system

Abstract

Provide a system. [Solution] a means of collecting data from a data source; a means for analyzing the format of the collected data; A means for extracting necessary data from the analyzed data; A means for converting the extracted data into a specified format and saving it; a means for notifying the user of the generated output; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern companies, the wide variety of data sources means that simply finding the data you need can be time-consuming and laborious. In particular, integrating and analyzing data stored in different formats and locations is a complex task, creating a demand for efficient data management. Under these circumstances, a system is needed that allows users to quickly and accurately collect and analyze data and generate the desired output. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system including a data collection means, a data format analysis means, a data extraction means, an output conversion means, and a notification means. The system collects data from data sources, analyzes the format of the collected data, and extracts necessary information from the analyzed data. The system then converts the extracted data into a specified format, saves it, and notifies the user of the generated output. This enables efficient integration and analysis of data in different formats and locations, and promptly provides the output desired by the user. Furthermore, the system includes a means for accessing the data source using appropriate authentication information depending on the type of data source, and filtering logic for selecting target data based on the collected data, achieving even greater accuracy and efficiency.

[0006] A "data source" refers to the location or medium where information is stored, such as a database, spreadsheet, or cloud storage.

[0007] "Data collection means" refers to the functions and processes for accessing data sources, obtaining the necessary information, and temporarily storing it.

[0008] "Data format analysis means" refers to processes and algorithms for understanding the format and structure of collected data and performing appropriate data processing based on that understanding.

[0009] "Data extraction means" refers to the functions and processes for selecting necessary information that meets specific conditions from the analyzed data.

[0010] "Output transformation means" refers to the functions or processes that transform extracted data into a specified format or form to create the final output.

[0011] "Notification means" refers to functions and methods for notifying users of generated output, such as email or chat tools.

[0012] "Authentication information" refers to information such as keys and passwords required for a system to access a data source.

[0013] "Filtering logic" refers to the algorithms and conditions used to select data that matches specific patterns or conditions from collected data. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention relates to a system for collecting, analyzing, and extracting data from data sources, generating output in a specified format, and notifying a user. The system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, and a notification means.

[0036] Overall system configuration

[0037] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. Users issue instructions, check the results, and make adjustments as necessary.

[0038] System processing flow

[0039] Data collection

[0040] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report).

[0041] Server: Receives user instructions and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[0042] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[0043] Server: Stores the collected data in a temporary data store.

[0044] Data analysis

[0045] Server: Analyzes the content and format of the stored data, for example, checking the file format (CSV, Excel, SQL database, etc.) and parsing header information and metadata.

[0046] Server: Define the conditions for extracting the required data items (project progress information, sales amount, etc.).

[0047] Data Extraction

[0048] Server: Extracts the required data from the temporary data store based on the defined criteria, for example, using SQL queries and filtering logic to select the target data.

[0049] Server: Organizes the extracted data and converts it into a format suitable for the final output (graphs, tables, etc.).

[0050] Output generation and notification

[0051] Server: Converts the formatted data into the specified format (PDF, Excel, HTML report, etc.) and saves it.

[0052] Server: Notifies the user of the generated output. For example, it saves it in cloud storage and sends the link to the user via email or chat tool.

[0053] User: Upon receiving notification, downloads the generated output, reviews it, makes any necessary adjustments, and finally approves it.

[0054] Specific examples

[0055] Scenario: Generating a weekly report

[0056] 1. User: Instructs the generation of a weekly report.

[0057] 2. Server: Accessed with the necessary API keys to collect data from project management tools (e.g., online project management systems) and spreadsheets.

[0058] 3. Server: Retrieves project progress data from each data source and stores it in a temporary data store.

[0059] 4. Server: Analyzes the format of the collected data and identifies task status information.

[0060] 5. Server: Extracts data based on defined criteria and organizes the information required for weekly reports.

[0061] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[0062] 7. Server: Saves the completed report to cloud storage and emails the user a link to the report.

[0063] 8. User: Checks email, opens report and examines contents.

[0064] 9. User: Make any necessary adjustments and give final approval.

[0065] This invention automates the entire process of data collection, analysis, extraction, and output, saving users time and effort, and is expected to improve work efficiency.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] User: Instructs the generation of the required report (e.g., weekly report, monthly sales report). The user specifies the data source, output format, report conditions, etc. through a dedicated interface.

[0069] Step 2:

[0070] Server: Receives user instructions and checks the list of target data sources, which can include databases, spreadsheets, cloud storage, etc.

[0071] Step 3:

[0072] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). At this stage, after successful authentication, access permissions are verified.

[0073] Step 4:

[0074] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[0075] Step 5:

[0076] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[0077] Step 6:

[0078] Server: Define the conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data. For example, use keyword search or regular expressions to identify the necessary information.

[0079] Step 7:

[0080] Server: Extracts the required data from the temporary data store based on the defined criteria, and applies SQL queries and filtering logic to select the target data.

[0081] Step 8:

[0082] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[0083] Step 9:

[0084] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[0085] Step 10:

[0086] Server: Notifies the user of the generated output. Notification methods include saving it to cloud storage, sending a link to it via email, or sharing it via a chat tool.

[0087] Step 11:

[0088] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[0089] Step 12:

[0090] User: Revises output as needed and gives final approval. Revises output using a PDF reader or spreadsheet software.

[0091] Through the above steps, the system can respond to user requests, smoothly collect, analyze, and extract data from different formats and locations, and generate and provide output.

[0092] Example 1

[0093] 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."

[0094] In conventional systems, the processes of data collection, analysis, extraction, format conversion, and notification were often manual or only partially automated, resulting in a lack of overall efficiency. This meant that users had to spend time and effort processing large amounts of data and generating reports, making it difficult to improve work efficiency. In addition, differences in authentication methods and data formats corresponding to different data sources made data integration and analysis technically complex.

[0095] 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.

[0096] In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This enables efficient collection and analysis of data. The server also includes means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, means for receiving and analyzing a prompt sentence in natural language, and means for securely accessing the data source using authentication information. This automates a series of data processing tasks performed by the user, enabling efficient and rapid generation of desired reports.

[0097] A "data source" is a location or system where the raw data from which a system obtains information is stored.

[0098] "Means of collection" refers to the methods and devices used to obtain the required data from the data source.

[0099] "Means of analysis" refers to the methods and algorithms used to understand the format and content of the collected data and find the necessary information.

[0100] "Extraction means" refers to methods or tools for extracting data that meets specific conditions from the analyzed data.

[0101] "Means of converting and saving into a specified format" refers to the method or procedure for converting extracted data into a specified format (PDF, Excel, etc.) and saving it.

[0102] "Means of notification" refers to the methods and techniques used to notify users of the generated output.

[0103] "Means for receiving and analyzing natural language prompts" refers to methods or techniques for receiving instructions in natural language from a user, analyzing them, and performing appropriate processing.

[0104] "Authentication information" refers to information (such as an API key or password) required to securely access a data source.

[0105] A "means for securely accessing a data source" refers to a method or algorithm for securely connecting to a data source using authentication information.

[0106] A "temporary data store" is a database or storage for temporarily storing collected data.

[0107] "Filtering logic" refers to algorithms or methods for filtering data based on specific conditions.

[0108] The present invention is a system that collects data from data sources, analyzes and extracts it, generates output in a specified format, and notifies users. This system consists of a server, a terminal, and a user.

[0109] Overall system configuration

[0110] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. The terminals are the interfaces that transmit user instructions to the server. Users issue instructions to the system, check the generated output, and make adjustments as necessary.

[0111] Hardware and Software Configuration

[0112] Server: Performs data collection, parsing, extraction, transformation, and notification functions. This server manages credentials to access various databases and APIs, securely exchanges data using communication protocols, and executes SQL queries and filtering logic for data analysis.

[0113] Terminal: The user inputs instructions and the results are displayed. The required hardware is a PC or tablet. It also uses an application or web browser that provides an interface such as a GUI (Graphical User Interface).

[0114] User: Enter specific prompts into the system and view the generated output. For example, enter natural language prompts such as "Generate this week's progress report" or "Generate this month's sales report."

[0115] Specific examples of processing

[0116] Generate weekly reports

[0117] 1. User: Instructs the generation of a weekly report. For example, the user enters the prompt "Please generate this week's progress report" into the terminal.

[0118] 2. Terminal: Sends this instruction to the server.

[0119] 3. Server: To collect data from project management tools (e.g., online project management systems) and spreadsheets, you connect securely using credentials, specifically, API keys to access data sources.

[0120] 4. Server: Retrieves project progress data from each data source and stores this data in a temporary data store.

[0121] 5. Server: Analyzes the format of the stored data and identifies the required data items (e.g., task status information).

[0122] 6. Server: Extracts the required data from the temporary data store based on defined criteria, for example, running an SQL query to extract only data from a specific time period.

[0123] 7. Server: Format the extracted data and generate a PDF report. Add graphs and charts using tools like ReportLab.

[0124] 8. Server: Saves the completed report to cloud storage and generates a link to it.

[0125] 9. Server: Sends the link to the user via email or chat tool.

[0126] 10. User: Checks email, opens report, checks contents, makes necessary adjustments and sends command to server again.

[0127] This invention is a system that uses a generative AI model to analyze prompts, automatically collect, analyze, and extract data, and generate targeted reports to notify users, thereby significantly reducing the user's workload and improving work efficiency.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The user uses a terminal to enter a prompt that instructs the system to generate a specific report, for example, "Please generate this week's progress report." This prompt is then sent from the terminal to the server.

[0131] Input: The prompt text entered by the user

[0132] Output: The prompt sent to the server

[0133] Specific behavior: The user enters a prompt sentence into the input form and clicks the submit button.

[0134] Step 2:

[0135] The server receives and parses the prompt, using a generative AI model to understand the content of the prompt and identify the required action.

[0136] Input: The prompt sent to the server

[0137] Output: Analysis results (type of report to generate and required data source)

[0138] What it does: It uses a natural language processing library (e.g., NLTK or Spacy) to parse the prompt and identify the type of report to generate (e.g., weekly status report) and the data source (e.g., project management tool).

[0139] Step 3:

[0140] Connect to the data source using the credentials (such as an API key or database connection string) to access the data source identified by the server.

[0141] Input: Analysis results (required data source and credentials)

[0142] Output: Connection to a data source

[0143] Specific operation: Connect to a database server using a database connection string, or access a Web API using an API key.

[0144] Step 4:

[0145] The server retrieves the required data from the data source and stores it in a temporary data store for further processing.

[0146] Input: Data source (database, spreadsheet, etc.)

[0147] Output: Data saved to a temporary data store

[0148] What it does: For example, execute a SQL query to retrieve project progress data from a database and store it in a temporary data store (for example, Redis or a temporary file).

[0149] Step 5:

[0150] The server analyzes the content and format of the data stored in the temporary data store. For example, in the case of a CSV file, it reads the header information and determines the data type of each column.

[0151] Input: Data stored in a temporary data store

[0152] Output: Analysis results (data format and content)

[0153] Specific operation: Uses Python's pandas library to read a CSV file and parse it into a data frame.

[0154] Step 6:

[0155] The server defines the conditions for identifying the required data items based on the analysis results. The conditions are expressed as SQL queries and filtering logic.

[0156] Input: Analysis results (data format and content)

[0157] Output: Condition definition (SQL query or filtering logic)

[0158] Specific operation: Generates a query such as "SELECT task_name, progress FROM project_data WHERE date BETWEEN(R) '2023-01-01' AND '2023-01-07'".

[0159] Step 7:

[0160] The server extracts the required data from the temporary data store based on defined criteria, for example, by running an SQL query to extract only data from a specific time period.

[0161] Input: Condition definition (SQL query or filtering logic)

[0162] Output: Extracted data

[0163] Specific behavior: Executes an SQL query to retrieve data that matches the specified criteria.

[0164] Step 8:

[0165] The server formats the extracted data and converts it to a suitable format for final output (PDF, Excel, etc.). For example, to generate a PDF report, use the ReportLab library.

[0166] Input: Extracted data

[0167] Output: Formatted data (output file)

[0168] What it does: Use ReportLab to add graphs and charts to PDF documents.

[0169] Step 9:

[0170] The server saves the generated output file in cloud storage and generates a link to it.

[0171] Input: Formatted data (output file)

[0172] Output: Cloud storage link

[0173] What it does: Uploads a file using the cloud storage API and gets its link.

[0174] Step 10:

[0175] The server will notify the user of the cloud storage link via email or chat tool.

[0176] Input: Cloud storage link

[0177] Output: Notification to user (email or chat)

[0178] Specific operation: Send a link to the user using an email sending service or chat API (e.g., Slack API).

[0179] Step 11:

[0180] The user receives a notification, clicks a link to download the output file (e.g., a PDF report), and reviews the contents.

[0181] Input: User notification

[0182] Output: The downloaded output file

[0183] What happens: User clicks on a link, downloads a file, and reviews its contents.

[0184] Step 12:

[0185] The user checks the content for any problems and instructs the server to provide feedback or make revisions as necessary.

[0186] Input: User feedback and rework instructions

[0187] Output: Redirect to server

[0188] Specific operation: Based on the review results, the user re-enters the necessary corrections as a prompt sentence and sends it to the server.

[0189] (Application example 1)

[0190] 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."

