatic collection of necessary data

[1077] The server automatically collects the necessary data according to the conditions specified by the user based on the analyzed metadata, and efficiently retrieves the data using Python parallel processing libraries (such as multiprocessing and asyncio).

[1078] 4. Data integration methods

[1079] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data from different file formats and database tables into a single data frame.

[1080] 5. Data Formatting Methods

[1081] The server then formats the aggregated data according to user requirements, including categorical aggregations and conversion to specific formats, using Python's Pandas and NumPy libraries.

[1082] 6. Chat Interface

[1083] The terminal provides a chat interface that allows users to check data and input instructions in real time. This interface is implemented using a web application framework (e.g., Flask or Django).

[1084] Users can modify data or provide additional instructions through chat, including instructions in natural language.

[1085] 7. Output Generation Methods

[1086] The server generates reports and dashboards based on the formatted data using Python's Matplotlib and Seaborn libraries, and outputs PDF and Excel files.

[1087] 8. Real-time processing methods

[1088] The device provides real-time data entry and validation, allowing users to receive immediate feedback and confirm that their data reflects their intended purpose.

[1089] Specific examples

[1090] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[1091] 1. The user requests, via the chat interface on their device, that they "collect quarterly sales data and create a report." The prompt reads, "Collect quarterly sales data and create a PDF report. The data should be for the first quarter of 2023 and include breakdowns by sales category."

[1092] 2. The server connects to the cloud storage (e.g., Amazon S3) or data warehouse (e.g., Google BigQuery) where the sales data is stored and analyzes the metadata of the files and tables.

[1093] 3. The server collects data for the specified quarter from each data storage location and efficiently ingests the data using parallel processing using Python's asyncio.

[1094] 4. The server uses Python's Pandas library to convert the collected data into a unified data frame and format it into quarterly segments.

[1095] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[1096] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[1097] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[1098] 8. The device presents the generated report to the user, offering options to download or share it.

[1099] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, allowing users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[1100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1101] Step 1:

[1102] The user logs in to the user interface on the device and enters information about the data storage destination (such as an API key, connection URL, query conditions, etc.). This input information is sent to the server.

[1103] Input: API key for data storage destination, connection URL, query conditions

[1104] Output: Request sent to server

[1105] Specific behavior:

[1106] A user types into the chat interface, "Please aggregate our quarterly sales data and create a PDF report," along with details of where the data will be stored (e.g., Google BigQuery API key XYZ123).

[1107] Step 2:

[1108] The server connects to the specified data store based on the information provided by the user, and uses an HTTP request to connect to the API endpoint and perform authentication.

[1109] Input: User-provided data storage location information

[1110] Output: Authentication token, connection status

[1111] Specific behavior:

[1112] The server sends an authentication request to the Google BigQuery API, receives an authentication token in response, checks the connection status, and notifies the user.

[1113] Step 3:

[1114] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format using the Python Pandas library.

[1115] Input: Authentication token for data storage destination

[1116] Output: Metadata (column names, data types, etc.)

[1117] Specific behavior:

[1118] The server retrieves table information from BigQuery and lists the column names and data types. For example, it retrieves column information for the "sales" table.

[1119] Step 4:

[1120] The server automatically collects the necessary data according to the conditions (query conditions) specified by the user based on the analyzed metadata, and uses Python's asyncio to efficiently retrieve data through parallel processing.

[1121] Input: User query criteria, metadata

[1122] Output: Collected dataset

[1123] Specific behavior:

[1124] The server sends a query such as "SELECT FROM sales WHERE quarter='Q1'" to BigQuery and receives the results. Data is collected from multiple tables in parallel.

[1125] Step 5:

[1126] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data of different formats and structures into a single data frame.

[1127] Input: Collected dataset

[1128] Output: Unified data frame

[1129] Specific behavior:

[1130] The server converts the data from each table into a Pandas data frame, and then combines multiple data frames into a single dataset. For example, merging sales data with customer data.

[1131] Step 6:

[1132] The server then formats the integrated data according to user requests, such as by aggregating data by category or converting it into a specific format, using the Python Pandas and NumPy libraries.

[1133] Input: unified data frame

[1134] Output: Formatted data

[1135] Specific behavior:

[1136] The server aggregates the quarterly sales data using Pandas and adds a new calculated column. For example, a "total_sales" column is created to calculate the total sales for each quarter.

[1137] Step 7:

[1138] The terminal displays the formatted data as an intermediate result to the user and asks for confirmation.

[1139] Input: Formatted data

[1140] Output: Intermediate results that are displayed to the user

[1141] Specific behavior:

[1142] A data summary or sample of the intermediate results is displayed on the chat interface, along with a message asking, "Is this data okay?"

[1143] Step 8:

[1144] The user can modify or add data through the chat interface, using natural language prompts.

[1145] Input: User instructions

[1146] Output: Corrected or added data

[1147] Specific behavior:

[1148] The user enters instructions in the chat window, such as "Please also include column X in the calculation," and the server reprocesses the data based on those instructions.

[1149] Step 9:

[1150] The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[1151] Input: Corrected formatted data

[1152] Output: Final output (PDF or Excel)

[1153] Specific behavior:

[1154] The server-generated reports are visualized using Matplotlib and Seaborn, and an Excel file is created using Pandas' to_excel method.

[1155] Step 10:

[1156] The device presents the generated output to the user, offering options to download or share it.

[1157] Input: Final Output

[1158] Output: Download link or sharing option for the output

[1159] Specific behavior:

[1160] Display a link to the generated PDF report in the chat window and provide a "Download Report" button.

[1161] (Application example 1)

[1162] 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."

[1163] Modern logistics centers have a variety of data sources (inventory management systems, delivery management systems, order management systems, etc.), and there is a need to manage and operate each data in an integrated manner. However, manually collecting, analyzing, integrating, and displaying data from different sources in various output formats requires a great deal of time and effort. In addition, it is difficult to check data and respond to instructions in real time, making it difficult to achieve efficient logistics management.

[1164] 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.

[1165] In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata from each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for users to enter instructions for data corrections and additions via a chat interface on their smartphones, and means for generating output in real time based on the formatted data and displaying it in dashboard format, thereby enabling data integration from different data sources and real-time logistics management.

[1166] "Different data storage locations" refers to multiple locations where data is stored, such as cloud storage or databases.

[1167] "Metadata" refers to data that includes information about the data itself, such as the format, structure, and attribute information of the data.

[1168] "Analysis" refers to the process of deconstructing and interpreting collected metadata and other data to understand its structure and content.

[1169] "Automatic collection" refers to the act of collecting data by a system without human intervention.

[1170] "Integration" means bringing together different collected data into one standardized format.

[1171] "Formatting into a standardized format" means converting various data formats and structures into a unified format.

[1172] A "smartphone" refers to a multi-function mobile phone, a device capable of wireless communication and internet access.

[1173] A "chat interface" is an interface that allows users to interact with the system to check data, give instructions, etc.

[1174] "Instructions for correction or addition" refers to the act of a user issuing instructions to the system to change existing data or add new data.

[1175] "Real-time" refers to a situation in which user actions are reflected immediately without any time delay.

[1176] The "dashboard format" is a format in which data is visually organized and displayed so that the current situation can be grasped at a glance.

[1177] "Output" refers to the reports and data visualizations that are generated based on the formatted data.

[1178] MODE FOR CARRYING OUT THE INVENTION

[1179] This invention is a system that efficiently collects, integrates, and formats data from different data sources in logistics centers, allowing logistics managers to check and modify data in real time using their smartphones and make decisions quickly.

[1180] System Configuration

[1181] The system consists of the following elements:

[1182] 1. Server

[1183] The server receives data storage information provided by the user and connects to different data storage locations such as cloud storage or databases. For example, the user can enter an API key or connection URL, and the server uses that information to authenticate with the data storage location. The connection is established using the Python requests library.

[1184] 2. Metadata Analysis

[1185] The server analyzes the metadata of each data storage location to understand the data structure and format. Specifically, it uses the Python pandas library to retrieve and analyze the metadata.

[1186] 3. Automatic data collection

[1187] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata.To efficiently collect data using parallel processing techniques, the Python multiprocessing library is used.

[1188] 4. Data Integration

[1189] The server consolidates the collected data into a standardized format and converts data from different formats (e.g., CSV, JSON) into a single data frame. Again, this consolidation is performed using the pandas library.

[1190] 5. Data Formatting

[1191] The server formats the integrated data into a format specified by the user, generating aggregated data for each category, for example.

[1192] 6. Generating Output

[1193] Based on the formatted data, the server generates dashboard-style output and provides it to users in real time. The dashboard is created using the Python matplotlib library.

[1194] 7. User Interface

[1195] The device (smartphone) provides a chat interface to the user, allowing them to check data and input instructions. The front end is implemented using React Native and the back end is implemented using Flask.

[1196] Program processing

[1197] Next, the details of the processing by the hardware and software of each element will be described.

[1198] Connecting and collecting data: The server uses the Python requests library to connect to each data store based on the API key and connection URL entered by the user. It then analyzes the metadata of the data store using the pandas library and automatically collects the required data.

[1199] Example: Enter the API key and URL of the inventory management system of the distribution center, and the server will connect based on that.

[1200] Example prompt sentence:

[1201] "Please enter the API key for your inventory management system."