[0191] Modern logistics centers require a series of processes, including data collection, analysis, extraction, and output generation from a wide variety of data sources. However, doing all of this manually is extremely time-consuming and labor-intensive, resulting in errors and delays. It is also difficult to optimize inventory information and delivery routes in real time, reducing the efficiency of management operations. To solve these issues, a system is needed that automatically collects and analyzes data, and efficiently manages inventory and optimizes delivery routes.

[0192] 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.

[0193] In this invention, the server includes means for collecting data from data sources, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying a user of the generated output, means for analyzing logistics management information and calculating an optimal delivery route, and means for monitoring inventory information in real time and notifying necessary warnings, thereby enabling automated data management, efficient inventory management, and calculation of an optimal delivery route within a logistics center.

[0194] "Data Sources" are various information sources that serve as starting points for collecting data.

[0195] "Means for collecting data" refers to a function for obtaining necessary information from a specified data source.

[0196] "Means for analyzing data format" refers to the function of identifying the structure and type of collected data and processing it in an appropriate format.

[0197] "Means for extracting necessary data" refers to the function of extracting important information from the analyzed data based on specific conditions.

[0198] The "means for converting and saving into a specified format" is a function for converting extracted data into a specified format and saving it so that it can be referenced later.

[0199] "Means for notifying the user of the generated output" is a function that notifies the user of the final generated report or information.

[0200] "Means for analyzing logistics management information and calculating optimal delivery routes" is a function that uses data collected within the logistics center to derive efficient delivery routes.

[0201] "Means of monitoring inventory information in real time and notifying necessary warnings" refers to a function that constantly monitors the inventory status in the warehouse and immediately issues an alert if an abnormality occurs.

[0202] This invention is a system for automating and streamlining inventory management and delivery route optimization in logistics centers. This system combines various methods for data collection, analysis, extraction, output generation, and notification.

[0203] Hardware and software used

[0204] Hardware:

[0205] Smartphone (iOS / ANDROID (registered trademark))

[0206] Logistics robots

[0207] IoT sensors (for inventory management)

[0208] GPS device (for shipping tracking)

[0209] software:

[0210] Database (PostgreSQL, MySQL (registered trademark))

[0211] Cloud storage (AWS (registered trademark) S3, Google (registered trademark) Drive)

[0212] API services (Google Maps API, Twilio for notifications)

[0213] AI / ML models (TENSORFLOW (registered trademark), PyTorch)

[0214] The server uses this hardware and software to perform the following processes.

[0215] Data collection

[0216] The server collects data from inventory sensors and GPS devices as data sources, thereby obtaining real-time inventory information and delivery route information within the distribution center. For example, sensors detect the current inventory status and input that information into a database.

[0217] Data analysis

[0218] The server analyzes the format of the collected data and extracts the necessary data, such as detailed information about a specific product from inventory data or analyzing GPS data to confirm the current delivery route and time.

[0219] Data extraction and output generation

[0220] The server converts the extracted data into a specified format and generates output, such as generating an inventory report in PDF format or calculating the optimal delivery route and saving it as an HTML report.

[0221] notification

[0222] The generated output is stored in cloud storage and the user is notified via email or chat using API services such as Twilio.

[0223] Specific examples

[0224] For example, if you want to generate a report on products that have significantly decreased in stock this week, the system collects data from sensors in real time, analyzes that data, extracts product information that falls within a specified decrease rate, compiles it into a report, and notifies the user.

[0225] Prompt Sentence Examples

[0226] "Please create a report on products that have significantly decreased based on this week's inventory status. For example, generate a PDF report containing a list of products whose inventory has decreased by 20% or more and the rate of decrease, and send it to the specified email address."

[0227] Such a system will make logistics center management more efficient and enable optimization of inventory and delivery routes.

[0228] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0229] Step 1:

[0230] Data collection

[0231] The server collects data from data sources such as inventory sensors and GPS devices. Specifically, it calls the sensor API and GPS API to obtain real-time data. The input is the API key and authentication information, and the output is stored in the database as inventory counts and delivery route information.

[0232] Step 2:

[0233] Data analysis

[0234] The server analyzes the format of the collected data. Specifically, it analyzes data formats such as CSV and JSON to check the field names and data types. The input is raw data from the database, and the output is structural information about the analyzed data. This process determines which data can be used and how.

[0235] Step 3:

[0236] Data Extraction

[0237] The server extracts the necessary information from the parsed data. Specifically, it executes SQL queries to extract data about specific products and delivery routes. The input is the parsed data, and the output is the extracted target data. This process identifies the necessary information and makes it available for the next step.

[0238] Step 4:

[0239] Output Generation

[0240] The server converts the extracted data into a specified format and generates the output. Specifically, it inserts the data into a report template and generates a report in PDF or HTML format. The input is the extracted data, and the output is the generated output file. This step creates a report in a format that is intuitive for the user.

[0241] Step 5:

[0242] notification

[0243] The server notifies the user of the generated output. Specifically, it sends a notification using Twilio or email API. The input is the generated output file and destination information, and the output is a notification to the user. This allows the user to immediately check the new report.

[0244] 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.

[0245] The present invention is a system that collects data from a data source, analyzes and extracts it, generates output in a specified format, and notifies a user, and further combines it with an emotion engine that recognizes the user's emotions. This system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, a notification means, and an emotion engine.

[0246] Overall system configuration

[0247] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. The emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system. Users issue instructions, check the results, and make adjustments as necessary.

[0248] System processing flow

[0249] Data collection

[0250] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report). The emotion engine simultaneously recognizes the user's emotions.

[0251] Server: Receives user instructions and information from the emotion engine and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[0252] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[0253] Server: Stores the collected data in a temporary data store.

[0254] Data analysis

[0255] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[0256] Server: Defines conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data, taking into account the user's emotional state.

[0257] Data Extraction

[0258] Server: Extracts the required data from the temporary data store based on the defined conditions, which are adjusted accordingly based on the analysis results of the emotion engine.

[0259] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs, tables).

[0260] Output generation and notification

[0261] Server: Converts the formatted data into the specified format (e.g. PDF, Excel, HTML report) and saves it.

[0262] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine (for example, a brief notification when stress is high).

[0263] User: Receives a notification, downloads the generated output, and reviews it. Feedback based on emotions is also recorded.

[0264] Specific examples

[0265] Scenario: Weekly report generation and emotion recognition

[0266] 1. User: Instructs the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired).

[0267] 2. Server: Accessed with appropriate credentials to collect data from project management tools and spreadsheets.

[0268] 3. Server: Stores the data in a temporary data store and analyzes its format and content.

[0269] 4. Server: Using the results of the emotion engine, set conditions to identify the required data items. For example, if the user is feeling stressed, prioritize summary data.

[0270] 5. Server: Extract data based on criteria and organize the information needed for weekly reports.

[0271] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[0272] 7. Server: Saves the completed report to cloud storage and sends a notification to the user reflecting the results of the emotion engine (e.g., a brief email notification with an encouraging message).

[0273] 8. User: Checks email, opens report, examines content, makes adjustments as needed, and provides emotional feedback to the system.

[0274] The system dynamically responds to the user's emotional state and aims to improve the user experience while streamlining the entire process from data collection to output generation.

[0275] The processing flow will be explained below.

[0276] Step 1:

[0277] User: Instructs the system to generate the required report (e.g., weekly report, monthly sales report). Through a dedicated interface, the user specifies the data source, output format, report conditions, etc. Furthermore, the emotion engine recognizes the user's emotions in real time.

[0278] Step 2:

[0279] Server: Receives user instructions and sentiment analysis results from the sentiment engine, and checks a list of target data sources, including databases, spreadsheets, cloud storage, etc.

[0280] Step 3:

[0281] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). After successful authentication at this stage, check the access permissions for each data source.

[0282] Step 4:

[0283] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[0284] Step 5:

[0285] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[0286] Step 6:

[0287] Server: Based on the content of the analyzed data, define the conditions for extracting the necessary data items (e.g., project progress information, sales amount). At this time, set conditions according to the user's emotions based on the analysis results of the emotion engine.

[0288] Step 7:

[0289] Server: Extracts the required data from the temporary data store based on the defined criteria. For example, it applies SQL queries and filtering logic to select the target data. This selection process is also adjusted based on the results of the emotion engine.

[0290] Step 8:

[0291] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[0292] Step 9:

[0293] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[0294] Step 10:

[0295] Server: Notifies the user of the generated output. At this time, the notification method and message content are optimized based on the results of the emotion engine. For example, if the user is feeling stressed, a concise and easy-to-understand notification is sent.

[0296] Step 11:

[0297] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[0298] Step 12:

[0299] User: Adjusts the output as needed and gives final approval, with the emotion engine recording the user's feedback for further analysis.

[0300] Through these steps, the system can adapt to the user's emotional state and efficiently process data from collection to output generation, saving the user time and effort and providing a better user experience.

[0301] Example 2

[0302] 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."

[0303] Conventional data collection and analysis systems were unable to take into account the user's emotional state, making it difficult to respond flexibly to the user's psychological conditions, such as stress and fatigue. Furthermore, they were limited to simple data collection and analysis and lacked functionality to improve the user experience. This resulted in a heavy burden on the user and reduced system usage efficiency.

[0304] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This makes it possible to analyze the user's emotions in real time and adjust the operation of the entire system based on the results.

[0305] A "data source" is the source from which data is collected, including databases, spreadsheets, cloud storage, etc.

[0306] "Collection" is the act of obtaining necessary information from a data source.

[0307] "Analysis" is the process of examining and interpreting collected data to understand its content and form.

[0308] "Extraction" is the act of extracting necessary information from analyzed data.

[0309] "Format" means a particular form or standard for storing or displaying data.

[0310] "Notification" is the act of communicating generated output to a user.

[0311] An "emotion engine" is a software or hardware function that analyzes a user's emotional state in real time and provides the results.

[0312] "Adjustment" is the act of dynamically changing the behavior and settings of the entire system based on the results of the emotion engine.

[0313] "Authentication information" refers to the information required to access a data source, including API keys and database connection strings.

[0314] "Filtering logic" refers to logical conditions or algorithms for selecting target data based on collected data.

[0315] "Output" means the final product of the analyzed, extracted, and transformed data, presented in the form of reports and / or graphs.

[0316] This invention is a system that collects, analyzes, and extracts data from data sources, generates output in a specified format, and notifies a user. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to respond flexibly while taking into account the user's psychological state. This system includes data collection means, data format analysis means, data extraction means, output conversion means, notification means, and an emotion engine.

[0317] Overall system configuration

[0318] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. Furthermore, the emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system.

[0319] Hardware and software used

[0320] Specifically, data collection involves software that accesses databases and cloud storage using API keys and database connection strings. Data analysis and transformation is performed using the Python pandas library, and output is generated using tools such as PDF generation tools (e.g., ReportLab) and Excel file creation tools (e.g., openpyxl). The emotion engine includes software for analyzing user emotions in real time. This emotion engine performs emotion analysis using machine learning models.

[0321] Specific examples

[0322] Take the example of weekly report generation and emotion recognition. A user requests the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired). The server collects data from project management tools or spreadsheets, accessing them with appropriate credentials. The collected data is stored in a temporary data store and analyzed for format and content. Based on the results of the emotion engine, conditions are set to identify the required data items. For example, if the user is feeling stressed, summary data is prioritized.

[0323] Based on these settings, data is extracted and the information required for the weekly report is organized. A weekly report in PDF format is generated based on the formatted data. The completed report is saved in cloud storage, and a notification reflecting the results of the emotion engine is sent to the user. For example, a brief email notification containing an encouraging message is sent.

[0324] Prompt Sentence Examples

[0325] Below are some example prompts to be input to the generative AI model of this system:

[0326] Follow the steps below to generate a weekly report. Also use the sentiment engine to analyze user sentiment and take the results into account in your data extraction and notifications.

[0327] 1. Collect weekly data from your project management tool.

[0328] 2. Analyze the data format to identify the required items.

[0329] 3. Set the conditions for data extraction taking into account the user's emotions.

[0330] 4. Generate weekly reports in PDF format.

[0331] 5. Save the report to cloud storage and notify the user.

[0332] This example and prompts provide a detailed understanding of the process by which the system takes the user's emotions into account when collecting data and generating output.

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1: User Instructions

[0335] User: The user instructs the system to generate a weekly report. As input, the user enters the command "generate a weekly report." The emotion engine recognizes the user's current emotion (e.g., stress or fatigue). This command is sent to the server.

[0336] Specific operation: A user accesses the system dashboard and clicks the report generation button. The emotion engine then collects and analyzes emotion data from the user's facial expressions and voice.

[0337] Step 2: Accessing the Data Source

[0338] Server: Takes as input the user's instructions and emotion engine's emotion data. The server checks the list of data sources and prepares access. It identifies the authentication information to use (API key, database connection string).

[0339] What happens: The server loads the list of database URLs and API keys and performs authentication for each data source.

[0340] Step 3: Collect and store data

[0341] Server: Accesses data sources using API keys and database connection strings to collect data. Authentication information for each data source and the data to be collected are given as input. The collected data is stored in a temporary data store.

[0342] What happens: The server connects to the database using an API, sends SQL queries or API requests to retrieve data, and stores that data in a temporary data store.

[0343] Step 4: Parsing the data format

[0344] Server: Analyzes the content and format of the temporarily stored data. As input, it receives the data stored in the temporary data store. It checks the file format (CSV, Excel, SQL database, etc.) and extracts the headers and metadata for the required information.

[0345] What happens: The server reads the header line of the data file, runs an algorithm to identify the file format, and analyzes the data content using the Python pandas library.

[0346] Step 5: Define data conditions

[0347] Server: Defines the conditions for extracting necessary data items from the analyzed data, taking into account the user's emotional state. The emotion engine's emotional data and the analyzed data are given as input. Specific conditions are set.

[0348] How it works: The server dynamically sets the conditions for data extraction queries based on information from the emotion engine. For example, if stress is high, summary data is prioritized.

[0349] Step 6: Extract the data

[0350] Server: Extracts the required data from the temporary data store based on the defined conditions. As input, the set conditions and the data stored in the temporary data store are given. As a result, the required data is retrieved.

[0351] Specific operation: Executes a data extraction query and retrieves target data from multiple tables by joining them.

[0352] Step 7: Data processing and organization

[0353] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs or tables). The extracted data is given as input. The result is formatted data.

[0354] How it works: The server aggregates the data and converts it into a data frame using the Python pandas library. Libraries such as matplotlib and seaborn are used to visualize the data.

[0355] Step 8: Generate output

[0356] Server: Converts and saves the formatted data in a specified format (e.g. PDF, Excel, HTML report). As input, the formatted data is given. As a result, the final output file is generated.

[0357] Specific operation: The server generates PDF or Excel files using a generative AI model library (e.g., ReportLab or openpyxl).

[0358] Step 9: Optimizing notifications

[0359] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine. The emotion engine data and the generated output are given as input. As a result, the appropriate notification method and message content are set.

[0360] What happens: The server uses an email notification API (e.g., SendGrid or SMTP) to send an optimized message to the user, such as a brief notification email with an encouraging message.

[0361] Step 10: Check the output

[0362] User: Upon receiving a notification, downloads the generated output and checks its contents. The notified output link is given as input. As a result, the user checks the output and provides feedback if necessary.

[0363] Specific operations: The user accesses the cloud storage, downloads the output file, checks its contents, and inputs and submits feedback through the system interface.

[0364] (Application example 2)

[0365] 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."

[0366] In modern virtual stores, product recommendations and customer support tailored to the customer's emotional state are important for improving customer satisfaction. However, conventional systems have difficulty recognizing customer emotions in real time and providing optimal services based on that information.

[0367] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, emotion recognition means for recognizing the user's emotions in real time, and means for adjusting the operation of the entire system based on the emotion information obtained by the emotion recognition means. This makes it possible to provide product recommendations and support according to the customer's emotional state.

[0368] "Data Source" means a source of data, such as a database, spreadsheet, or cloud storage.

[0369] A "data collection method" is a method that has the function of obtaining the necessary data from a data source, such as using an API call or a database query.

[0370] The "data format analysis means" is a means having a function for analyzing the structure and format of collected data, and recognizes file formats and extracts metadata.

[0371] "Data extraction means" refers to a means that has the function of extracting specific necessary information from the analyzed data, applying filtering logic and search conditions.

[0372] An "output conversion means" is a means that has the function of converting extracted data into a specified format and saving it, such as PDF, Excel, or HTML.

[0373] "Notification means" refers to a means that has the function of notifying the user of the generated output, such as email, app notification, or message delivery.

[0374] "Emotion recognition means" refers to a means that has the function of identifying a user's emotions in real time and acquiring that information, and utilizes a facial recognition camera and emotion analysis software.

[0375] The "means for adjusting the operation of the entire system" is a means for adjusting other functions and behaviors of the system based on the emotional information acquired by the emotional recognition means, and customizes the content of the service according to the emotional state.

[0376] This invention realizes a system that provides product recommendations and customer support in a virtual store according to the emotional state of the customer. The system operates using smart glasses or a head-mounted display worn by the user, analyzes the emotional state in real time through emotion recognition means, and adjusts the operation of the entire system based on that information.

[0377] Hardware and Software Configuration

[0378] Hardware:

[0379] Cameras (built into smart glasses or head-mounted displays)

[0380] Server (performs data processing and sentiment analysis)

[0381] User's device (smartphone, tablet, etc.)

[0382] software:

[0383] OpenCV (a library that provides face recognition functionality)

[0384] EmotionRecognitionModule (software for emotion analysis)

[0385] DataSourceModule (data collection and filtering software)

[0386] OutputFormatModule (software that converts data output formats)

[0387] Program processing

[0388] The server first acquires video data using the camera installed on the user's device and performs real-time emotion analysis using emotion recognition means. Based on the analysis results, it collects, analyzes, and extracts appropriate data. Next, it converts the extracted data into a specified format (e.g., a product recommendation list) and notifies the user of the results. The notification content is customized based on the user's emotional state.

[0389] Specific examples

[0390] For example, when a user enters a virtual store, the camera installed in the smart glasses captures the user's face, and if the emotion recognition means determines that the user is smiling (happy), the server will prioritize displaying a list of new products. Conversely, if the user is feeling stressed, the server will display a list of products with a relaxing effect (aroma candles, relaxation gadgets, etc.).

[0391] Usage example

[0392] Example prompt sentence:

[0393] When a user wears smart glasses and enters a virtual store, please capture their face with a camera and perform real-time emotion analysis. If the emotion is "smile", please suggest a new product list. If the emotion is "stress", please suggest a product list with a relaxing effect.

[0394] By using this system, high-quality customer support can be provided in a virtual store according to the customer's emotional state, resulting in improved customer satisfaction.

[0395] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0396] Step 1:

[0397] A user puts on smart glasses and enters a virtual store. The device's camera captures the user's face. The captured video data is sent to the server in real time. The input is the user's face video data, and the output is the video data sent to the server.

[0398] Step 2:

[0399] The server receives the video data and uses OpenCV to recognize the user's face. It then uses the EmotionRecognitionModule to analyze the user's emotions. The input is video data, and face recognition and emotion analysis are performed as data processing. The output is the user's emotional information (e.g., smiling, stress, etc.).

[0400] Step 3:

[0401] The server determines the next data processing instructions based on the obtained emotional information. Specifically, it sets conditions such as prioritizing a list of new products if the person is smiling, or a list of products with a relaxing effect if the person is under stress. The input is emotional information, and the output is the data processing instructions.

[0402] Step 4:

[0403] The server uses the DataSourceModule to collect the required data from the appropriate data source based on the configured instructions. Examples include collecting data from a product database or cloud storage. The input is the data processing instructions, and the data is collected as data processing. The output is the collected product data.

[0404] Step 5:

[0405] The server analyzes the format of the collected data. Using data format analysis means, it analyzes and extracts the data structure and necessary information. The input is the collected product data, and format analysis is performed as data calculation. The output is the analyzed data.

[0406] Step 6:

[0407] The server extracts necessary data from the analyzed data. Using the data extraction method, it filters appropriate product information based on the emotion information. The input is the analyzed data, and filtering logic is applied as data processing. The output is the extracted product information.

[0408] Step 7:

[0409] The server converts the extracted data into the specified format and saves it using OutputFormatModule. For example, converting a recommended product list into PDF or HTML format. The input is the extracted product information, and format conversion is performed as data processing. The output is the formatted output.

[0410] Step 8:

[0411] The server notifies the user of the generated output. Based on the results of the emotion recognition means, the notification method and message content are optimized. For example, if stress is high, a simple notification is sent. The input is the formatted output, and the output is the notification to the user.

[0412] Step 9:

[0413] The user receives a notification and checks the provided product list. If necessary, the user can provide feedback to the system using prompt sentences. The input feedback from the user helps improve the system.

[0414] In this way, the present invention realizes a system that can provide optimal product recommendations and support in a virtual store according to the emotional state of the customer.

[0415] 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.

[0416] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0417] 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.

[0418] [Second embodiment]

[0419] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0420] 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.

[0421] 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).

[0422] 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.

[0423] 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.

[0424] 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).

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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."

[0431] The present invention relates to a system for collecting, analyzing, and extracting data from data sources, generating output in a specified format, and notifying a user. The system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, and a notification means.

[0432] Overall system configuration

[0433] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. Users issue instructions, check the results, and make adjustments as necessary.

[0434] System processing flow

[0435] Data collection

[0436] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report).

[0437] Server: Receives user instructions and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[0438] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[0439] Server: Stores the collected data in a temporary data store.

[0440] Data analysis

[0441] Server: Analyzes the content and format of the stored data, for example, checking the file format (CSV, Excel, SQL database, etc.) and parsing header information and metadata.

[0442] Server: Define the conditions for extracting the required data items (project progress information, sales amount, etc.).

[0443] Data Extraction

[0444] Server: Extracts the required data from the temporary data store based on the defined criteria, for example, using SQL queries and filtering logic to select the target data.

[0445] Server: Organizes the extracted data and converts it into a format suitable for the final output (graphs, tables, etc.).

[0446] Output generation and notification

[0447] Server: Converts the formatted data into the specified format (PDF, Excel, HTML report, etc.) and saves it.

[0448] Server: Notifies the user of the generated output. For example, it saves it in cloud storage and sends the link to the user via email or chat tool.

[0449] User: Upon receiving notification, downloads the generated output, reviews it, makes any necessary adjustments, and finally approves it.

[0450] Specific examples

[0451] Scenario: Generating a weekly report

[0452] 1. User: Instructs the generation of a weekly report.

[0453] 2. Server: Accessed with the necessary API keys to collect data from project management tools (e.g., online project management systems) and spreadsheets.

[0454] 3. Server: Retrieves project progress data from each data source and stores it in a temporary data store.

[0455] 4. Server: Analyzes the format of the collected data and identifies task status information.

[0456] 5. Server: Extracts data based on defined criteria and organizes the information required for weekly reports.

[0457] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[0458] 7. Server: Saves the completed report to cloud storage and emails the user a link to the report.

[0459] 8. User: Checks email, opens report and examines contents.

[0460] 9. User: Make any necessary adjustments and give final approval.

[0461] This invention automates the entire process of data collection, analysis, extraction, and output, saving users time and effort, and is expected to improve work efficiency.

[0462] The processing flow will be explained below.

[0463] Step 1:

[0464] User: Instructs the generation of the required report (e.g., weekly report, monthly sales report). The user specifies the data source, output format, report conditions, etc. through a dedicated interface.

[0465] Step 2:

[0466] Server: Receives user instructions and checks the list of target data sources, which can include databases, spreadsheets, cloud storage, etc.

[0467] Step 3:

[0468] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). At this stage, after successful authentication, access permissions are verified.

[0469] Step 4:

[0470] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[0471] Step 5:

[0472] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[0473] Step 6:

[0474] Server: Define the conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data. For example, use keyword search or regular expressions to identify the necessary information.

[0475] Step 7:

[0476] Server: Extracts the required data from the temporary data store based on the defined criteria, and applies SQL queries and filtering logic to select the target data.

[0477] Step 8:

[0478] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[0479] Step 9:

[0480] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[0481] Step 10:

[0482] Server: Notifies the user of the generated output. Notification methods include saving it to cloud storage, sending a link to it via email, or sharing it via a chat tool.

[0483] Step 11:

[0484] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[0485] Step 12:

[0486] User: Revises output as needed and gives final approval. Revises output using a PDF reader or spreadsheet software.

[0487] Through the above steps, the system can respond to user requests, smoothly collect, analyze, and extract data from different formats and locations, and generate and provide output.

[0488] Example 1

[0489] 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."

[0490] In conventional systems, the processes of data collection, analysis, extraction, format conversion, and notification were often manual or only partially automated, resulting in a lack of overall efficiency. This meant that users had to spend time and effort processing large amounts of data and generating reports, making it difficult to improve work efficiency. In addition, differences in authentication methods and data formats corresponding to different data sources made data integration and analysis technically complex.

[0491] 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.

[0492] In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This enables efficient collection and analysis of data. The server also includes means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, means for receiving and analyzing a prompt sentence in natural language, and means for securely accessing the data source using authentication information. This automates a series of data processing tasks performed by the user, enabling efficient and rapid generation of desired reports.

[0493] A "data source" is a location or system where the raw data from which a system obtains information is stored.

[0494] "Means of collection" refers to the methods and devices used to obtain the required data from the data source.

[0495] "Means of analysis" refers to the methods and algorithms used to understand the format and content of the collected data and find the necessary information.

[0496] "Extraction means" refers to methods or tools for extracting data that meets specific conditions from the analyzed data.

[0497] "Means of converting and saving into a specified format" refers to the method or procedure for converting extracted data into a specified format (PDF, Excel, etc.) and saving it.

[0498] "Means of notification" refers to the methods and techniques used to notify users of the generated output.

[0499] "Means for receiving and analyzing natural language prompts" refers to methods or techniques for receiving instructions in natural language from a user, analyzing them, and performing appropriate processing.

[0500] "Authentication information" refers to information (such as an API key or password) required to securely access a data source.

[0501] A "means for securely accessing a data source" refers to a method or algorithm for securely connecting to a data source using authentication information.

[0502] A "temporary data store" is a database or storage for temporarily storing collected data.

[0503] "Filtering logic" refers to algorithms or methods for filtering data based on specific conditions.

[0504] The present invention is a system that collects data from data sources, analyzes and extracts it, generates output in a specified format, and notifies users. This system consists of a server, a terminal, and a user.