[1202] Please enter the URL to connect to.

[1203] Data integration and transformation: The collected data is integrated into a single data frame using the pandas library. The data is then transformed and converted into the required format based on the user's instructions.

[1204] Example: Taking inventory and order data in different formats and transforming it into a unified data frame.

[1205] Example prompt sentence:

[1206] "Standardize the format of your data."

[1207] "Generate aggregate data by category."

[1208] Output Generation: Based on the consolidated and formatted data, the server generates a dashboard using Python's matplotlib library, which is displayed in real time through the user interface.

[1209] Example: Generate a dashboard that visualizes the current inventory status based on formatted inventory and order data.

[1210] Example prompt sentence:

[1211] "Generate a dashboard based on inventory data."

[1212] User interface: The device (smartphone) is equipped with a chat interface developed with React Native, through which users can correct or add data in real time.Flask is used as the backend to ensure that data is updated in real time.

[1213] Example: A user issues a command such as "Please update the latest inventory information," and the server formats the data accordingly and displays an updated dashboard.

[1214] Example prompt sentence:

[1215] View the latest inventory information

[1216] Please update the delivery status

[1217] The system streamlines data collection, integration, formatting and output generation, and enables real-time data verification and correction, facilitating fast and accurate data management and decision-making in logistics centers.

[1218] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1219] Step 1:

[1220] When a user uses a device (smartphone) to enter the API key and connection URL of the data storage destination, the data storage destination information is sent to the server. Based on the entered data storage destination information, the server uses the Python requests library to establish a connection to each data storage destination. Specifically, by including the API key and URL in the request, authentication to the cloud storage or database is performed. This allows the server to access the data from each data storage destination.

[1221] Input: API key for data storage destination, connection URL

[1222] Output: Establish connection to each data storage location

[1223] Step 2:

[1224] The server retrieves metadata from the connected data store and analyzes it using the Python pandas library. The metadata includes information about the data format, structure, and attributes, and analyzing this information provides an overall understanding of the data. Specifically, the server reads the file using the pandas read_json or read_csv method.

[1225] Input: Metadata for each data storage location

[1226] Output: Parsed metadata

[1227] Step 3:

[1228] The server automatically collects the necessary data based on the analyzed metadata. Here, the Python multiprocessing library is used to efficiently collect data using parallel processing techniques. Specifically, multiple processes are launched, and each process collects data from a different data storage location. This improves the speed at which data is collected.

[1229] Input: Parsed metadata

[1230] Output: Required data collected

[1231] Step 4:

[1232] The server consolidates the collected data and formats it into a standardized format. Because data collected from multiple data storage locations may have different formats and structures, it combines the data into a single data frame using the Python pandas library. Specifically, the data is consolidated using the pandas concat and merge methods.

[1233] Input: Required data collected

[1234] Output: Unified data frame

[1235] Step 5:

[1236] Users can use their smartphones to modify or add data via a chat interface. The chat interface is based on React Native, and the user's input is sent to the server. For example, a user might enter a command such as "Please update the latest inventory information."

[1237] Input: Corrections and additional instructions from the user

[1238] Output: Instructions sent to the server

[1239] Step 6:

[1240] The server modifies or adds data based on user instructions. It uses the Python pandas library to reprocess data according to the instructions. For example, if a user requests that the inventory quantity of a specific product be updated, the server searches for the relevant data and performs the update process.

[1241] Input: User corrections and additional instructions

[1242] Output: Corrected and added data

[1243] Step 7:

[1244] The server generates dashboard-style output based on the formatted data. It uses the Python matplotlib library to visualize the data and display it in a dashboard format. Specifically, it generates graphs and charts and creates a visual representation of them.

[1245] Input: Corrected and added data

[1246] Output: Dashboard-style output

[1247] Step 8:

[1248] The device (smartphone) provides the generated dashboard to the user in real time, allowing the user to view it and provide additional instructions as needed. The front end, implemented using React Native, immediately reflects data updates from the server.

[1249] Input: Dashboard output

[1250] Output: The dashboard as seen by the user

[1251] The above processing steps make data management at logistics centers more efficient and enable real-time data checking and decision-making.

[1252] 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.

[1253] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. This not only improves the efficiency of data collection, formatting, and output, but also enables more appropriate responses by taking the user's emotional state into consideration.

[1254] System Configuration

[1255] The system mainly consists of the following elements:

[1256] 1. Means of connection to the data storage destination

[1257] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[1258] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[1259] 2. Metadata Analysis Methods

[1260] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[1261] 3. Automatic collection of necessary data

[1262] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[1263] 4. Data integration methods

[1264] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[1265] 5. Data Formatting Methods

[1266] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[1267] 6. Chat Interface

[1268] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[1269] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[1270] 7. Emotion Engine

[1271] The device is equipped with an emotion engine that performs emotion analysis based on user input and behavior, such as text context, input speed, and typing intensity, to determine the user's emotional state.

[1272] The server automatically adjusts data collection and processing procedures based on the emotional data obtained by the emotion engine, including simplifying operations if the user is feeling stressed.

[1273] 8. Output Generation Methods

[1274] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[1275] Specific examples

[1276] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[1277] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[1278] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[1279] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[1280] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[1281] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[1282] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[1283] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[1284] 8. The device presents the generated report to the user, offering options to download or share it.

[1285] 9. The device will analyze the user's emotional state in real time through an emotion engine, and automatically adjust operations and data presentation methods if the user is feeling stressed or dissatisfied.

[1286] 10. The server performs flexible data processing based on the results of emotion analysis to improve the user experience.

[1287] This system significantly improves the efficiency of the previously manual process from data collection to output generation, enabling users to analyze data and make decisions more quickly.In addition, the introduction of an emotion engine enables flexible and optimal data manipulation that takes into account the user's emotional state.

[1288] The processing flow will be explained below.

[1289] Step 1:

[1290] The user uses the chat interface on the device to input information about the data storage destination (e.g., cloud storage URL, API key, DWH connection information, etc.) and provides it to the system.

[1291] Step 2:

[1292] The server establishes a connection to each data store based on the provided data store information, authenticates using an API or database client, and completes the connection.

[1293] Step 3:

[1294] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[1295] Step 4:

[1296] The user issues a command via the chat interface on the device saying, "I want you to compile quarterly sales data and create a report."

[1297] Step 5:

[1298] The server uses the parsed metadata to identify the required data based on user-specified criteria, such as files and table entries that match the criteria "sales data for the first quarter of last year."

[1299] Step 6:

[1300] The server efficiently retrieves the data to be collected using parallel processing techniques (for example, multi-threading or multi-processing) and aggregates the data.

[1301] Step 7:

[1302] The server aggregates the collected data into a standardized format (e.g., data frames or statistical data), and converts data from different formats into a consistent form.

[1303] Step 8:

[1304] The server then formats the integrated data into a user-specified format, for example, by aggregating the data by quarter and converting it into a table or graph format.

[1305] Step 9:

[1306] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[1307] Step 10:

[1308] Through the chat interface, users can give instructions to correct or add necessary data, such as "Please change the data for a specific period and recalculate it."

[1309] Step 11:

[1310] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[1311] Step 12:

[1312] The device runs an emotion engine that performs emotion analysis based on the user's input and behavior, for example, by determining the user's emotional state from input speed and context analysis.

[1313] Step 13:

[1314] The server automatically adjusts data collection and processing procedures based on the analysis results of the emotion engine. For example, if the user is feeling stressed, it will simplify the operation procedures.

[1315] Step 14:

[1316] The server generates reports and dashboards based on the final formatted data, which can include PDF reports, Excel sheets, and web-based dashboards.

[1317] Step 15:

[1318] The device displays the generated report to the user and provides options for downloading and sharing.

[1319] Step 16:

[1320] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[1321] These are the specific processing steps of a system incorporating the emotion engine of the present invention. This system streamlines the process from data collection to output generation, and also enables flexible responses tailored to the user's emotional state.

[1322] Example 2

[1323] 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."

[1324] In conventional data collection and processing systems, collecting data from different data storage locations and integrating the collected data takes time and effort, making it difficult for users to analyze data efficiently. Furthermore, data manipulation that ignores the user's emotional state causes operational complexity and stress, ultimately resulting in a poor user experience. This has led to a demand for more efficient data processing and improved user experience.

[1325] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata of each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for a user to issue instructions for data correction or addition through a chat interface, means for generating output based on the formatted data, means for adjusting data processing procedures by performing sentiment analysis on user inputs and actions, and means for simplifying user operations based on the sentiment analysis results. This enables efficient data collection and formatting, as well as flexible data manipulation that takes into account the user's emotional state and an improved user experience.

[1326] A "data destination" is a physical or virtual location where data is stored, such as cloud storage, a database, or a data warehouse.

[1327] "Metadata" refers to information about the attributes and structure of data, including the type of data, format, size, creation date, and so on.

[1328] "Analyzing" refers to breaking down data and metadata and converting them into an understandable form, thereby understanding the structure and content of the data.

[1329] "Collect" refers to extracting data based on specified conditions and gathering it in one place.

[1330] "Integrate" refers to combining multiple data sets into one standardized format.

[1331] "Format" refers to converting collected and integrated data into a specific form or format, and processing the data in accordance with the user's request.

[1332] "Chat interface" refers to an interactive user interface that allows a user to issue text-based instructions to a system and receive responses from the system.

[1333] "Output" refers to the results generated based on formatted data, including reports, dashboards, graphs, PDF files, etc.

[1334] "Emotion analysis" refers to identifying and analyzing a user's emotional state based on their input and behavior.

[1335] "Tuning" refers to changing the system's behavior based on the information obtained to achieve optimal results.

[1336] "Simplifying operations" refers to techniques for simplifying the process of users collecting, formatting, checking, and correcting data, thereby reducing the burden on users.

[1337] The present invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. A specific embodiment of the present invention will be described below.

[1338] Hardware and Software Use

[1339] This system mainly consists of a server and a terminal. The server is located on a cloud infrastructure, and the terminal is a personal computer or mobile device operated by a user. The server uses the following main software components:

[1340] Data Collection and Analysis: Data collection and analysis will be performed using Python programs and the Pandas library.

[1341] Concurrency: Use Python's multithreading library to collect data efficiently.

[1342] Data integration and shaping: Use Pandas to standardize data in different formats and shape it as needed.

[1343] Output generation: Creating reports and dashboards using Matplotlib or other data visualization libraries.

[1344] The device uses the following main software components:

[1345] Chat interface: Provides a front-end application using React.js to receive user instructions in real time.

[1346] Sentiment analysis: Analyze the user's input text using an NLP library (e.g., NLTK or SpaCy).

[1347] Specific examples

[1348] For example, a specific flow will be described in which a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report."

[1349] 1. The user instructs the chat interface on their device to "aggregate quarterly sales data and create a report."

[1350] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[1351] 3. The server collects the data for the specified quarter using parallel processing and integrates it into a Pandas data frame.

[1352] 4. The server groups the consolidated data by quarter and performs aggregations.

[1353] 5. The terminal displays a preview of the intermediate results in the chat interface and asks for the user's confirmation.

[1354] 6. The user communicates data corrections and additions to the server through the chat interface.

[1355] 7. The server reprocesses the data based on the correction instructions and generates a PDF report as the final output.

[1356] 8. The device will display a download link for the generated PDF report in the chat interface.

[1357] 9. The device uses an emotion analysis engine to analyze user input and simplify operations if the user is feeling stressed.

[1358] 10. The server adjusts the priority of data processing based on the emotion data to optimize the user experience.

[1359] Specific examples of prompts are as follows:

[1360] "I want you to compile quarterly sales data and create a report."

[1361] In this way, the present invention not only improves the efficiency of data collection and shaping, but also enables flexible data manipulation that takes into account the emotional state of the user.

[1362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1363] Step 1:

[1364] The user inputs the command "I want you to compile the sales data for each quarter and create a report" into the chat interface on the device. The input data becomes "I want you to compile the sales data for each quarter and create a report." Based on this input, the next data collection step is initiated.

[1365] Step 2:

[1366] The server connects to the cloud storage (e.g., AWS S3) or data warehouse where the sales data is stored and analyzes the metadata of the files and tables. The input data is the authentication information for the data storage destination (API key, URL, etc.) and the structure information of the storage destination. By analyzing the metadata, the structure and format of the data are understood and the information necessary for the next data collection is obtained.

[1367] Step 3:

[1368] The server efficiently collects data for the specified quarter from each data repository using parallel processing based on the parsed metadata. The input data is the metadata information and quarter specification, and the output data is the collected raw sales data. Parallel processing speeds up data collection, ingesting data from multiple API endpoints simultaneously.

[1369] Step 4:

[1370] The server consolidates the collected data into a standardized format. Specifically, it converts different file formats (e.g., CSV, JSON) into a data frame using Pandas. The input data is the collected raw data, and the output data is the consolidated data frame. This allows data from different sources to be converted into a consistent format.

[1371] Step 5:

[1372] The server groups the consolidated data by quarter and performs the necessary aggregation operations to reshape it. Specifically, it uses the grouping and aggregation functions of Pandas. The input data is a consolidated data frame, and the output data is data reshaped by quarter. This allows for efficient analysis of data for a specific period.

[1373] Step 6:

[1374] The terminal displays the intermediate results of the formatted data on the chat interface and requests the user's confirmation. The displayed information includes a preview of the quarterly summary results. The input data is the formatted data, and the output data is a data preview displayed to the user for confirmation.

[1375] Step 7:

[1376] The user sends instructions to the server via the chat interface to correct or add data. For example, the user might say, "Please correct the data for the second quarter." The input data is the user's correction instruction, and the output data is the correction instruction itself.

[1377] Step 8:

[1378] The server reprocesses the data in response to the user's correction instructions. Specifically, it uses Pandas to correct the data frame and perform recalculation. The input data is the correction instructions and the data to be corrected, and the output data is the corrected data frame.

[1379] Step 9:

[1380] The server generates the quarterly sales report as the final output and outputs it in PDF or other specified format. Specifically, it generates a graph from the data frame using Matplotlib and embeds it in a PDF. The input data is the modified data frame, and the output data is the final report file.

[1381] Step 10:

[1382] The terminal displays a download link for the generated PDF report on the chat interface and presents it to the user. The input data is the generated report file, and the output data is the download link.

[1383] Step 11:

[1384] The device uses an emotion analysis engine to analyze the user's input and simplifies the operation if the user is feeling stressed or dissatisfied. Specifically, it performs text analysis and simplifies the next step based on the results. The input data is the user's input text, and the output data is the emotion analysis result.

[1385] Step 12:

[1386] The server modifies the data processing procedures and user interface based on the emotion analysis results, simplifying user operations. The input data is the emotion analysis results, and the output data is the adjusted processing procedures and user interface settings. This process optimizes the user experience and improves work efficiency.

[1387] The above are the specific processing steps and operations of this system.

[1388] (Application example 2)

[1389] 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."

[1390] On modern online shopping sites, it is difficult for users to find the right product for them from the vast number of products available. Furthermore, typical recommendation systems are based on the user's recent behavior and purchase history, and are unable to suggest products that take into account the user's emotional state. Furthermore, data collection, formatting, and output generation are often done manually, which can often be perceived as inefficient. To solve these problems, a data processing system that also takes into account the user's emotional state is needed.

[1391] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1392] In this invention, the server includes a means for connecting to different data storage locations and analyzing the metadata of each data storage location, a means for automatically collecting necessary data based on the analyzed metadata, and a means for integrating the collected data and formatting it into a standardized format, which enables product recommendations based on the user's emotional state and efficient data collection, formatting, and output generation.

[1393] "Data storage" refers to the system or storage that stores data stored in different locations.

[1394] "Metadata" is additional data that contains information about data and describes the structure and attributes of the data.

[1395] An "automatic collection means" is a method or device for automatically obtaining necessary data from a designated data storage location without user intervention.

[1396] A "means for converting data into a standardized format" is a method or device for converting data stored in different formats into a single unified format.

[1397] A "chat interface" is an interactive user interface through which a user can enter text and interact with the system.

[1398] An "emotion engine" is software or hardware that analyzes a user's input and actions to determine their emotional state at that time.

[1399] An "output generating means" is a method or device that generates reports or visualizations based on the formatted data.

[1400] A "means for generating product recommendations" is a method or device that suggests suitable products based on the user's emotional state and past data.

[1401] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. Specific embodiments for realizing this system are described below.

[1402] System Configuration

[1403] The system mainly consists of the following elements:

[1404] 1. How to connect to the data storage location:

[1405] The server connects to the data storage destination using information such as an API key and connection URL provided by the user. For example, it authenticates and establishes a connection to different data storage destinations such as cloud storage services and data warehouses.

[1406] 2. Metadata analysis methods:

[1407] The server analyzes the metadata of the connected data storage destination to understand the data structure and format, and identifies the required data based on the analysis results.

[1408] 3. Automated collection of required data:

[1409] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[1410] 4. Data integration methods:

[1411] The server consolidates the collected data into a single standardized format, for example by converting data from different file formats into a data frame.

[1412] 5. Data Formatting Methods:

[1413] The server then processes the combined data in a user-specified format, such as by aggregating it by category or converting it into a specific format.

[1414] 6. Chat Interface:

[1415] The terminal provides a chat interface to the user, allowing the user to check data and input instructions in real time. The user can correct data or give additional instructions through the chat.

[1416] 7. Emotion Engine:

[1417] The device is equipped with an emotion engine that performs emotion analysis based on the user's input and behavior. For example, it analyzes the user's emotional state based on the context of the text, input speed, typing intensity, etc. The server automatically adjusts data collection and formatting procedures based on the emotion data obtained by the emotion engine.

[1418] 8. Output Generation Means:

[1419] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[1420] 9. Product recommendation generation method:

[1421] The server suggests suitable products based on the user's emotional state and past data, utilizing algorithms based on emotion engines and data refinement methods.

[1422] Example

[1423] For example, there is a smartphone application called "Smart Shopping Assistant" for an online shopping site. This application works as follows:

[1424] 1. The user types "I'm looking for soothing products" into the chat interface on their device.

[1425] 2. The server collects data from different product data APIs and parses the metadata to extract the required data.

[1426] 3. The analyzed data is collected in parallel and formatted into a standardized format.

[1427] 4. The emotion engine analyzes the user's input and determines that it is a negative state.