[0505] Overall system configuration

[0506] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. The terminals are the interfaces that transmit user instructions to the server. Users issue instructions to the system, check the generated output, and make adjustments as necessary.

[0507] Hardware and Software Configuration

[0508] Server: Performs data collection, parsing, extraction, transformation, and notification functions. This server manages credentials to access various databases and APIs, securely exchanges data using communication protocols, and executes SQL queries and filtering logic for data analysis.

[0509] Terminal: The user inputs instructions and the results are displayed. The required hardware is a PC or tablet. It also uses an application or web browser that provides an interface such as a GUI (Graphical User Interface).

[0510] User: Enter specific prompts into the system and view the generated output. For example, enter natural language prompts such as "Generate this week's progress report" or "Generate this month's sales report."

[0511] Specific examples of processing

[0512] Generate weekly reports

[0513] 1. User: Instructs the generation of a weekly report. For example, the user enters the prompt "Please generate this week's progress report" into the terminal.

[0514] 2. Terminal: Sends this instruction to the server.

[0515] 3. Server: To collect data from project management tools (e.g., online project management systems) and spreadsheets, you connect securely using credentials, specifically, API keys to access data sources.

[0516] 4. Server: Retrieves project progress data from each data source and stores this data in a temporary data store.

[0517] 5. Server: Analyzes the format of the stored data and identifies the required data items (e.g., task status information).

[0518] 6. Server: Extracts the required data from the temporary data store based on defined criteria, for example, running an SQL query to extract only data from a specific time period.

[0519] 7. Server: Format the extracted data and generate a PDF report. Add graphs and charts using tools like ReportLab.

[0520] 8. Server: Saves the completed report to cloud storage and generates a link to it.

[0521] 9. Server: Sends the link to the user via email or chat tool.

[0522] 10. User: Checks email, opens report, checks contents, makes necessary adjustments and sends command to server again.

[0523] This invention is a system that uses a generative AI model to analyze prompts, automatically collect, analyze, and extract data, and generate targeted reports to notify users, thereby significantly reducing the user's workload and improving work efficiency.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] Step 1:

[0526] The user uses a terminal to enter a prompt that instructs the system to generate a specific report, for example, "Please generate this week's progress report." This prompt is then sent from the terminal to the server.

[0527] Input: The prompt text entered by the user

[0528] Output: The prompt sent to the server

[0529] Specific behavior: The user enters a prompt sentence into the input form and clicks the submit button.

[0530] Step 2:

[0531] The server receives and parses the prompt, using a generative AI model to understand the content of the prompt and identify the required action.

[0532] Input: The prompt sent to the server

[0533] Output: Analysis results (type of report to generate and required data source)

[0534] What it does: It uses a natural language processing library (e.g., NLTK or Spacy) to parse the prompt and identify the type of report to generate (e.g., weekly status report) and the data source (e.g., project management tool).

[0535] Step 3:

[0536] Connect to the data source using the credentials (such as an API key or database connection string) to access the data source identified by the server.

[0537] Input: Analysis results (required data source and credentials)

[0538] Output: Connection to a data source

[0539] Specific operation: Connect to a database server using a database connection string, or access a Web API using an API key.

[0540] Step 4:

[0541] The server retrieves the required data from the data source and stores it in a temporary data store for further processing.

[0542] Input: Data source (database, spreadsheet, etc.)

[0543] Output: Data saved to a temporary data store

[0544] What it does: For example, execute a SQL query to retrieve project progress data from a database and store it in a temporary data store (for example, Redis or a temporary file).

[0545] Step 5:

[0546] The server analyzes the content and format of the data stored in the temporary data store. For example, in the case of a CSV file, it reads the header information and determines the data type of each column.

[0547] Input: Data stored in a temporary data store

[0548] Output: Analysis results (data format and content)

[0549] Specific operation: Uses Python's pandas library to read a CSV file and parse it into a data frame.

[0550] Step 6:

[0551] The server defines the conditions for identifying the required data items based on the analysis results. The conditions are expressed as SQL queries and filtering logic.

[0552] Input: Analysis results (data format and content)

[0553] Output: Condition definition (SQL query or filtering logic)

[0554] Specific behavior: Generates a query like "SELECT task_name, progress FROM project_data WHERE date BETWEEN '2023-01-01' AND '2023-01-07'".

[0555] Step 7:

[0556] The server extracts the required data from the temporary data store based on defined criteria, for example, by running an SQL query to extract only data from a specific time period.

[0557] Input: Condition definition (SQL query or filtering logic)

[0558] Output: Extracted data

[0559] Specific behavior: Executes an SQL query to retrieve data that matches the specified criteria.

[0560] Step 8:

[0561] The server formats the extracted data and converts it to a suitable format for final output (PDF, Excel, etc.). For example, to generate a PDF report, use the ReportLab library.

[0562] Input: Extracted data

[0563] Output: Formatted data (output file)

[0564] What it does: Use ReportLab to add graphs and charts to PDF documents.

[0565] Step 9:

[0566] The server saves the generated output file in cloud storage and generates a link to it.

[0567] Input: Formatted data (output file)

[0568] Output: Cloud storage link

[0569] What it does: Uploads a file using the cloud storage API and gets its link.

[0570] Step 10:

[0571] The server will notify the user of the cloud storage link via email or chat tool.

[0572] Input: Cloud storage link

[0573] Output: Notification to user (email or chat)

[0574] Specific operation: Send a link to the user using an email sending service or chat API (e.g., Slack API).

[0575] Step 11:

[0576] The user receives a notification, clicks a link to download the output file (e.g., a PDF report), and reviews the contents.

[0577] Input: User notification

[0578] Output: The downloaded output file

[0579] What happens: User clicks on a link, downloads a file, and reviews its contents.

[0580] Step 12:

[0581] The user checks the content for any problems and instructs the server to provide feedback or make revisions as necessary.

[0582] Input: User feedback and rework instructions

[0583] Output: Redirect to server

[0584] Specific operation: Based on the review results, the user re-enters the necessary corrections as a prompt sentence and sends it to the server.

[0585] (Application example 1)

[0586] 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."

[0587] Modern logistics centers require a series of processes, including data collection, analysis, extraction, and output generation from a wide variety of data sources. However, doing all of this manually is extremely time-consuming and labor-intensive, resulting in errors and delays. It is also difficult to optimize inventory information and delivery routes in real time, reducing the efficiency of management operations. To solve these issues, a system is needed that automatically collects and analyzes data, and efficiently manages inventory and optimizes delivery routes.

[0588] 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.

[0589] In this invention, the server includes means for collecting data from data sources, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying a user of the generated output, means for analyzing logistics management information and calculating an optimal delivery route, and means for monitoring inventory information in real time and notifying necessary warnings, thereby enabling automated data management, efficient inventory management, and calculation of an optimal delivery route within a logistics center.

[0590] "Data Sources" are various information sources that serve as starting points for collecting data.

[0591] "Means for collecting data" refers to a function for obtaining necessary information from a specified data source.

[0592] "Means for analyzing data format" refers to the function of identifying the structure and type of collected data and processing it in an appropriate format.

[0593] "Means for extracting necessary data" refers to the function of extracting important information from the analyzed data based on specific conditions.

[0594] The "means for converting and saving into a specified format" is a function for converting extracted data into a specified format and saving it so that it can be referenced later.

[0595] "Means for notifying the user of the generated output" is a function that notifies the user of the final generated report or information.

[0596] "Means for analyzing logistics management information and calculating optimal delivery routes" is a function that uses data collected within the logistics center to derive efficient delivery routes.

[0597] "Means of monitoring inventory information in real time and notifying necessary warnings" refers to a function that constantly monitors the inventory status in the warehouse and immediately issues an alert if an abnormality occurs.

[0598] This invention is a system for automating and streamlining inventory management and delivery route optimization in logistics centers. This system combines various methods for data collection, analysis, extraction, output generation, and notification.

[0599] Hardware and software used

[0600] Hardware:

[0601] Smartphone (iOS / Android)

[0602] Logistics robots

[0603] IoT sensors (for inventory management)

[0604] GPS device (for shipping tracking)

[0605] software:

[0606] Database (PostgreSQL, MySQL)

[0607] Cloud storage (AWS S3, Google Drive)

[0608] API services (Google Maps API, Twilio for notifications)

[0609] AI / ML models (TensorFlow, PyTorch)

[0610] The server uses this hardware and software to perform the following processes.

[0611] Data collection

[0612] The server collects data from inventory sensors and GPS devices as data sources, thereby obtaining real-time inventory information and delivery route information within the distribution center. For example, sensors detect the current inventory status and input that information into a database.

[0613] Data analysis

[0614] The server analyzes the format of the collected data and extracts the necessary data, such as detailed information about a specific product from inventory data or analyzing GPS data to confirm the current delivery route and time.

[0615] Data extraction and output generation

[0616] The server converts the extracted data into a specified format and generates output, such as generating an inventory report in PDF format or calculating the optimal delivery route and saving it as an HTML report.

[0617] notification

[0618] The generated output is stored in cloud storage and the user is notified via email or chat using API services such as Twilio.

[0619] Specific examples

[0620] For example, if you want to generate a report on products that have significantly decreased in stock this week, the system collects data from sensors in real time, analyzes that data, extracts product information that falls within a specified decrease rate, compiles it into a report, and notifies the user.

[0621] Prompt Sentence Examples

[0622] "Please create a report on products that have significantly decreased based on this week's inventory status. For example, generate a PDF report containing a list of products whose inventory has decreased by 20% or more and the rate of decrease, and send it to the specified email address."

[0623] Such a system will make logistics center management more efficient and enable optimization of inventory and delivery routes.

[0624] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0625] Step 1:

[0626] Data collection

[0627] The server collects data from data sources such as inventory sensors and GPS devices. Specifically, it calls the sensor API and GPS API to obtain real-time data. The input is the API key and authentication information, and the output is stored in the database as inventory counts and delivery route information.

[0628] Step 2:

[0629] Data analysis

[0630] The server analyzes the format of the collected data. Specifically, it analyzes data formats such as CSV and JSON to check the field names and data types. The input is raw data from the database, and the output is structural information about the analyzed data. This process determines which data can be used and how.

[0631] Step 3:

[0632] Data Extraction

[0633] The server extracts the necessary information from the parsed data. Specifically, it executes SQL queries to extract data about specific products and delivery routes. The input is the parsed data, and the output is the extracted target data. This process identifies the necessary information and makes it available for the next step.

[0634] Step 4:

[0635] Output Generation

[0636] The server converts the extracted data into a specified format and generates the output. Specifically, it inserts the data into a report template and generates a report in PDF or HTML format. The input is the extracted data, and the output is the generated output file. This step creates a report in a format that is intuitive for the user.

[0637] Step 5:

[0638] notification

[0639] The server notifies the user of the generated output. Specifically, it sends a notification using Twilio or email API. The input is the generated output file and destination information, and the output is a notification to the user. This allows the user to immediately check the new report.

[0640] 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.

[0641] The present invention is a system that collects data from a data source, analyzes and extracts it, generates output in a specified format, and notifies a user, and further combines it with an emotion engine that recognizes the user's emotions. This system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, a notification means, and an emotion engine.

[0642] Overall system configuration

[0643] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. The emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system. Users issue instructions, check the results, and make adjustments as necessary.

[0644] System processing flow

[0645] Data collection

[0646] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report). The emotion engine simultaneously recognizes the user's emotions.

[0647] Server: Receives user instructions and information from the emotion engine and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[0648] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[0649] Server: Stores the collected data in a temporary data store.

[0650] Data analysis

[0651] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[0652] Server: Defines conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data, taking into account the user's emotional state.

[0653] Data Extraction

[0654] Server: Extracts the required data from the temporary data store based on the defined conditions, which are adjusted accordingly based on the analysis results of the emotion engine.

[0655] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs, tables).

[0656] Output generation and notification

[0657] Server: Converts the formatted data into the specified format (e.g. PDF, Excel, HTML report) and saves it.

[0658] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine (for example, a brief notification when stress is high).

[0659] User: Receives a notification, downloads the generated output, and reviews it. Feedback based on emotions is also recorded.

[0660] Specific examples

[0661] Scenario: Weekly report generation and emotion recognition

[0662] 1. User: Instructs the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired).

[0663] 2. Server: Accessed with appropriate credentials to collect data from project management tools and spreadsheets.

[0664] 3. Server: Stores the data in a temporary data store and analyzes its format and content.

[0665] 4. Server: Using the results of the emotion engine, set conditions to identify the required data items. For example, if the user is feeling stressed, prioritize summary data.

[0666] 5. Server: Extract data based on criteria and organize the information needed for weekly reports.

[0667] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[0668] 7. Server: Saves the completed report to cloud storage and sends a notification to the user reflecting the results of the emotion engine (e.g., a brief email notification with an encouraging message).

[0669] 8. User: Checks email, opens report, examines content, makes adjustments as needed, and provides emotional feedback to the system.

[0670] The system dynamically responds to the user's emotional state and aims to improve the user experience while streamlining the entire process from data collection to output generation.

[0671] The processing flow will be explained below.

[0672] Step 1:

[0673] User: Instructs the system to generate the required report (e.g., weekly report, monthly sales report). Through a dedicated interface, the user specifies the data source, output format, report conditions, etc. Furthermore, the emotion engine recognizes the user's emotions in real time.