[1428] 5. Based on this emotional data, relaxation goods and aroma products are recommended preferentially.

[1429] 6. Present product recommendations to users through the chat interface and offer purchasing options.

[1430] In this way, it becomes possible to recommend products based on the user's emotional state, as well as to efficiently collect, format, and generate output from data.

[1431] Prompt Sentence Examples

[1432] How are you feeling right now? What products are you looking for?

[1433] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1434] Step 1:

[1435] Connecting to a data storage location

[1436] The server receives the API key and connection URL information provided by the user as input and connects to each data storage destination. Specifically, it authenticates and establishes a connection with different data storage destinations such as cloud storage services and data warehouses. This prepares the server to retrieve the required data from the data storage destination.

[1437] Step 2:

[1438] Metadata analysis

[1439] The server analyzes the metadata of the connected data store, which includes file structure, database schema, data format, etc. It takes the metadata as input and understands the overall structure of the data, which forms the basis for identifying what data is needed.

[1440] Step 3:

[1441] Collection of necessary data

[1442] The server automatically collects the necessary data based on the analyzed metadata. It receives condition settings as input and efficiently collects the necessary data from the data storage location using parallel processing technology. The collected data is converted into a standardized format, allowing data in a unified format to be obtained from diverse data sources.

[1443] Step 4:

[1444] Data integration and formatting

[1445] The server aggregates the collected data and formats it into a standardized format. The input is the raw data collected, and the output is a unified data frame. During this process, data is aggregated by category and converted into a specific format to ensure consistency.

[1446] Step 5:

[1447] Emotion analysis

[1448] The device performs emotion analysis based on the user's input and behavior. For example, it displays prompts such as "How are you feeling right now? What kind of product are you looking for?" and receives user input. The input is text data, which the emotion engine analyzes and outputs the user's emotional state. This includes analyzing the context of the text and the speed of input.

[1449] Step 6:

[1450] Generate product recommendations

[1451] The server generates product recommendations based on the analysis results of the emotion engine according to the user's emotional state. The input is the results of the emotion analysis and formatted data, and the output is a product list presented to the user. For example, if the user is feeling stressed, relaxation goods and aroma products will be recommended first.

[1452] Step 7:

[1453] Output through the chat interface

[1454] The terminal displays the generated product recommendations to the user through a chat interface. The input is the generated product list, and the output is the display to the user on the terminal. The user can provide further instructions through this interface, and the system will reprocess the data accordingly.

[1455] Step 8:

[1456] Generating the final output

[1457] The server generates the final output and provides it to the user as needed, such as a report or dashboard. The input is the formatted data and additional user instructions, and the output is a PDF report or a web-based dashboard, allowing the user to see the results of the data processing in a tangible way.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] [Fourth embodiment]

[1462] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1463] 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.

[1464] 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).

[1465] 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.

[1466] 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.

[1467] 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).

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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.

[1472] 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.

[1473] 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.

[1474] 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."

[1475] This invention is a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, thereby significantly reducing the time and effort required to collect and format the data.

[1476] System Configuration

[1477] The system mainly consists of the following elements:

[1478] 1. Means of connection to the data storage destination

[1479] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[1480] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[1481] 2. Metadata Analysis Methods

[1482] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[1483] 3. Automatic collection of necessary data

[1484] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[1485] 4. Data integration methods

[1486] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[1487] 5. Data Formatting Methods

[1488] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[1489] 6. Chat Interface

[1490] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[1491] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[1492] 7. Output Generation Methods

[1493] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[1494] Specific examples

[1495] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[1496] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[1497] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[1498] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[1499] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[1500] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[1501] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[1502] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[1503] 8. The device presents the generated report to the user, offering options to download or share it.

[1504] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, enabling users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[1505] The processing flow will be explained below.

[1506] Step 1:

[1507] The user inputs information about the data storage destination to be used in the chat interface on the device (for example, the URL of the cloud storage, the API key, the connection information of the DWH, etc.) and provides it to the system.

[1508] Step 2:

[1509] The server establishes a connection to each data store based on the provided information, authenticates using an API or database client, and maintains the connection.

[1510] Step 3:

[1511] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[1512] Step 4:

[1513] The user instructs the chat interface on the device to "collect specific data and create a report."

[1514] Step 5:

[1515] The server identifies data that matches the conditions specified by the user based on the analyzed metadata, for example, files and table entries that match the condition "sales data for this month."

[1516] Step 6:

[1517] The server efficiently retrieves the data to be collected using parallel processing techniques (multi-threading or multi-processing) and aggregates the data.

[1518] Step 7:

[1519] The server aggregates the collected data into a standardized format (e.g., a data frame), resolving inconsistencies and missing values ​​between different formats to create a consistent dataset.

[1520] Step 8:

[1521] The server then formats the integrated data into a user-specified format. For example, it can aggregate sales data by day, month, or category and format it in a table or graph format.

[1522] Step 9:

[1523] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[1524] Step 10:

[1525] The user can issue instructions to correct or add data through a chat interface, such as "I want the data for a specific period to be changed and re-aggregated."

[1526] Step 11:

[1527] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[1528] Step 12:

[1529] The server generates the final reports and dashboards based on the corrected data, which can be PDF reports, Excel sheets, or web-based dashboards.

[1530] Step 13:

[1531] The device presents the generated report to the user and offers options to download or share it.

[1532] Step 14:

[1533] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[1534] Example 1

[1535] 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."

[1536] Many companies and organizations are faced with the need to integrate, analyze, and utilize data distributed across different data storage locations. Traditionally, manually collecting data and integrating and formatting it has required time and effort, and there is a high risk of manual error. Therefore, there is a need for a method to process data efficiently and accurately and generate output quickly. Furthermore, a user-friendly interface is required to correct data and provide additional instructions in real time, and a concrete solution for this is needed.

[1537] 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.

[1538] In this invention, the server includes means for connecting to different data storage locations and analyzing metadata from each data storage location, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for issuing instructions for data correction or addition through a user interface on a terminal, means for generating a report or dashboard based on the formatted data, means for making the generated report or dashboard downloadable or sharable, means for collecting data in parallel based on the analyzed metadata, means for accepting data processing instructions based on natural language prompts through a chat interface on the terminal using a generative AI model, and means for inputting and confirming data on the terminal in real time. This allows users to efficiently and accurately integrate and format data and quickly generate output. Furthermore, the ability to check and correct data in real time enables flexible and accurate data utilization.

[1539] A "data destination" is a storage service or database where different data is stored.

[1540] "Metadata" refers to additional information about data, including information about the data's structure, format, data type, and so on.

[1541] "Automatic collection means" refers to a system that uses a program to continuously and efficiently collect the necessary data based on analyzed metadata and in accordance with conditions specified by the user.

[1542] "Means of integration and standardization" refers to the process of converting data of different formats and structures into a single common format and unifying it.

[1543] A "user interface" refers to a screen or operation panel that allows a user to interact with and operate a system.

[1544] A "report" or "dashboard" is a document or screen that visually displays analytical results or information created based on collected and formatted data.

[1545] "Real-time" is a term that refers to a state in which processing results are obtained almost immediately after data is input.

[1546] "Parallel processing" refers to the technology of simultaneously executing multiple data processing tasks to efficiently collect and format data.

[1547] A "generative AI model" is an algorithm that has been trained to automatically analyze and process data using AI technology.

[1548] A "prompt sentence" is an instruction or question entered by a user in natural language.

[1549] This invention is a system that collects data from different data storage locations, integrates and formats the data based on user instructions, and generates output. This system is composed of multiple hardware and software elements.

[1550] Basic system configuration

[1551] 1. Means of connection to the data storage destination

[1552] The user inputs information about the data storage destination (such as an API key, a connection URL, and query conditions) through a user interface on the terminal. Any personal computer, smartphone, or tablet can be used as the terminal.

[1553] The server connects to the specified data storage location (such as a cloud storage service or data warehouse) based on the information provided by the user. The server software uses a programming language such as Python or Java, and connects to the API endpoint using an HTTP request and performs authentication.

[1554] 2. Metadata Analysis Methods

[1555] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format (for example, column information for JSON or CSV files). It obtains and analyzes the metadata using Python's Pandas library, etc.

[1556] 3. Automatic collection of necessary data

[1557] The server automatically collects the necessary data according to the conditions specified by the user based on the analyzed metadata, and efficiently retrieves the data using Python parallel processing libraries (such as multiprocessing and asyncio).

[1558] 4. Data integration methods

[1559] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data from different file formats and database tables into a single data frame.

[1560] 5. Data Formatting Methods

[1561] The server then formats the aggregated data according to user requirements, including categorical aggregations and conversions to specific formats, using the Python Pandas and NumPy libraries.

[1562] 6. Chat Interface

[1563] The terminal provides a chat interface that allows users to check data and input instructions in real time. This interface is implemented using a web application framework (e.g., Flask or Django).

[1564] Users can modify data or provide additional instructions through chat, including instructions in natural language.

[1565] 7. Output Generation Methods

[1566] The server generates reports and dashboards based on the formatted data using Python's Matplotlib and Seaborn libraries, and outputs PDF and Excel files.

[1567] 8. Real-time processing methods

[1568] The device provides real-time data entry and validation, allowing users to receive immediate feedback and confirm that their data reflects their intended purpose.