[0674] Step 2:

[0675] Server: Receives user instructions and sentiment analysis results from the sentiment engine, and checks a list of target data sources, including databases, spreadsheets, cloud storage, etc.

[0676] Step 3:

[0677] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). After successful authentication at this stage, check the access permissions for each data source.

[0678] Step 4:

[0679] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[0680] Step 5:

[0681] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[0682] Step 6:

[0683] Server: Based on the content of the analyzed data, define the conditions for extracting the necessary data items (e.g., project progress information, sales amount). At this time, set conditions according to the user's emotions based on the analysis results of the emotion engine.

[0684] Step 7:

[0685] Server: Extracts the required data from the temporary data store based on the defined criteria. For example, it applies SQL queries and filtering logic to select the target data. This selection process is also adjusted based on the results of the emotion engine.

[0686] Step 8:

[0687] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[0688] Step 9:

[0689] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[0690] Step 10:

[0691] Server: Notifies the user of the generated output. At this time, the notification method and message content are optimized based on the results of the emotion engine. For example, if the user is feeling stressed, a concise and easy-to-understand notification is sent.

[0692] Step 11:

[0693] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[0694] Step 12:

[0695] User: Adjusts the output as needed and gives final approval, with the emotion engine recording the user's feedback for further analysis.

[0696] Through these steps, the system can adapt to the user's emotional state and efficiently process data from collection to output generation, saving the user time and effort and providing a better user experience.

[0697] Example 2

[0698] 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."

[0699] Conventional data collection and analysis systems were unable to take into account the user's emotional state, making it difficult to respond flexibly to the user's psychological conditions, such as stress and fatigue. Furthermore, they were limited to simple data collection and analysis and lacked functionality to improve the user experience. This resulted in a heavy burden on the user and reduced system usage efficiency.

[0700] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This makes it possible to analyze the user's emotions in real time and adjust the operation of the entire system based on the results.

[0701] A "data source" is the source from which data is collected, including databases, spreadsheets, cloud storage, etc.

[0702] "Collection" is the act of obtaining necessary information from a data source.

[0703] "Analysis" is the process of examining and interpreting collected data to understand its content and form.

[0704] "Extraction" is the act of extracting necessary information from analyzed data.

[0705] "Format" means a particular form or standard for storing or displaying data.

[0706] "Notification" is the act of communicating generated output to a user.

[0707] An "emotion engine" is a software or hardware function that analyzes a user's emotional state in real time and provides the results.

[0708] "Adjustment" is the act of dynamically changing the behavior and settings of the entire system based on the results of the emotion engine.

[0709] "Authentication information" refers to the information required to access a data source, including API keys and database connection strings.

[0710] "Filtering logic" refers to logical conditions or algorithms for selecting target data based on collected data.

[0711] "Output" means the final product of the analyzed, extracted, and transformed data, presented in the form of reports and / or graphs.

[0712] This invention is a system that collects, analyzes, and extracts data from data sources, generates output in a specified format, and notifies a user. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to respond flexibly while taking into account the user's psychological state. This system includes data collection means, data format analysis means, data extraction means, output conversion means, notification means, and an emotion engine.

[0713] Overall system configuration

[0714] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. Furthermore, the emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system.

[0715] Hardware and software used

[0716] Specifically, data collection involves software that accesses databases and cloud storage using API keys and database connection strings. Data analysis and transformation is performed using the Python pandas library, and output is generated using tools such as PDF generation tools (e.g., ReportLab) and Excel file creation tools (e.g., openpyxl). The emotion engine includes software for analyzing user emotions in real time. This emotion engine performs emotion analysis using machine learning models.

[0717] Specific examples

[0718] Take the example of weekly report generation and emotion recognition. A user requests the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired). The server collects data from project management tools or spreadsheets, accessing them with appropriate credentials. The collected data is stored in a temporary data store and analyzed for format and content. Based on the results of the emotion engine, conditions are set to identify the required data items. For example, if the user is feeling stressed, summary data is prioritized.

[0719] Based on these settings, data is extracted and the information required for the weekly report is organized. A weekly report in PDF format is generated based on the formatted data. The completed report is saved in cloud storage, and a notification reflecting the results of the emotion engine is sent to the user. For example, a brief email notification containing an encouraging message is sent.

[0720] Prompt Sentence Examples

[0721] Below are some example prompts to be input to the generative AI model of this system:

[0722] Follow the steps below to generate a weekly report. Also use the sentiment engine to analyze user sentiment and take the results into account in your data extraction and notifications.

[0723] 1. Collect weekly data from your project management tool.

[0724] 2. Analyze the data format to identify the required items.

[0725] 3. Set the conditions for data extraction taking into account the user's emotions.

[0726] 4. Generate weekly reports in PDF format.

[0727] 5. Save the report to cloud storage and notify the user.

[0728] This example and prompts provide a detailed understanding of the process by which the system takes the user's emotions into account when collecting data and generating output.

[0729] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0730] Step 1: User Instructions

[0731] User: The user instructs the system to generate a weekly report. As input, the user enters the command "generate a weekly report." The emotion engine recognizes the user's current emotion (e.g., stress or fatigue). This command is sent to the server.

[0732] Specific operation: A user accesses the system dashboard and clicks the report generation button. The emotion engine then collects and analyzes emotion data from the user's facial expressions and voice.

[0733] Step 2: Accessing the Data Source

[0734] Server: Takes as input the user's instructions and emotion engine's emotion data. The server checks the list of data sources and prepares access. It identifies the authentication information to use (API key, database connection string).

[0735] What happens: The server loads the list of database URLs and API keys and performs authentication for each data source.

[0736] Step 3: Collect and store data

[0737] Server: Accesses data sources using API keys and database connection strings to collect data. Authentication information for each data source and the data to be collected are given as input. The collected data is stored in a temporary data store.

[0738] What happens: The server connects to the database using an API, sends SQL queries or API requests to retrieve data, and stores that data in a temporary data store.

[0739] Step 4: Parsing the data format

[0740] Server: Analyzes the content and format of the temporarily stored data. As input, it receives the data stored in the temporary data store. It checks the file format (CSV, Excel, SQL database, etc.) and extracts the headers and metadata for the required information.

[0741] What happens: The server reads the header line of the data file, runs an algorithm to identify the file format, and analyzes the data content using the Python pandas library.

[0742] Step 5: Define data conditions

[0743] Server: Defines the conditions for extracting necessary data items from the analyzed data, taking into account the user's emotional state. The emotion engine's emotional data and the analyzed data are given as input. Specific conditions are set.

[0744] How it works: The server dynamically sets the conditions for data extraction queries based on information from the emotion engine. For example, if stress is high, summary data is prioritized.

[0745] Step 6: Extract the data

[0746] Server: Extracts the required data from the temporary data store based on the defined conditions. As input, the set conditions and the data stored in the temporary data store are given. As a result, the required data is retrieved.

[0747] Specific operation: Executes a data extraction query and retrieves target data from multiple tables by joining them.

[0748] Step 7: Data processing and organization

[0749] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs or tables). The extracted data is given as input. The result is formatted data.

[0750] How it works: The server aggregates the data and converts it into a data frame using the Python pandas library. Libraries such as matplotlib and seaborn are used to visualize the data.

[0751] Step 8: Generate output

[0752] Server: Converts and saves the formatted data in a specified format (e.g. PDF, Excel, HTML report). As input, the formatted data is given. As a result, the final output file is generated.

[0753] Specific operation: The server generates PDF or Excel files using a generative AI model library (e.g., ReportLab or openpyxl).

[0754] Step 9: Optimizing notifications

[0755] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine. The emotion engine data and the generated output are given as input. As a result, the appropriate notification method and message content are set.

[0756] What happens: The server uses an email notification API (e.g., SendGrid or SMTP) to send an optimized message to the user, such as a brief notification email with an encouraging message.

[0757] Step 10: Check the output

[0758] User: Upon receiving a notification, downloads the generated output and checks its contents. The notified output link is given as input. As a result, the user checks the output and provides feedback if necessary.

[0759] Specific operations: The user accesses the cloud storage, downloads the output file, checks its contents, and inputs and submits feedback through the system interface.

[0760] (Application example 2)

[0761] 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."

[0762] In modern virtual stores, product recommendations and customer support tailored to the customer's emotional state are important for improving customer satisfaction. However, conventional systems have difficulty recognizing customer emotions in real time and providing optimal services based on that information.

[0763] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, emotion recognition means for recognizing the user's emotions in real time, and means for adjusting the operation of the entire system based on the emotion information obtained by the emotion recognition means. This makes it possible to provide product recommendations and support according to the customer's emotional state.

[0764] "Data Source" means a source of data, such as a database, spreadsheet, or cloud storage.

[0765] A "data collection method" is a method that has the function of obtaining the necessary data from a data source, such as using an API call or a database query.

[0766] The "data format analysis means" is a means having a function for analyzing the structure and format of collected data, and recognizes file formats and extracts metadata.

[0767] "Data extraction means" refers to a means that has the function of extracting specific necessary information from the analyzed data, applying filtering logic and search conditions.

[0768] An "output conversion means" is a means that has the function of converting extracted data into a specified format and saving it, such as PDF, Excel, or HTML.

[0769] "Notification means" refers to a means that has the function of notifying the user of the generated output, such as email, app notification, or message delivery.

[0770] "Emotion recognition means" refers to a means that has the function of identifying a user's emotions in real time and acquiring that information, and utilizes a facial recognition camera and emotion analysis software.

[0771] The "means for adjusting the operation of the entire system" is a means for adjusting other functions and behaviors of the system based on the emotional information acquired by the emotional recognition means, and customizes the content of the service according to the emotional state.

[0772] This invention realizes a system that provides product recommendations and customer support in a virtual store according to the emotional state of the customer. The system operates using smart glasses or a head-mounted display worn by the user, analyzes the emotional state in real time through emotion recognition means, and adjusts the operation of the entire system based on that information.

[0773] Hardware and Software Configuration

[0774] Hardware:

[0775] Cameras (built into smart glasses or head-mounted displays)

[0776] Server (performs data processing and sentiment analysis)

[0777] User's device (smartphone, tablet, etc.)

[0778] software:

[0779] OpenCV (a library that provides face recognition functionality)

[0780] EmotionRecognitionModule (software for emotion analysis)

[0781] DataSourceModule (data collection and filtering software)

[0782] OutputFormatModule (software that converts data output formats)

[0783] Program processing

[0784] The server first acquires video data using the camera installed on the user's device and performs real-time emotion analysis using emotion recognition means. Based on the analysis results, it collects, analyzes, and extracts appropriate data. Next, it converts the extracted data into a specified format (e.g., a product recommendation list) and notifies the user of the results. The notification content is customized based on the user's emotional state.

[0785] Specific examples

[0786] For example, when a user enters a virtual store, the camera installed in the smart glasses captures the user's face, and if the emotion recognition means determines that the user is smiling (happy), the server will prioritize displaying a list of new products. Conversely, if the user is feeling stressed, the server will display a list of products with a relaxing effect (aroma candles, relaxation gadgets, etc.).

[0787] Usage example

[0788] Example prompt sentence:

[0789] When a user wears smart glasses and enters a virtual store, please capture their face with a camera and perform real-time emotion analysis. If the emotion is "smile", please suggest a new product list. If the emotion is "stress", please suggest a product list with a relaxing effect.

[0790] By using this system, high-quality customer support can be provided in a virtual store according to the customer's emotional state, resulting in improved customer satisfaction.

[0791] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0792] Step 1:

[0793] A user puts on smart glasses and enters a virtual store. The device's camera captures the user's face. The captured video data is sent to the server in real time. The input is the user's face video data, and the output is the video data sent to the server.

[0794] Step 2:

[0795] The server receives the video data and uses OpenCV to recognize the user's face. It then uses the EmotionRecognitionModule to analyze the user's emotions. The input is video data, and face recognition and emotion analysis are performed as data processing. The output is the user's emotional information (e.g., smiling, stress, etc.).

[0796] Step 3:

[0797] The server determines the next data processing instructions based on the obtained emotional information. Specifically, it sets conditions such as prioritizing a list of new products if the person is smiling, or a list of products with a relaxing effect if the person is under stress. The input is emotional information, and the output is the data processing instructions.

[0798] Step 4:

[0799] The server uses the DataSourceModule to collect the required data from the appropriate data source based on the configured instructions. Examples include collecting data from a product database or cloud storage. The input is the data processing instructions, and the data is collected as data processing. The output is the collected product data.

[0800] Step 5:

[0801] The server analyzes the format of the collected data. Using data format analysis means, it analyzes and extracts the data structure and necessary information. The input is the collected product data, and format analysis is performed as data calculation. The output is the analyzed data.

[0802] Step 6:

[0803] The server extracts necessary data from the analyzed data. Using the data extraction method, it filters appropriate product information based on the emotion information. The input is the analyzed data, and filtering logic is applied as data processing. The output is the extracted product information.

[0804] Step 7:

[0805] The server converts the extracted data into the specified format and saves it using OutputFormatModule. For example, converting a recommended product list into PDF or HTML format. The input is the extracted product information, and format conversion is performed as data processing. The output is the formatted output.

[0806] Step 8:

[0807] The server notifies the user of the generated output. Based on the results of the emotion recognition means, the notification method and message content are optimized. For example, if stress is high, a simple notification is sent. The input is the formatted output, and the output is the notification to the user.