[1569] Specific examples

[1570] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[1571] 1. The user requests, via the chat interface on their device, that they "collect quarterly sales data and create a report." The prompt reads, "Collect quarterly sales data and create a PDF report. The data should be for the first quarter of 2023 and include breakdowns by sales category."

[1572] 2. The server connects to the cloud storage (e.g., Amazon S3) or data warehouse (e.g., Google BigQuery) where the sales data is stored and analyzes the metadata of the files and tables.

[1573] 3. The server collects data for the specified quarter from each data storage location and efficiently ingests the data using parallel processing using Python's asyncio.

[1574] 4. The server uses Python's Pandas library to convert the collected data into a unified data frame and format it into quarterly segments.

[1575] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[1576] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[1577] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[1578] 8. The device presents the generated report to the user, offering options to download or share it.

[1579] This system significantly improves the efficiency of the process from data collection to output generation, which was previously done manually, allowing users to analyze data and make decisions more quickly.In addition, data can be checked and corrected in real time, allowing for flexible and accurate document creation.

[1580] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1581] Step 1:

[1582] The user logs in to the user interface on the device and enters information about the data storage destination (such as an API key, connection URL, query conditions, etc.). This input information is sent to the server.

[1583] Input: API key for data storage destination, connection URL, query conditions

[1584] Output: Request sent to server

[1585] Specific behavior:

[1586] A user types into the chat interface, "Please aggregate our quarterly sales data and create a PDF report," along with details of where the data will be stored (e.g., Google BigQuery API key XYZ123).

[1587] Step 2:

[1588] The server connects to the specified data store based on the information provided by the user, and uses an HTTP request to connect to the API endpoint and perform authentication.

[1589] Input: User-provided data storage location information

[1590] Output: Authentication token, connection status

[1591] Specific behavior:

[1592] The server sends an authentication request to the Google BigQuery API, receives an authentication token in response, checks the connection status, and notifies the user.

[1593] Step 3:

[1594] The server analyzes the metadata of the connected data storage file or database to obtain the data structure and format using the Python Pandas library.

[1595] Input: Authentication token for data storage destination

[1596] Output: Metadata (column names, data types, etc.)

[1597] Specific behavior:

[1598] The server retrieves table information from BigQuery and lists the column names and data types. For example, it retrieves column information for the "sales" table.

[1599] Step 4:

[1600] The server automatically collects the necessary data according to the conditions (query conditions) specified by the user based on the analyzed metadata, and uses Python's asyncio to efficiently retrieve data through parallel processing.

[1601] Input: User query criteria, metadata

[1602] Output: Collected dataset

[1603] Specific behavior:

[1604] The server sends a query such as "SELECT FROM sales WHERE quarter='Q1'" to BigQuery and receives the results. Data is collected from multiple tables in parallel.

[1605] Step 5:

[1606] The server consolidates the collected data into a standardized format, using the Python Pandas library to combine data of different formats and structures into a single data frame.

[1607] Input: Collected dataset

[1608] Output: Unified data frame

[1609] Specific behavior:

[1610] The server converts the data from each table into a Pandas data frame, and then combines multiple data frames into a single dataset. For example, merging sales data with customer data.

[1611] Step 6:

[1612] The server then formats the integrated data according to user requests, such as by aggregating data by category or converting it into a specific format, using the Python Pandas and NumPy libraries.

[1613] Input: unified data frame

[1614] Output: Formatted data

[1615] Specific behavior:

[1616] The server aggregates the quarterly sales data using Pandas and adds a new calculated column. For example, a "total_sales" column is created to calculate the total sales for each quarter.

[1617] Step 7:

[1618] The terminal displays the formatted data as an intermediate result to the user and asks for confirmation.

[1619] Input: Formatted data

[1620] Output: Intermediate results that are displayed to the user

[1621] Specific behavior:

[1622] A data summary or sample of the intermediate results is displayed on the chat interface, along with a message asking, "Is this data okay?"

[1623] Step 8:

[1624] The user can modify or add data through the chat interface, using natural language prompts.

[1625] Input: User instructions

[1626] Output: Corrected or added data

[1627] Specific behavior:

[1628] The user enters instructions in the chat window, such as "Please also include column X in the calculation," and the server reprocesses the data based on those instructions.

[1629] Step 9:

[1630] The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format using Pandas' to_excel or Matplotlib's PDF export function.

[1631] Input: Corrected formatted data

[1632] Output: Final output (PDF or Excel)

[1633] Specific behavior:

[1634] The server-generated reports are visualized using Matplotlib and Seaborn, and an Excel file is created using Pandas' to_excel method.

[1635] Step 10:

[1636] The device presents the generated output to the user, offering options to download or share it.

[1637] Input: Final Output

[1638] Output: Download link or sharing option for the output

[1639] Specific behavior:

[1640] Display a link to the generated PDF report in the chat window and provide a "Download Report" button.

[1641] (Application example 1)

[1642] 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."

[1643] Modern logistics centers have a variety of data sources (inventory management systems, delivery management systems, order management systems, etc.), and there is a need to manage and operate each data in an integrated manner. However, manually collecting, analyzing, integrating, and displaying data from different sources in various output formats requires a great deal of time and effort. In addition, it is difficult to check data and respond to instructions in real time, making it difficult to achieve efficient logistics management.

[1644] 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.

[1645] In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata from each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for users to enter instructions for data corrections and additions via a chat interface on their smartphones, and means for generating output in real time based on the formatted data and displaying it in dashboard format, thereby enabling data integration from different data sources and real-time logistics management.

[1646] "Different data storage locations" refers to multiple locations where data is stored, such as cloud storage or databases.

[1647] "Metadata" refers to data that includes information about the data itself, such as the format, structure, and attribute information of the data.

[1648] "Analysis" refers to the process of deconstructing and interpreting collected metadata and other data to understand its structure and content.

[1649] "Automatic collection" refers to the act of collecting data by a system without human intervention.

[1650] "Integration" means bringing together different collected data into one standardized format.

[1651] "Formatting into a standardized format" means converting various data formats and structures into a unified format.

[1652] A "smartphone" refers to a multi-function mobile phone, a device capable of wireless communication and internet access.

[1653] A "chat interface" is an interface that allows users to interact with the system to check data, give instructions, etc.

[1654] "Instructions for correction or addition" refers to the act of a user issuing instructions to the system to change existing data or add new data.

[1655] "Real-time" refers to a situation in which user actions are reflected immediately without any time delay.

[1656] The "dashboard format" is a format in which data is visually organized and displayed so that the current situation can be grasped at a glance.

[1657] "Output" refers to the reports and data visualizations that are generated based on the formatted data.

[1658] MODE FOR CARRYING OUT THE INVENTION

[1659] This invention is a system that efficiently collects, integrates, and formats data from different data sources in logistics centers, allowing logistics managers to check and modify data in real time using their smartphones and make decisions quickly.

[1660] System Configuration

[1661] The system consists of the following elements:

[1662] 1. Server

[1663] The server receives data storage information provided by the user and connects to different data storage locations such as cloud storage or databases. For example, the user can enter an API key or connection URL, and the server uses that information to authenticate with the data storage location. The connection is established using the Python requests library.

[1664] 2. Metadata Analysis

[1665] The server analyzes the metadata of each data storage location to understand the data structure and format. Specifically, it uses the Python pandas library to retrieve and analyze the metadata.

[1666] 3. Automatic data collection

[1667] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata.To efficiently collect data using parallel processing techniques, the Python multiprocessing library is used.

[1668] 4. Data integration

[1669] The server consolidates the collected data into a standardized format and converts data from different formats (e.g., CSV, JSON) into a single data frame. Again, this consolidation is performed using the pandas library.

[1670] 5. Data Formatting

[1671] The server formats the integrated data into a format specified by the user, generating aggregated data for each category, for example.

[1672] 6. Generating Output

[1673] Based on the formatted data, the server generates dashboard-style output and provides it to users in real time. The dashboard is created using the Python matplotlib library.

[1674] 7. User Interface

[1675] The device (smartphone) provides a chat interface to the user, allowing them to check data and input instructions. The front end is implemented using React Native and the back end is implemented using Flask.

[1676] Program processing

[1677] Next, the details of the processing by the hardware and software of each element will be described.

[1678] Connecting and collecting data: The server uses the Python requests library to connect to each data store based on the API key and connection URL entered by the user. It then analyzes the metadata of the data store using the pandas library and automatically collects the required data.

[1679] Example: Enter the API key and URL of the inventory management system of the distribution center, and the server will connect based on that.

[1680] Example prompt sentence:

[1681] "Please enter the API key for your inventory management system."

[1682] Please enter the URL to connect to.

[1683] Data integration and transformation: The collected data is integrated into a single data frame using the pandas library. The data is then transformed and converted into the required format based on the user's instructions.

[1684] Example: Taking inventory and order data in different formats and transforming it into a unified data frame.

[1685] Example prompt sentence:

[1686] "Standardize the format of your data."

[1687] "Generate aggregate data by category."

[1688] Output Generation: Based on the consolidated and formatted data, the server generates a dashboard using Python's matplotlib library, which is displayed in real time through the user interface.

[1689] Example: Generate a dashboard that visualizes the current inventory status based on formatted inventory and order data.

[1690] Example prompt sentence:

[1691] "Generate a dashboard based on inventory data."