[0808] Step 9:

[0809] The user receives a notification and checks the provided product list. If necessary, the user can provide feedback to the system using prompt sentences. The input feedback from the user helps improve the system.

[0810] In this way, the present invention realizes a system that can provide optimal product recommendations and support in a virtual store according to the emotional state of the customer.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] [Third embodiment]

[0815] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0816] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0817] 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).

[0818] 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.

[0819] 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.

[0820] 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).

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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."

[0827] The present invention relates to a system for collecting, analyzing, and extracting data from data sources, generating output in a specified format, and notifying a user. The system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, and a notification means.

[0828] Overall system configuration

[0829] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. Users issue instructions, check the results, and make adjustments as necessary.

[0830] System processing flow

[0831] Data collection

[0832] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report).

[0833] Server: Receives user instructions and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[0834] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[0835] Server: Stores the collected data in a temporary data store.

[0836] Data analysis

[0837] Server: Analyzes the content and format of the stored data, for example, checking the file format (CSV, Excel, SQL database, etc.) and parsing header information and metadata.

[0838] Server: Define the conditions for extracting the required data items (project progress information, sales amount, etc.).

[0839] Data Extraction

[0840] Server: Extracts the required data from the temporary data store based on the defined criteria, for example, using SQL queries and filtering logic to select the target data.

[0841] Server: Organizes the extracted data and converts it into a format suitable for the final output (graphs, tables, etc.).

[0842] Output generation and notification

[0843] Server: Converts the formatted data into the specified format (PDF, Excel, HTML report, etc.) and saves it.

[0844] Server: Notifies the user of the generated output. For example, it saves it in cloud storage and sends the link to the user via email or chat tool.

[0845] User: Upon receiving notification, downloads the generated output, reviews it, makes any necessary adjustments, and finally approves it.

[0846] Specific examples

[0847] Scenario: Generating a weekly report

[0848] 1. User: Instructs the generation of a weekly report.

[0849] 2. Server: Accessed with the necessary API keys to collect data from project management tools (e.g., online project management systems) and spreadsheets.

[0850] 3. Server: Retrieves project progress data from each data source and stores it in a temporary data store.

[0851] 4. Server: Analyzes the format of the collected data and identifies task status information.

[0852] 5. Server: Extracts data based on defined criteria and organizes the information required for weekly reports.

[0853] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[0854] 7. Server: Saves the completed report to cloud storage and emails the user a link to the report.

[0855] 8. User: Checks email, opens report and examines contents.

[0856] 9. User: Make any necessary adjustments and give final approval.

[0857] This invention automates the entire process of data collection, analysis, extraction, and output, saving users time and effort, and is expected to improve work efficiency.

[0858] The processing flow will be explained below.

[0859] Step 1:

[0860] User: Instructs the generation of the required report (e.g., weekly report, monthly sales report). The user specifies the data source, output format, report conditions, etc. through a dedicated interface.

[0861] Step 2:

[0862] Server: Receives user instructions and checks the list of target data sources, which can include databases, spreadsheets, cloud storage, etc.

[0863] Step 3:

[0864] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). At this stage, after successful authentication, access permissions are verified.

[0865] Step 4:

[0866] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[0867] Step 5:

[0868] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[0869] Step 6:

[0870] Server: Define the conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data. For example, use keyword search or regular expressions to identify the necessary information.

[0871] Step 7:

[0872] Server: Extracts the required data from the temporary data store based on the defined criteria, and applies SQL queries and filtering logic to select the target data.

[0873] Step 8:

[0874] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[0875] Step 9:

[0876] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[0877] Step 10:

[0878] Server: Notifies the user of the generated output. Notification methods include saving it to cloud storage, sending a link to it via email, or sharing it via a chat tool.

[0879] Step 11:

[0880] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[0881] Step 12:

[0882] User: Revises output as needed and gives final approval. Revises output using a PDF reader or spreadsheet software.

[0883] Through the above steps, the system can respond to user requests, smoothly collect, analyze, and extract data from different formats and locations, and generate and provide output.

[0884] Example 1

[0885] 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."

[0886] In conventional systems, the processes of data collection, analysis, extraction, format conversion, and notification were often manual or only partially automated, resulting in a lack of overall efficiency. This meant that users had to spend time and effort processing large amounts of data and generating reports, making it difficult to improve work efficiency. In addition, differences in authentication methods and data formats corresponding to different data sources made data integration and analysis technically complex.

[0887] 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.

[0888] In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This enables efficient collection and analysis of data. The server also includes means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, means for receiving and analyzing a prompt sentence in natural language, and means for securely accessing the data source using authentication information. This automates a series of data processing tasks performed by the user, enabling efficient and rapid generation of desired reports.

[0889] A "data source" is a location or system where the raw data from which a system obtains information is stored.

[0890] "Means of collection" refers to the methods and devices used to obtain the required data from the data source.

[0891] "Means of analysis" refers to the methods and algorithms used to understand the format and content of the collected data and find the necessary information.

[0892] "Extraction means" refers to methods or tools for extracting data that meets specific conditions from the analyzed data.

[0893] "Means of converting and saving into a specified format" refers to the method or procedure for converting extracted data into a specified format (PDF, Excel, etc.) and saving it.

[0894] "Means of notification" refers to the methods and techniques used to notify users of the generated output.

[0895] "Means for receiving and analyzing natural language prompts" refers to methods or techniques for receiving instructions in natural language from a user, analyzing them, and performing appropriate processing.

[0896] "Authentication information" refers to information (such as an API key or password) required to securely access a data source.

[0897] A "means for securely accessing a data source" refers to a method or algorithm for securely connecting to a data source using authentication information.

[0898] A "temporary data store" is a database or storage for temporarily storing collected data.

[0899] "Filtering logic" refers to algorithms or methods for filtering data based on specific conditions.

[0900] The present invention is a system that collects data from data sources, analyzes and extracts it, generates output in a specified format, and notifies users. This system consists of a server, a terminal, and a user.

[0901] Overall system configuration

[0902] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. The terminals are the interfaces that transmit user instructions to the server. Users issue instructions to the system, check the generated output, and make adjustments as necessary.

[0903] Hardware and Software Configuration

[0904] Server: Performs data collection, parsing, extraction, transformation, and notification functions. This server manages credentials to access various databases and APIs, securely exchanges data using communication protocols, and executes SQL queries and filtering logic for data analysis.

[0905] Terminal: The user inputs instructions and the results are displayed. The required hardware is a PC or tablet. It also uses an application or web browser that provides an interface such as a GUI (Graphical User Interface).

[0906] User: Enter specific prompts into the system and view the generated output. For example, enter natural language prompts such as "Generate this week's progress report" or "Generate this month's sales report."

[0907] Specific examples of processing

[0908] Generate weekly reports

[0909] 1. User: Instructs the generation of a weekly report. For example, the user enters the prompt "Please generate this week's progress report" into the terminal.

[0910] 2. Terminal: Sends this instruction to the server.

[0911] 3. Server: To collect data from project management tools (e.g., online project management systems) and spreadsheets, you connect securely using credentials, specifically, API keys to access data sources.

[0912] 4. Server: Retrieves project progress data from each data source and stores this data in a temporary data store.

[0913] 5. Server: Analyzes the format of the stored data and identifies the required data items (e.g., task status information).

[0914] 6. Server: Extracts the required data from the temporary data store based on defined criteria, for example, running an SQL query to extract only data from a specific time period.

[0915] 7. Server: Format the extracted data and generate a PDF report. Add graphs and charts using tools like ReportLab.

[0916] 8. Server: Saves the completed report to cloud storage and generates a link to it.

[0917] 9. Server: Sends the link to the user via email or chat tool.

[0918] 10. User: Checks email, opens report, checks contents, makes necessary adjustments and sends command to server again.

[0919] This invention is a system that uses a generative AI model to analyze prompts, automatically collect, analyze, and extract data, and generate targeted reports to notify users, thereby significantly reducing the user's workload and improving work efficiency.

[0920] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0921] Step 1:

[0922] The user uses a terminal to enter a prompt that instructs the system to generate a specific report, for example, "Please generate this week's progress report." This prompt is then sent from the terminal to the server.

[0923] Input: The prompt text entered by the user

[0924] Output: The prompt sent to the server

[0925] Specific behavior: The user enters a prompt sentence into the input form and clicks the submit button.

[0926] Step 2:

[0927] The server receives and parses the prompt, using a generative AI model to understand the content of the prompt and identify the required action.

[0928] Input: The prompt sent to the server

[0929] Output: Analysis results (type of report to generate and required data source)

[0930] What it does: It uses a natural language processing library (e.g., NLTK or Spacy) to parse the prompt and identify the type of report to generate (e.g., weekly status report) and the data source (e.g., project management tool).

[0931] Step 3:

[0932] Connect to the data source using the credentials (such as an API key or database connection string) to access the data source identified by the server.

[0933] Input: Analysis results (required data source and credentials)

[0934] Output: Connection to a data source

[0935] Specific operation: Connect to a database server using a database connection string, or access a Web API using an API key.

[0936] Step 4:

[0937] The server retrieves the required data from the data source and stores it in a temporary data store for further processing.

[0938] Input: Data source (database, spreadsheet, etc.)

[0939] Output: Data saved to a temporary data store

[0940] What it does: For example, execute a SQL query to retrieve project progress data from a database and store it in a temporary data store (for example, Redis or a temporary file).

[0941] Step 5:

[0942] The server analyzes the content and format of the data stored in the temporary data store. For example, in the case of a CSV file, it reads the header information and determines the data type of each column.

[0943] Input: Data stored in a temporary data store

[0944] Output: Analysis results (data format and content)

[0945] Specific operation: Uses Python's pandas library to read a CSV file and parse it into a data frame.

[0946] Step 6:

[0947] The server defines the conditions for identifying the required data items based on the analysis results. The conditions are expressed as SQL queries and filtering logic.

[0948] Input: Analysis results (data format and content)

[0949] Output: Condition definition (SQL query or filtering logic)

[0950] Specific behavior: Generates a query like "SELECT task_name, progress FROM project_data WHERE date BETWEEN '2023-01-01' AND '2023-01-07'".

[0951] Step 7:

[0952] The server extracts the required data from the temporary data store based on defined criteria, for example, by running an SQL query to extract only data from a specific time period.

[0953] Input: Condition definition (SQL query or filtering logic)

[0954] Output: Extracted data

[0955] Specific behavior: Executes an SQL query to retrieve data that matches the specified criteria.

[0956] Step 8:

[0957] The server formats the extracted data and converts it to a suitable format for final output (PDF, Excel, etc.). For example, to generate a PDF report, use the ReportLab library.

[0958] Input: Extracted data

[0959] Output: Formatted data (output file)

[0960] What it does: Use ReportLab to add graphs and charts to PDF documents.

[0961] Step 9:

[0962] The server saves the generated output file in cloud storage and generates a link to it.

[0963] Input: Formatted data (output file)

[0964] Output: Cloud storage link

[0965] What it does: Uploads a file using the cloud storage API and gets its link.

[0966] Step 10:

[0967] The server will notify the user of the cloud storage link via email or chat tool.

[0968] Input: Cloud storage link

[0969] Output: Notification to user (email or chat)

[0970] Specific operation: Send a link to the user using an email sending service or chat API (e.g., Slack API).

[0971] Step 11:

[0972] The user receives a notification, clicks a link to download the output file (e.g., a PDF report), and reviews the contents.

[0973] Input: User notification

[0974] Output: The downloaded output file

[0975] What happens: User clicks on a link, downloads a file, and reviews its contents.

[0976] Step 12:

[0977] The user checks the content for any problems and instructs the server to provide feedback or make revisions as necessary.

[0978] Input: User feedback and rework instructions

[0979] Output: Redirect to server

[0980] Specific operation: Based on the review results, the user re-enters the necessary corrections as a prompt sentence and sends it to the server.

[0981] (Application example 1)

[0982] 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."

[0983] Modern logistics centers require a series of processes, including data collection, analysis, extraction, and output generation from a wide variety of data sources. However, doing all of this manually is extremely time-consuming and labor-intensive, resulting in errors and delays. It is also difficult to optimize inventory information and delivery routes in real time, reducing the efficiency of management operations. To solve these issues, a system is needed that automatically collects and analyzes data, and efficiently manages inventory and optimizes delivery routes.

[0984] 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.

[0985] In this invention, the server includes means for collecting data from data sources, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying a user of the generated output, means for analyzing logistics management information and calculating an optimal delivery route, and means for monitoring inventory information in real time and notifying necessary warnings, thereby enabling automated data management, efficient inventory management, and calculation of an optimal delivery route within a logistics center.

[0986] "Data Sources" are various information sources that serve as starting points for collecting data.

[0987] "Means for collecting data" refers to a function for obtaining necessary information from a specified data source.

[0988] "Means for analyzing data format" refers to the function of identifying the structure and type of collected data and processing it in an appropriate format.

[0989] "Means for extracting necessary data" refers to the function of extracting important information from the analyzed data based on specific conditions.

[0990] The "means for converting and saving into a specified format" is a function for converting extracted data into a specified format and saving it so that it can be referenced later.

[0991] "Means for notifying the user of the generated output" is a function that notifies the user of the final generated report or information.

[0992] "Means for analyzing logistics management information and calculating optimal delivery routes" is a function that uses data collected within the logistics center to derive efficient delivery routes.