[1692] User interface: The device (smartphone) is equipped with a chat interface developed with React Native, through which users can correct or add data in real time.Flask is used as the backend to ensure that data is updated in real time.

[1693] Example: A user issues a command such as "Please update the latest inventory information," and the server formats the data accordingly and displays an updated dashboard.

[1694] Example prompt sentence:

[1695] View the latest inventory information

[1696] Please update the delivery status

[1697] The system streamlines data collection, integration, formatting and output generation, and enables real-time data verification and correction, facilitating fast and accurate data management and decision-making in logistics centers.

[1698] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1699] Step 1:

[1700] When a user uses a device (smartphone) to enter the API key and connection URL of the data storage destination, the data storage destination information is sent to the server. Based on the entered data storage destination information, the server uses the Python requests library to establish a connection to each data storage destination. Specifically, by including the API key and URL in the request, authentication to the cloud storage or database is performed. This allows the server to access the data from each data storage destination.

[1701] Input: API key for data storage destination, connection URL

[1702] Output: Establish connection to each data storage location

[1703] Step 2:

[1704] The server retrieves metadata from the connected data store and analyzes it using the Python pandas library. The metadata includes information about the data format, structure, and attributes, and analyzing this information provides an overall understanding of the data. Specifically, the server reads the file using the pandas read_json or read_csv method.

[1705] Input: Metadata for each data storage location

[1706] Output: Parsed metadata

[1707] Step 3:

[1708] The server automatically collects the necessary data based on the analyzed metadata. Here, the Python multiprocessing library is used to efficiently collect data using parallel processing techniques. Specifically, multiple processes are launched, and each process collects data from a different data storage location. This improves the speed at which data is collected.

[1709] Input: Parsed metadata

[1710] Output: Required data collected

[1711] Step 4:

[1712] The server consolidates the collected data and formats it into a standardized format. Because data collected from multiple data storage locations may have different formats and structures, it combines the data into a single data frame using the Python pandas library. Specifically, the data is consolidated using the pandas concat and merge methods.

[1713] Input: Required data collected

[1714] Output: Unified data frame

[1715] Step 5:

[1716] Users can use their smartphones to modify or add data via a chat interface. The chat interface is based on React Native, and the user's input is sent to the server. For example, a user might enter a command such as "Please update the latest inventory information."

[1717] Input: Corrections and additional instructions from the user

[1718] Output: Instructions sent to the server

[1719] Step 6:

[1720] The server modifies or adds data based on user instructions. It uses the Python pandas library to reprocess data according to the instructions. For example, if a user requests that the inventory quantity of a specific product be updated, the server searches for the relevant data and performs the update process.

[1721] Input: User corrections and additional instructions

[1722] Output: Corrected and added data

[1723] Step 7:

[1724] The server generates dashboard-style output based on the formatted data. It uses the Python matplotlib library to visualize the data and display it in a dashboard format. Specifically, it generates graphs and charts and creates a visual representation of them.

[1725] Input: Corrected and added data

[1726] Output: Dashboard-style output

[1727] Step 8:

[1728] The device (smartphone) provides the generated dashboard to the user in real time, allowing the user to view it and provide additional instructions as needed. The front end, implemented using React Native, immediately reflects data updates from the server.

[1729] Input: Dashboard output

[1730] Output: The dashboard as seen by the user

[1731] The above processing steps make data management at logistics centers more efficient and enable real-time data checking and decision-making.

[1732] 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.

[1733] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. This not only improves the efficiency of data collection, formatting, and output, but also enables more appropriate responses by taking the user's emotional state into consideration.

[1734] System Configuration

[1735] The system mainly consists of the following elements:

[1736] 1. Means of connection to the data storage destination

[1737] The user inputs data storage destination information (such as an API key or connection URL) on the device and provides it to the system.

[1738] The server uses the provided information to establish a connection with the data store, for example, authenticating to different data stores such as cloud storage services or data warehouses.

[1739] 2. Metadata Analysis Methods

[1740] The server analyzes the metadata of the files and databases in the connected data storage destination to understand the data structure and format.

[1741] 3. Automatic collection of necessary data

[1742] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[1743] 4. Data integration methods

[1744] The server consolidates the collected data into a single standardized format, for example, converting data from different file formats (CSV, JSON, etc.) into a data frame.

[1745] 5. Data Formatting Methods

[1746] The server then processes the aggregated data according to the user's specifications, which may include aggregating data by category or converting it into a specific format.

[1747] 6. Chat Interface

[1748] The terminal provides a chat interface to the user, allowing for real-time review of data and input of instructions.

[1749] Users can modify data or give additional instructions through chat, allowing for flexible data manipulation.

[1750] 7. Emotion Engine

[1751] The device is equipped with an emotion engine that performs emotion analysis based on user input and behavior, such as text context, input speed, and typing intensity, to determine the user's emotional state.

[1752] The server automatically adjusts data collection and processing procedures based on the emotional data obtained by the emotion engine, including simplifying operations if the user is feeling stressed.

[1753] 8. Output Generation Methods

[1754] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[1755] Specific examples

[1756] For example, when a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report," the specific flow is as follows:

[1757] 1. The user requests through the chat interface on their device that they want the sales data for each quarter compiled and a report created.

[1758] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[1759] 3. The server collects data for the specified quarter from each data storage location, efficiently ingesting the data using parallel processing.

[1760] 4. The server consolidates the collected data into a standardized format and organizes it into quarterly segments.

[1761] 5. The terminal displays the formatted data to the user as an intermediate result and asks for confirmation.

[1762] 6. The user issues instructions to correct or add data through the chat interface, and the server reprocesses the data based on those instructions.

[1763] 7. The server creates a quarterly sales report as the final output and outputs it in PDF or Excel format.

[1764] 8. The device presents the generated report to the user, offering options to download or share it.

[1765] 9. The device will analyze the user's emotional state in real time through an emotion engine, and will automatically adjust operations and data presentation methods if the user is feeling stressed or dissatisfied.

[1766] 10. The server performs flexible data processing based on the results of emotion analysis to improve the user experience.

[1767] This system significantly improves the efficiency of the previously manual process from data collection to output generation, enabling users to analyze data and make decisions more quickly.In addition, the introduction of an emotion engine enables flexible and optimal data manipulation that takes into account the user's emotional state.

[1768] The processing flow will be explained below.

[1769] Step 1:

[1770] The user uses the chat interface on the device to input information about the data storage destination (e.g., cloud storage URL, API key, DWH connection information, etc.) and provides it to the system.

[1771] Step 2:

[1772] The server establishes a connection to each data store based on the provided data store information, authenticates using an API or database client, and completes the connection.

[1773] Step 3:

[1774] The server scans the metadata of files and databases in connected data stores and analyzes their structure and format, such as collecting file extensions, table schemas, and column information.

[1775] Step 4:

[1776] The user issues a command via the chat interface on the device saying, "I want you to compile quarterly sales data and create a report."

[1777] Step 5:

[1778] The server uses the parsed metadata to identify the required data based on user-specified criteria, such as files and table entries that match the criteria "sales data for the first quarter of last year."

[1779] Step 6:

[1780] The server efficiently retrieves the data to be collected using parallel processing techniques (for example, multi-threading or multi-processing) and aggregates the data.

[1781] Step 7:

[1782] The server aggregates the collected data into a standardized format (e.g., data frames or statistical data), and converts data from different formats into a consistent form.

[1783] Step 8:

[1784] The server then formats the integrated data into a user-specified format, for example, by aggregating the data by quarter and converting it into a table or graph format.

[1785] Step 9:

[1786] The terminal presents the formatted data and intermediate results to the user through a chat interface and asks for confirmation, "Is this format OK?"

[1787] Step 10:

[1788] Through the chat interface, users can give instructions to correct or add necessary data, such as "Please change the data for a specific period and recalculate it."

[1789] Step 11:

[1790] The server re-executes the data manipulation based on the user's instructions and reformats the modified data.

[1791] Step 12:

[1792] The device runs an emotion engine that performs emotion analysis based on the user's input and behavior, for example, by determining the user's emotional state from input speed and context analysis.

[1793] Step 13:

[1794] The server automatically adjusts data collection and processing procedures based on the analysis results of the emotion engine. For example, if the user is feeling stressed, it will simplify the operation procedures.

[1795] Step 14:

[1796] The server generates reports and dashboards based on the final formatted data, which can include PDF reports, Excel sheets, and web-based dashboards.

[1797] Step 15:

[1798] The device displays the generated report to the user and provides options for downloading and sharing.

[1799] Step 16:

[1800] The server generates logs of all processing steps and stores them for future troubleshooting and analysis.

[1801] These are the specific processing steps of a system incorporating the emotion engine of the present invention. This system streamlines the process from data collection to output generation, and also enables flexible responses tailored to the user's emotional state.

[1802] Example 2

[1803] 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."

[1804] In conventional data collection and processing systems, collecting data from different data storage locations and integrating the collected data takes time and effort, making it difficult for users to analyze data efficiently. Furthermore, data manipulation that ignores the user's emotional state causes operational complexity and stress, ultimately resulting in a poor user experience. This has led to a demand for more efficient data processing and improved user experience.

[1805] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for connecting to different data storage destinations and analyzing metadata of each data storage destination, means for automatically collecting necessary data based on the analyzed metadata, means for integrating the collected data and formatting it into a standardized format, means for a user to issue instructions for data correction or addition through a chat interface, means for generating output based on the formatted data, means for adjusting data processing procedures by performing sentiment analysis on user inputs and actions, and means for simplifying user operations based on the sentiment analysis results. This enables efficient data collection and formatting, as well as flexible data manipulation that takes into account the user's emotional state and an improved user experience.

[1806] A "data destination" is a physical or virtual location where data is stored, such as cloud storage, a database, or a data warehouse.

[1807] "Metadata" refers to information about the attributes and structure of data, including the type of data, format, size, creation date, and so on.

[1808] "Analyzing" refers to breaking down data and metadata and converting them into an understandable form, thereby understanding the structure and content of the data.

[1809] "Collect" refers to extracting data based on specified conditions and gathering it in one place.

[1810] "Integrate" refers to combining multiple data sets into one standardized format.

[1811] "Format" refers to converting collected and integrated data into a specific form or format, and processing the data in accordance with the user's request.

[1812] "Chat interface" refers to an interactive user interface that allows a user to issue text-based instructions to a system and receive responses from the system.

[1813] "Output" refers to the results generated based on formatted data, including reports, dashboards, graphs, PDF files, etc.

[1814] "Emotion analysis" refers to identifying and analyzing a user's emotional state based on their input and behavior.

[1815] "Tuning" refers to changing the system's behavior based on the information obtained to achieve optimal results.

[1816] "Simplifying operations" refers to techniques for simplifying the process of users collecting, formatting, checking, and correcting data, thereby reducing the burden on users.

[1817] The present invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. A specific embodiment of the present invention will be described below.

[1818] Hardware and Software Use

[1819] This system mainly consists of a server and a terminal. The server is located on a cloud infrastructure, and the terminal is a personal computer or mobile device operated by a user. The server uses the following main software components:

[1820] Data Collection and Analysis: Data collection and analysis will be performed using Python programs and the Pandas library.

[1821] Concurrency: Use Python's multithreading library to collect data efficiently.

[1822] Data integration and shaping: Use Pandas to standardize data in different formats and shape it as needed.

[1823] Output generation: Creating reports and dashboards using Matplotlib or other data visualization libraries.

[1824] The device uses the following main software components:

[1825] Chat interface: Provides a front-end application using React.js to receive user instructions in real time.

[1826] Sentiment analysis: Analyze the user's input text using an NLP library (e.g., NLTK or SpaCy).

[1827] Specific examples

[1828] For example, a specific flow will be described in which a sales department employee (user) performs an operation to "aggregate quarterly sales data and create a report."

[1829] 1. The user instructs the chat interface on their device to "aggregate quarterly sales data and create a report."

[1830] 2. The server connects to the cloud storage or data warehouse where the sales data is stored and analyzes the metadata of the files and tables.

[1831] 3. The server collects the data for the specified quarter using parallel processing and integrates it into a Pandas data frame.

[1832] 4. The server groups the consolidated data by quarter and performs aggregations.

[1833] 5. The terminal displays a preview of the intermediate results in the chat interface and asks for the user's confirmation.

[1834] 6. The user communicates data corrections and additions to the server through the chat interface.

[1835] 7. The server reprocesses the data based on the correction instructions and generates a PDF report as the final output.

[1836] 8. The device will display a download link for the generated PDF report in the chat interface.

[1837] 9. The device uses an emotion analysis engine to analyze user input and simplify operations if the user is feeling stressed.

[1838] 10. The server adjusts the priority of data processing based on the emotion data to optimize the user experience.

[1839] Specific examples of prompts are as follows:

[1840] "I want you to compile quarterly sales data and create a report."

[1841] In this way, the present invention not only improves the efficiency of data collection and shaping, but also enables flexible data manipulation that takes into account the emotional state of the user.

[1842] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1843] Step 1:

[1844] The user inputs the command "I want you to compile the sales data for each quarter and create a report" into the chat interface on the device. The input data becomes "I want you to compile the sales data for each quarter and create a report." Based on this input, the next data collection step is initiated.

[1845] Step 2:

[1846] The server connects to the cloud storage (e.g., AWS S3) or data warehouse where the sales data is stored and analyzes the metadata of the files and tables. The input data is the authentication information for the data storage destination (API key, URL, etc.) and the structure information of the storage destination. By analyzing the metadata, the structure and format of the data are understood and the information necessary for the next data collection is obtained.

[1847] Step 3:

[1848] The server efficiently collects data for the specified quarter from each data repository using parallel processing based on the parsed metadata. The input data is the metadata information and quarter specification, and the output data is the collected raw sales data. Parallel processing speeds up data collection, ingesting data from multiple API endpoints simultaneously.

[1849] Step 4:

[1850] The server consolidates the collected data into a standardized format. Specifically, it converts different file formats (e.g., CSV, JSON) into a data frame using Pandas. The input data is the collected raw data, and the output data is the consolidated data frame. This allows data from different sources to be converted into a consistent format.

[1851] Step 5:

[1852] The server groups the consolidated data by quarter and performs the necessary aggregation operations to reshape it. Specifically, it uses the grouping and aggregation functions of Pandas. The input data is a consolidated data frame, and the output data is data reshaped by quarter. This allows for efficient analysis of data for a specific period.

[1853] Step 6:

[1854] The terminal displays the intermediate results of the formatted data on the chat interface and requests the user's confirmation. The displayed information includes a preview of the quarterly summary results. The input data is the formatted data, and the output data is a data preview displayed to the user for confirmation.

[1855] Step 7:

[1856] The user sends instructions to the server via the chat interface to correct or add data. For example, the user might say, "Please correct the data for the second quarter." The input data is the user's correction instruction, and the output data is the correction instruction itself.

[1857] Step 8:

[1858] The server reprocesses the data in response to the user's correction instructions. Specifically, it uses Pandas to correct the data frame and perform recalculation. The input data is the correction instructions and the data to be corrected, and the output data is the corrected data frame.

[1859] Step 9:

[1860] The server generates the quarterly sales report as the final output and outputs it in PDF or other specified format. Specifically, it generates a graph from the data frame using Matplotlib and embeds it in a PDF. The input data is the modified data frame, and the output data is the final report file.

[1861] Step 10:

[1862] The terminal displays a download link for the generated PDF report on the chat interface and presents it to the user. The input data is the generated report file, and the output data is the download link.

[1863] Step 11:

[1864] The device uses an emotion analysis engine to analyze the user's input and simplifies the operation if the user is feeling stressed or dissatisfied. Specifically, it performs text analysis and simplifies the next step based on the results. The input data is the user's input text, and the output data is the emotion analysis result.

[1865] Step 12:

[1866] The server modifies the data processing procedures and user interface based on the emotion analysis results, simplifying user operations. The input data is the emotion analysis results, and the output data is the adjusted processing procedures and user interface settings. This process optimizes the user experience and improves work efficiency.

[1867] The above are the specific processing steps and operations of this system.

[1868] (Application example 2)

[1869] 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."

[1870] On modern online shopping sites, it is difficult for users to find the right product for them from the vast number of products available. Furthermore, typical recommendation systems are based on the user's recent behavior and purchase history, and are unable to suggest products that take into account the user's emotional state. Furthermore, data collection, formatting, and output generation are often done manually, which can often be perceived as inefficient. To solve these problems, a data processing system that also takes into account the user's emotional state is needed.

[1871] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1872] In this invention, the server includes a means for connecting to different data storage locations and analyzing the metadata of each data storage location, a means for automatically collecting necessary data based on the analyzed metadata, and a means for integrating the collected data and formatting it into a standardized format, which enables product recommendations based on the user's emotional state and efficient data collection, formatting, and output generation.

[1873] "Data storage" refers to the system or storage that stores data stored in different locations.

[1874] "Metadata" is additional data that contains information about data and describes the structure and attributes of the data.

[1875] An "automatic collection means" is a method or device for automatically obtaining necessary data from a designated data storage location without user intervention.

[1876] A "means for converting data into a standardized format" is a method or device for converting data stored in different formats into a single unified format.

[1877] A "chat interface" is an interactive user interface through which a user can enter text and interact with the system.

[1878] An "emotion engine" is software or hardware that analyzes a user's input and actions to determine their emotional state at that time.

[1879] An "output generating means" is a method or device that generates reports or visualizations based on the formatted data.

[1880] A "means for generating product recommendations" is a method or device that suggests suitable products based on the user's emotional state and past data.

[1881] This invention is a system that combines a system that collects data from different data storage locations, integrates, formats, and outputs the data based on user instructions, with an emotion engine that recognizes the user's emotions and reflects the analysis results. Specific embodiments for realizing this system are described below.

[1882] System Configuration

[1883] The system mainly consists of the following elements:

[1884] 1. How to connect to the data storage location:

[1885] The server connects to the data storage destination using information such as an API key and connection URL provided by the user. For example, it authenticates and establishes a connection to different data storage destinations such as cloud storage services and data warehouses.

[1886] 2. Metadata analysis methods:

[1887] The server analyzes the metadata of the connected data storage destination to understand the data structure and format, and identifies the required data based on the analysis results.