[0993] "Means of monitoring inventory information in real time and notifying necessary warnings" refers to a function that constantly monitors the inventory status in the warehouse and immediately issues an alert if an abnormality occurs.

[0994] This invention is a system for automating and streamlining inventory management and delivery route optimization in logistics centers. This system combines various methods for data collection, analysis, extraction, output generation, and notification.

[0995] Hardware and software used

[0996] Hardware:

[0997] Smartphone (iOS / Android)

[0998] Logistics robots

[0999] IoT sensors (for inventory management)

[1000] GPS device (for shipping tracking)

[1001] software:

[1002] Database (PostgreSQL, MySQL)

[1003] Cloud storage (AWS S3, Google Drive)

[1004] API services (Google Maps API, Twilio for notifications)

[1005] AI / ML models (TensorFlow, PyTorch)

[1006] The server uses this hardware and software to perform the following processes.

[1007] Data collection

[1008] The server collects data from inventory sensors and GPS devices as data sources, thereby obtaining real-time inventory information and delivery route information within the distribution center. For example, sensors detect the current inventory status and input that information into a database.

[1009] Data analysis

[1010] The server analyzes the format of the collected data and extracts the necessary data, such as detailed information about a specific product from inventory data or analyzing GPS data to confirm the current delivery route and time.

[1011] Data extraction and output generation

[1012] The server converts the extracted data into a specified format and generates output, such as generating an inventory report in PDF format or calculating the optimal delivery route and saving it as an HTML report.

[1013] notification

[1014] The generated output is stored in cloud storage and the user is notified via email or chat using API services such as Twilio.

[1015] Specific examples

[1016] For example, if you want to generate a report on products that have significantly decreased in stock this week, the system collects data from sensors in real time, analyzes that data, extracts product information that falls within a specified decrease rate, compiles it into a report, and notifies the user.

[1017] Prompt Sentence Examples

[1018] "Please create a report on products that have significantly decreased based on this week's inventory status. For example, generate a PDF report containing a list of products whose inventory has decreased by 20% or more and the rate of decrease, and send it to the specified email address."

[1019] Such a system will make logistics center management more efficient and enable optimization of inventory and delivery routes.

[1020] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1021] Step 1:

[1022] Data collection

[1023] The server collects data from data sources such as inventory sensors and GPS devices. Specifically, it calls the sensor API and GPS API to obtain real-time data. The input is the API key and authentication information, and the output is stored in the database as inventory counts and delivery route information.

[1024] Step 2:

[1025] Data analysis

[1026] The server analyzes the format of the collected data. Specifically, it analyzes data formats such as CSV and JSON to check the field names and data types. The input is raw data from the database, and the output is structural information about the analyzed data. This process determines which data can be used and how.

[1027] Step 3:

[1028] Data Extraction

[1029] The server extracts the necessary information from the parsed data. Specifically, it executes SQL queries to extract data about specific products and delivery routes. The input is the parsed data, and the output is the extracted target data. This process identifies the necessary information and makes it available for the next step.

[1030] Step 4:

[1031] Output Generation

[1032] The server converts the extracted data into a specified format and generates the output. Specifically, it inserts the data into a report template and generates a report in PDF or HTML format. The input is the extracted data, and the output is the generated output file. This step creates a report in a format that is intuitive for the user.

[1033] Step 5:

[1034] notification

[1035] The server notifies the user of the generated output. Specifically, it sends a notification using Twilio or email API. The input is the generated output file and destination information, and the output is a notification to the user. This allows the user to immediately check the new report.

[1036] 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.

[1037] The present invention is a system that collects data from a data source, analyzes and extracts it, generates output in a specified format, and notifies a user, and further combines it with an emotion engine that recognizes the user's emotions. This system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, a notification means, and an emotion engine.

[1038] Overall system configuration

[1039] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. The emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system. Users issue instructions, check the results, and make adjustments as necessary.

[1040] System processing flow

[1041] Data collection

[1042] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report). The emotion engine simultaneously recognizes the user's emotions.

[1043] Server: Receives user instructions and information from the emotion engine and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[1044] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[1045] Server: Stores the collected data in a temporary data store.

[1046] Data analysis

[1047] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[1048] Server: Defines conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data, taking into account the user's emotional state.

[1049] Data Extraction

[1050] Server: Extracts the required data from the temporary data store based on the defined conditions, which are adjusted accordingly based on the analysis results of the emotion engine.

[1051] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs, tables).

[1052] Output generation and notification

[1053] Server: Converts the formatted data into the specified format (e.g. PDF, Excel, HTML report) and saves it.

[1054] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine (for example, a brief notification when stress is high).

[1055] User: Receives a notification, downloads the generated output, and reviews it. Feedback based on emotions is also recorded.

[1056] Specific examples

[1057] Scenario: Weekly report generation and emotion recognition

[1058] 1. User: Instructs the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired).

[1059] 2. Server: Accessed with appropriate credentials to collect data from project management tools and spreadsheets.

[1060] 3. Server: Stores the data in a temporary data store and analyzes its format and content.

[1061] 4. Server: Using the results of the emotion engine, set conditions to identify the required data items. For example, if the user is feeling stressed, prioritize summary data.

[1062] 5. Server: Extract data based on criteria and organize the information needed for weekly reports.

[1063] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[1064] 7. Server: Saves the completed report to cloud storage and sends a notification to the user reflecting the results of the emotion engine (e.g., a brief email notification with an encouraging message).

[1065] 8. User: Checks email, opens report, examines content, makes adjustments as needed, and provides emotional feedback to the system.

[1066] The system dynamically responds to the user's emotional state and aims to improve the user experience while streamlining the entire process from data collection to output generation.

[1067] The processing flow will be explained below.

[1068] Step 1:

[1069] User: Instructs the system to generate the required report (e.g., weekly report, monthly sales report). Through a dedicated interface, the user specifies the data source, output format, report conditions, etc. Furthermore, the emotion engine recognizes the user's emotions in real time.

[1070] Step 2:

[1071] Server: Receives user instructions and sentiment analysis results from the sentiment engine, and checks a list of target data sources, including databases, spreadsheets, cloud storage, etc.

[1072] Step 3:

[1073] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). After successful authentication at this stage, check the access permissions for each data source.

[1074] Step 4:

[1075] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[1076] Step 5:

[1077] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[1078] Step 6:

[1079] Server: Based on the content of the analyzed data, define the conditions for extracting the necessary data items (e.g., project progress information, sales amount). At this time, set conditions according to the user's emotions based on the analysis results of the emotion engine.

[1080] Step 7:

[1081] Server: Extracts the required data from the temporary data store based on the defined criteria. For example, it applies SQL queries and filtering logic to select the target data. This selection process is also adjusted based on the results of the emotion engine.

[1082] Step 8:

[1083] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[1084] Step 9:

[1085] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[1086] Step 10:

[1087] Server: Notifies the user of the generated output. At this time, the notification method and message content are optimized based on the results of the emotion engine. For example, if the user is feeling stressed, a concise and easy-to-understand notification is sent.

[1088] Step 11:

[1089] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[1090] Step 12:

[1091] User: Adjusts the output as needed and gives final approval, with the emotion engine recording the user's feedback for further analysis.

[1092] Through these steps, the system can adapt to the user's emotional state and efficiently process data from collection to output generation, saving the user time and effort and providing a better user experience.

[1093] Example 2

[1094] 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."

[1095] Conventional data collection and analysis systems were unable to take into account the user's emotional state, making it difficult to respond flexibly to the user's psychological conditions, such as stress and fatigue. Furthermore, they were limited to simple data collection and analysis and lacked functionality to improve the user experience. This resulted in a heavy burden on the user and reduced system usage efficiency.

[1096] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This makes it possible to analyze the user's emotions in real time and adjust the operation of the entire system based on the results.

[1097] A "data source" is the source from which data is collected, including databases, spreadsheets, cloud storage, etc.

[1098] "Collection" is the act of obtaining necessary information from a data source.

[1099] "Analysis" is the process of examining and interpreting collected data to understand its content and form.

[1100] "Extraction" is the act of extracting necessary information from analyzed data.

[1101] "Format" means a particular form or standard for storing or displaying data.

[1102] "Notification" is the act of communicating generated output to a user.

[1103] An "emotion engine" is a software or hardware function that analyzes a user's emotional state in real time and provides the results.

[1104] "Adjustment" is the act of dynamically changing the behavior and settings of the entire system based on the results of the emotion engine.

[1105] "Authentication information" refers to the information required to access a data source, including API keys and database connection strings.

[1106] "Filtering logic" refers to logical conditions or algorithms for selecting target data based on collected data.

[1107] "Output" means the final product of the analyzed, extracted, and transformed data, presented in the form of reports and / or graphs.

[1108] This invention is a system that collects, analyzes, and extracts data from data sources, generates output in a specified format, and notifies a user. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to respond flexibly while taking into account the user's psychological state. This system includes data collection means, data format analysis means, data extraction means, output conversion means, notification means, and an emotion engine.

[1109] Overall system configuration

[1110] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. Furthermore, the emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system.

[1111] Hardware and software used

[1112] Specifically, data collection involves software that accesses databases and cloud storage using API keys and database connection strings. Data analysis and transformation is performed using the Python pandas library, and output is generated using tools such as PDF generation tools (e.g., ReportLab) and Excel file creation tools (e.g., openpyxl). The emotion engine includes software for analyzing user emotions in real time. This emotion engine performs emotion analysis using machine learning models.

[1113] Specific examples

[1114] Take the example of weekly report generation and emotion recognition. A user requests the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired). The server collects data from project management tools or spreadsheets, accessing them with appropriate credentials. The collected data is stored in a temporary data store and analyzed for format and content. Based on the results of the emotion engine, conditions are set to identify the required data items. For example, if the user is feeling stressed, summary data is prioritized.

[1115] Based on these settings, data is extracted and the information required for the weekly report is organized. A weekly report in PDF format is generated based on the formatted data. The completed report is saved in cloud storage, and a notification reflecting the results of the emotion engine is sent to the user. For example, a brief email notification containing an encouraging message is sent.

[1116] Prompt Sentence Examples

[1117] Below are some example prompts to be input to the generative AI model of this system:

[1118] Follow the steps below to generate a weekly report. Also use the sentiment engine to analyze user sentiment and take the results into account in your data extraction and notifications.

[1119] 1. Collect weekly data from your project management tool.

[1120] 2. Analyze the data format to identify the required items.

[1121] 3. Set the conditions for data extraction taking into account the user's emotions.

[1122] 4. Generate weekly reports in PDF format.

[1123] 5. Save the report to cloud storage and notify the user.

[1124] This example and prompts provide a detailed understanding of the process by which the system takes the user's emotions into account when collecting data and generating output.

[1125] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1126] Step 1: User Instructions

[1127] User: The user instructs the system to generate a weekly report. As input, the user enters the command "generate a weekly report." The emotion engine recognizes the user's current emotion (e.g., stress or fatigue). This command is sent to the server.

[1128] Specific operation: A user accesses the system dashboard and clicks the report generation button. The emotion engine then collects and analyzes emotion data from the user's facial expressions and voice.

[1129] Step 2: Accessing the Data Source

[1130] Server: Takes as input the user's instructions and emotion engine's emotion data. The server checks the list of data sources and prepares access. It identifies the authentication information to use (API key, database connection string).

[1131] What happens: The server loads the list of database URLs and API keys and performs authentication for each data source.

[1132] Step 3: Collect and store data

[1133] Server: Accesses data sources using API keys and database connection strings to collect data. Authentication information for each data source and the data to be collected are given as input. The collected data is stored in a temporary data store.

[1134] What happens: The server connects to the database using an API, sends SQL queries or API requests to retrieve data, and stores that data in a temporary data store.

[1135] Step 4: Parsing the data format

[1136] Server: Analyzes the content and format of the temporarily stored data. As input, it receives the data stored in the temporary data store. It checks the file format (CSV, Excel, SQL database, etc.) and extracts the headers and metadata for the required information.

[1137] What happens: The server reads the header line of the data file, runs an algorithm to identify the file format, and analyzes the data content using the Python pandas library.

[1138] Step 5: Define data conditions

[1139] Server: Defines the conditions for extracting necessary data items from the analyzed data, taking into account the user's emotional state. The emotion engine's emotional data and the analyzed data are given as input. Specific conditions are set.

[1140] How it works: The server dynamically sets the conditions for data extraction queries based on information from the emotion engine. For example, if stress is high, summary data is prioritized.

[1141] Step 6: Extract the data

[1142] Server: Extracts the required data from the temporary data store based on the defined conditions. As input, the set conditions and the data stored in the temporary data store are given. As a result, the required data is retrieved.

[1143] Specific operation: Executes a data extraction query and retrieves target data from multiple tables by joining them.

[1144] Step 7: Data processing and organization

[1145] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs or tables). The extracted data is given as input. The result is formatted data.

[1146] How it works: The server aggregates the data and converts it into a data frame using the Python pandas library. Libraries such as matplotlib and seaborn are used to visualize the data.

[1147] Step 8: Generate output

[1148] Server: Converts and saves the formatted data in a specified format (e.g. PDF, Excel, HTML report). As input, the formatted data is given. As a result, the final output file is generated.

[1149] Specific operation: The server generates PDF or Excel files using a generative AI model library (e.g., ReportLab or openpyxl).