[1888] 3. Automated collection of required data:

[1889] The server automatically collects data that meets the conditions specified by the user based on the analyzed metadata, using parallel processing technology to efficiently perform the collection work.

[1890] 4. Data integration methods:

[1891] The server consolidates the collected data into a single standardized format, for example by converting data from different file formats into a data frame.

[1892] 5. Data Formatting Methods:

[1893] The server then processes the combined data in a user-specified format, such as by aggregating it by category or converting it into a specific format.

[1894] 6. Chat Interface:

[1895] The terminal provides a chat interface to the user, allowing the user to check data and input instructions in real time. The user can correct data or give additional instructions through the chat.

[1896] 7. Emotion Engine:

[1897] The device is equipped with an emotion engine that performs emotion analysis based on the user's input and behavior. For example, it analyzes the user's emotional state based on the context of the text, input speed, typing intensity, etc. The server automatically adjusts data collection and formatting procedures based on the emotion data obtained by the emotion engine.

[1898] 8. Output Generation Means:

[1899] The server generates reports, dashboards, and other outputs based on the formatted data, such as PDF reports, Excel spreadsheets, and web-based dashboards.

[1900] 9. Product recommendation generation method:

[1901] The server suggests suitable products based on the user's emotional state and past data, utilizing algorithms based on emotion engines and data refinement methods.

[1902] Example

[1903] For example, there is a smartphone application called "Smart Shopping Assistant" for an online shopping site. This application works as follows:

[1904] 1. The user types "I'm looking for soothing products" into the chat interface on their device.

[1905] 2. The server collects data from different product data APIs and parses the metadata to extract the required data.

[1906] 3. The analyzed data is collected in parallel and formatted into a standardized format.

[1907] 4. The emotion engine analyzes the user's input and determines that it is a negative state.

[1908] 5. Based on this emotional data, relaxation goods and aroma products are recommended preferentially.

[1909] 6. Present product recommendations to users through the chat interface and offer purchasing options.

[1910] In this way, it becomes possible to recommend products based on the user's emotional state, as well as to efficiently collect, format, and generate output from data.

[1911] Prompt Sentence Examples

[1912] How are you feeling right now? What products are you looking for?

[1913] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1914] Step 1:

[1915] Connecting to a data storage location

[1916] The server receives the API key and connection URL information provided by the user as input and connects to each data storage destination. Specifically, it authenticates and establishes a connection with different data storage destinations such as cloud storage services and data warehouses. This prepares the server to retrieve the required data from the data storage destination.

[1917] Step 2:

[1918] Metadata analysis

[1919] The server analyzes the metadata of the connected data store, which includes file structure, database schema, data format, etc. It takes the metadata as input and understands the overall structure of the data, which forms the basis for identifying what data is needed.

[1920] Step 3:

[1921] Collection of necessary data

[1922] The server automatically collects the necessary data based on the analyzed metadata. It receives condition settings as input and efficiently collects the necessary data from the data storage location using parallel processing technology. The collected data is converted into a standardized format, allowing data in a unified format to be obtained from diverse data sources.

[1923] Step 4:

[1924] Data integration and formatting

[1925] The server aggregates the collected data and formats it into a standardized format. The input is the raw data collected, and the output is a unified data frame. During this process, data is aggregated by category and converted into a specific format to ensure consistency.

[1926] Step 5:

[1927] Emotion analysis

[1928] The device performs emotion analysis based on the user's input and behavior. For example, it displays prompts such as "How are you feeling right now? What kind of product are you looking for?" and receives user input. The input is text data, which the emotion engine analyzes and outputs the user's emotional state. This includes analyzing the context of the text and the speed of input.

[1929] Step 6:

[1930] Generate product recommendations

[1931] The server generates product recommendations based on the analysis results of the emotion engine according to the user's emotional state. The input is the results of the emotion analysis and formatted data, and the output is a product list presented to the user. For example, if the user is feeling stressed, relaxation goods and aroma products will be recommended first.

[1932] Step 7:

[1933] Output through the chat interface

[1934] The terminal displays the generated product recommendations to the user through a chat interface. The input is the generated product list, and the output is the display to the user on the terminal. The user can provide further instructions through this interface, and the system will reprocess the data accordingly.

[1935] Step 8:

[1936] Generating the final output

[1937] The server generates the final output and provides it to the user as needed, such as a report or dashboard. The input is the formatted data and additional user instructions, and the output is a PDF report or a web-based dashboard, allowing the user to see the results of the data processing in a tangible way.

[1938] 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.

[1939] 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.

[1940] 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.

[1941] 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.

[1942] 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.

[1943] 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.

[1944] 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).

[1945] 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.

[1946] 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."

[1947] 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.

[1948] 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).

[1949] 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.

[1950] 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.

[1951] 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.

[1952] 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.

[1953] 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.

[1954] 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.

[1955] 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.

[1956] 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.

[1957] 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.

[1958] 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.

[1959] The following is further disclosed regarding the above embodiment.

[1960] (Claim 1)

[1961] means for connecting to different data stores and analyzing the metadata of each data store;

[1962] A means for automatically collecting necessary data based on the analyzed metadata;

[1963] A means of integrating and formatting the collected data into a standardized format;

[1964] a means for the user to modify or add data through a chat interface;

[1965] A system that includes a means for generating output based on the formatted data.

[1966] (Claim 2)

[1967] 10. The system of claim 1, further comprising means for parallel processing data collection based on the analyzed metadata.

[1968] (Claim 3)

[1969] 10. The system of claim 1, further comprising means for checking data and outputting instructions in real time through a chat interface.

[1970] "Example 1"

[1971] (Claim 1)

[1972] means for connecting to different data stores and analyzing the metadata of each data store;

[1973] A means for automatically collecting necessary data based on the analyzed metadata;

[1974] A means of integrating and formatting the collected data into a standardized format;

[1975] A means for inputting instructions to correct or add data through a user interface on the terminal;

[1976] A means for generating reports or dashboards based on the formatted data; and

[1977] A means to make the generated report or dashboard available for download or sharing;

[1978] A system that includes a means for entering and verifying data on a terminal in real time.

[1979] (Claim 2)

[1980] 10. The system of claim 1, further comprising means for parallel processing data collection based on the analyzed metadata.

[1981] (Claim 3)

[1982] 10. The system of claim 1, further comprising means for accepting data processing instructions based on natural language prompts via a chat interface on a terminal using the generative AI model.

[1983] "Application Example 1"

[1984] (Claim 1)

[1985] means for connecting to different data stores and analyzing the metadata of each data store;

[1986] A means for automatically collecting necessary data based on the analyzed metadata;

[1987] A means of integrating and formatting the collected data into a standardized format;

[1988] A means for a user to give instructions to correct or add data through a chat interface via a smartphone;

[1989] A system that generates output in real time based on formatted data and displays it in a dashboard format.

[1990] (Claim 2)

[1991] 10. The system of claim 1, further comprising means for parallel processing data collection based on the analyzed metadata.

[1992] (Claim 3)

[1993] The system according to claim 1, further comprising means for checking data and outputting instructions in real time through a chat interface on a smartphone.

[1994] "Example 2: Combining Emotion Engines"

[1995] (Claim 1)

[1996] means for connecting to different data stores and analyzing the metadata of each data store;

[1997] A means for automatically collecting necessary data based on the analyzed metadata;

[1998] A means of integrating and formatting the collected data into a standardized format;

[1999] a means for the user to modify or add data through a chat interface;

[2000] A means for generating output based on the formatted data; and

[2001] a means for sentiment analysis of user input and behavior to adjust data processing procedures;

[2002] A system including a means for simplifying user operations based on emotion analysis results.

[2003] (Claim 2)

[2004] 10. The system of claim 1, further comprising means for parallel processing data collection based on the analyzed metadata.

[2005] (Claim 3)

[2006] 10. The system of claim 1, further comprising means for checking data and outputting instructions in real time through a chat interface.

[2007] "Application example 2 when combining emotion engines"

[2008] (Claim 1)

[2009] means for connecting to different data stores and analyzing the metadata of each data store;

[2010] A means for automatically collecting necessary data based on the analyzed metadata;

[2011] A means of integrating and formatting the collected data into a standardized format;

[2012] a means for the user to modify or add data through a chat interface;

[2013] A means for generating output based on the formatted data; and

[2014] an emotion engine for analyzing the user's emotional state and means for adjusting data collection and shaping procedures based on the emotional state;

[2015] A means for generating product recommendations according to the emotional state of a user;

[2016] A system including:

[2017] (Claim 2)

[2018] 10. The system of claim 1, further comprising means for parallel processing data collection based on the analyzed metadata.

[2019] (Claim 3)

[2020] 10. The system of claim 1, further comprising means for checking data and outputting instructions in real time through a chat interface. [Explanation of symbols]

[2021] 10, 210, 310, 410 Data Processing Systems 12 Data Processing D...

Claims

1. means for connecting to different data stores and analyzing the metadata of each data store; A means for automatically collecting necessary data based on the analyzed metadata; A means of integrating and formatting the collected data into a standardized format; a means for the user to modify or add data through a chat interface; A system that includes a means for generating output based on the formatted data.

2. 10. The system of claim 1, further comprising means for performing parallel processing to collect data based on the analyzed metadata.

3. 2. The system according to claim 1, further comprising means for checking data and outputting instructions in real time through a chat interface.

Images