[1150] Step 9: Optimizing notifications

[1151] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine. The emotion engine data and the generated output are given as input. As a result, the appropriate notification method and message content are set.

[1152] What happens: The server uses an email notification API (e.g., SendGrid or SMTP) to send an optimized message to the user, such as a brief notification email with an encouraging message.

[1153] Step 10: Check the output

[1154] User: Upon receiving a notification, downloads the generated output and checks its contents. The notified output link is given as input. As a result, the user checks the output and provides feedback if necessary.

[1155] Specific operations: The user accesses the cloud storage, downloads the output file, checks its contents, and inputs and submits feedback through the system interface.

[1156] (Application example 2)

[1157] 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."

[1158] In modern virtual stores, product recommendations and customer support tailored to the customer's emotional state are important for improving customer satisfaction. However, conventional systems have difficulty recognizing customer emotions in real time and providing optimal services based on that information.

[1159] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, emotion recognition means for recognizing the user's emotions in real time, and means for adjusting the operation of the entire system based on the emotion information obtained by the emotion recognition means. This makes it possible to provide product recommendations and support according to the customer's emotional state.

[1160] "Data Source" means a source of data, such as a database, spreadsheet, or cloud storage.

[1161] A "data collection method" is a method that has the function of obtaining the necessary data from a data source, such as using an API call or a database query.

[1162] The "data format analysis means" is a means having a function for analyzing the structure and format of collected data, and recognizes file formats and extracts metadata.

[1163] "Data extraction means" refers to a means that has the function of extracting specific necessary information from the analyzed data, applying filtering logic and search conditions.

[1164] An "output conversion means" is a means that has the function of converting extracted data into a specified format and saving it, such as PDF, Excel, or HTML.

[1165] "Notification means" refers to a means that has the function of notifying the user of the generated output, such as email, app notification, or message delivery.

[1166] "Emotion recognition means" refers to a means that has the function of identifying a user's emotions in real time and acquiring that information, and utilizes a facial recognition camera and emotion analysis software.

[1167] The "means for adjusting the operation of the entire system" is a means for adjusting other functions and behaviors of the system based on the emotional information acquired by the emotional recognition means, and customizes the content of the service according to the emotional state.

[1168] This invention realizes a system that provides product recommendations and customer support in a virtual store according to the emotional state of the customer. The system operates using smart glasses or a head-mounted display worn by the user, analyzes the emotional state in real time through emotion recognition means, and adjusts the operation of the entire system based on that information.

[1169] Hardware and Software Configuration

[1170] Hardware:

[1171] Cameras (built into smart glasses or head-mounted displays)

[1172] Server (performs data processing and sentiment analysis)

[1173] User's device (smartphone, tablet, etc.)

[1174] software:

[1175] OpenCV (a library that provides face recognition functionality)

[1176] EmotionRecognitionModule (software for emotion analysis)

[1177] DataSourceModule (data collection and filtering software)

[1178] OutputFormatModule (software that converts data output formats)

[1179] Program processing

[1180] The server first acquires video data using the camera installed on the user's device and performs real-time emotion analysis using emotion recognition means. Based on the analysis results, it collects, analyzes, and extracts appropriate data. Next, it converts the extracted data into a specified format (e.g., a product recommendation list) and notifies the user of the results. The notification content is customized based on the user's emotional state.

[1181] Specific examples

[1182] For example, when a user enters a virtual store, the camera installed in the smart glasses captures the user's face, and if the emotion recognition means determines that the user is smiling (happy), the server will prioritize displaying a list of new products. Conversely, if the user is feeling stressed, the server will display a list of products with a relaxing effect (aroma candles, relaxation gadgets, etc.).

[1183] Usage example

[1184] Example prompt sentence:

[1185] When a user wears smart glasses and enters a virtual store, please capture their face with a camera and perform real-time emotion analysis. If the emotion is "smile", please suggest a new product list. If the emotion is "stress", please suggest a product list with a relaxing effect.

[1186] By using this system, high-quality customer support can be provided in a virtual store according to the customer's emotional state, resulting in improved customer satisfaction.

[1187] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1188] Step 1:

[1189] A user puts on smart glasses and enters a virtual store. The device's camera captures the user's face. The captured video data is sent to the server in real time. The input is the user's face video data, and the output is the video data sent to the server.

[1190] Step 2:

[1191] The server receives the video data and uses OpenCV to recognize the user's face. It then uses the EmotionRecognitionModule to analyze the user's emotions. The input is video data, and face recognition and emotion analysis are performed as data processing. The output is the user's emotional information (e.g., smiling, stress, etc.).

[1192] Step 3:

[1193] The server determines the next data processing instructions based on the obtained emotional information. Specifically, it sets conditions such as prioritizing a list of new products if the person is smiling, or a list of products with a relaxing effect if the person is under stress. The input is emotional information, and the output is the data processing instructions.

[1194] Step 4:

[1195] The server uses the DataSourceModule to collect the required data from the appropriate data source based on the configured instructions. Examples include collecting data from a product database or cloud storage. The input is the data processing instructions, and the data is collected as data processing. The output is the collected product data.

[1196] Step 5:

[1197] The server analyzes the format of the collected data. Using data format analysis means, it analyzes and extracts the data structure and necessary information. The input is the collected product data, and format analysis is performed as data calculation. The output is the analyzed data.

[1198] Step 6:

[1199] The server extracts necessary data from the analyzed data. Using the data extraction method, it filters appropriate product information based on the emotion information. The input is the analyzed data, and filtering logic is applied as data processing. The output is the extracted product information.

[1200] Step 7:

[1201] The server converts the extracted data into the specified format and saves it using OutputFormatModule. For example, converting a recommended product list into PDF or HTML format. The input is the extracted product information, and format conversion is performed as data processing. The output is the formatted output.

[1202] Step 8:

[1203] The server notifies the user of the generated output. Based on the results of the emotion recognition means, the notification method and message content are optimized. For example, if stress is high, a simple notification is sent. The input is the formatted output, and the output is the notification to the user.

[1204] Step 9:

[1205] The user receives a notification and checks the provided product list. If necessary, the user can provide feedback to the system using prompt sentences. The input feedback from the user helps improve the system.

[1206] In this way, the present invention realizes a system that can provide optimal product recommendations and support in a virtual store according to the emotional state of the customer.

[1207] 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.

[1208] 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.

[1209] 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.

[1210] [Fourth embodiment]

[1211] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1212] 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.

[1213] 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).

[1214] 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.

[1215] 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.

[1216] 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).

[1217] 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.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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."

[1224] The present invention relates to a system for collecting, analyzing, and extracting data from data sources, generating output in a specified format, and notifying a user. The system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, and a notification means.

[1225] Overall system configuration

[1226] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. Users issue instructions, check the results, and make adjustments as necessary.

[1227] System processing flow

[1228] Data collection

[1229] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report).

[1230] Server: Receives user instructions and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[1231] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[1232] Server: Stores the collected data in a temporary data store.

[1233] Data analysis

[1234] Server: Analyzes the content and format of the stored data, for example, checking the file format (CSV, Excel, SQL database, etc.) and parsing header information and metadata.

[1235] Server: Define the conditions for extracting the required data items (project progress information, sales amount, etc.).

[1236] Data Extraction

[1237] Server: Extracts the required data from the temporary data store based on the defined criteria, for example, using SQL queries and filtering logic to select the target data.

[1238] Server: Organizes the extracted data and converts it into a format suitable for the final output (graphs, tables, etc.).

[1239] Output generation and notification

[1240] Server: Converts the formatted data into the specified format (PDF, Excel, HTML report, etc.) and saves it.

[1241] Server: Notifies the user of the generated output. For example, it saves it in cloud storage and sends the link to the user via email or chat tool.

[1242] User: Upon receiving notification, downloads the generated output, reviews it, makes any necessary adjustments, and finally approves it.

[1243] Specific examples

[1244] Scenario: Generating a weekly report

[1245] 1. User: Instructs the generation of a weekly report.

[1246] 2. Server: Accessed with the necessary API keys to collect data from project management tools (e.g., online project management systems) and spreadsheets.

[1247] 3. Server: Retrieves project progress data from each data source and stores it in a temporary data store.

[1248] 4. Server: Analyzes the format of the collected data and identifies task status information.

[1249] 5. Server: Extracts data based on defined criteria and organizes the information required for weekly reports.

[1250] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[1251] 7. Server: Saves the completed report to cloud storage and emails the user a link to the report.

[1252] 8. User: Checks email, opens report and examines contents.

[1253] 9. User: Make any necessary adjustments and give final approval.

[1254] This invention automates the entire process of data collection, analysis, extraction, and output, saving users time and effort, and is expected to improve work efficiency.

[1255] The processing flow will be explained below.

[1256] Step 1:

[1257] User: Instructs the generation of the required report (e.g., weekly report, monthly sales report). The user specifies the data source, output format, report conditions, etc. through a dedicated interface.

[1258] Step 2:

[1259] Server: Receives user instructions and checks the list of target data sources, which can include databases, spreadsheets, cloud storage, etc.

[1260] Step 3:

[1261] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). At this stage, after successful authentication, access permissions are verified.

[1262] Step 4:

[1263] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[1264] Step 5:

[1265] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[1266] Step 6:

[1267] Server: Define the conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data. For example, use keyword search or regular expressions to identify the necessary information.

[1268] Step 7:

[1269] Server: Extracts the required data from the temporary data store based on the defined criteria, and applies SQL queries and filtering logic to select the target data.

[1270] Step 8:

[1271] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[1272] Step 9:

[1273] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[1274] Step 10:

[1275] Server: Notifies the user of the generated output. Notification methods include saving it to cloud storage, sending a link to it via email, or sharing it via a chat tool.

[1276] Step 11:

[1277] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[1278] Step 12:

[1279] User: Revises output as needed and gives final approval. Revises output using a PDF reader or spreadsheet software.

[1280] Through the above steps, the system can respond to user requests, smoothly collect, analyze, and extract data from different formats and locations, and generate and provide output.

[1281] Example 1

[1282] 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."

[1283] In conventional systems, the processes of data collection, analysis, extraction, format conversion, and notification were often manual or only partially automated, resulting in a lack of overall efficiency. This meant that users had to spend time and effort processing large amounts of data and generating reports, making it difficult to improve work efficiency. In addition, differences in authentication methods and data formats corresponding to different data sources made data integration and analysis technically complex.

[1284] 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.

[1285] In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This enables efficient collection and analysis of data. The server also includes means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, means for receiving and analyzing a prompt sentence in natural language, and means for securely accessing the data source using authentication information. This automates a series of data processing tasks performed by the user, enabling efficient and rapid generation of desired reports.

[1286] A "data source" is a location or system where the raw data from which a system obtains information is stored.

[1287] "Means of collection" refers to the methods and devices used to obtain the required data from the data source.

[1288] "Means of analysis" refers to the methods and algorithms used to understand the format and content of the collected data and find the necessary information.

[1289] "Extraction means" refers to methods or tools for extracting data that meets specific conditions from the analyzed data.

[1290] "Means of converting and saving into a specified format" refers to the method or procedure for converting extracted data into a specified format (PDF, Excel, etc.) and saving it.

[1291] "Means of notification" refers to the methods and techniques used to notify users of the generated output.

[1292] "Means for receiving and analyzing natural language prompts" refers to methods or techniques for receiving instructions in natural language from a user, analyzing them, and performing appropriate processing.

[1293] "Authentication information" refers to information (such as an API key or password) required to securely access a data source.

[1294] A "means for securely accessing a data source" refers to a method or algorithm for securely connecting to a data source using authentication information.

[1295] A "temporary data store" is a database or storage for temporarily storing collected data.

[1296] "Filtering logic" refers to algorithms or methods for filtering data based on specific conditions.

[1297] The present invention is a system that collects data from data sources, analyzes and extracts it, generates output in a specified format, and notifies users. This system consists of a server, a terminal, and a user.

[1298] Overall system configuration

[1299] This system functions through the collaboration of a server, terminals, and users. The server is the center of data processing, collecting data in response to instructions from users, analyzing, converting, and notifying them. The terminals are the interfaces that transmit user instructions to the server. Users issue instructions to the system, check the generated output, and make adjustments as necessary.

[1300] Hardware and Software Configuration

[1301] Server: Performs data collection, parsing, extraction, transformation, and notification functions. This server manages credentials to access various databases and APIs, securely exchanges data using communication protocols, and executes SQL queries and filtering logic for data analysis.

[1302] Terminal: The user inputs instructions and the results are displayed. The required hardware is a PC or tablet. It also uses an application or web browser that provides an interface such as a GUI (Graphical User Interface).

[1303] User: Enter specific prompts into the system and view the generated output. For example, enter natural language prompts such as "Generate this week's progress report" or "Generate this month's sales report."

[1304] Specific examples of processing

[1305] Generate weekly reports

[1306] 1. User: Instructs the generation of a weekly report. For example, the user enters the prompt "Please generate this week's progress report" into the terminal.

[1307] 2. Terminal: Sends this instruction to the server.

[1308] 3. Server: To collect data from project management tools (e.g., online project management systems) and spreadsheets, you connect securely using credentials, specifically, API keys to access data sources.

[1309] 4. Server: Retrieves project progress data from each data source and stores this data in a temporary data store.

[1310] 5. Server: Analyzes the format of the stored data and identifies the required data items (e.g., task status information).

[1311] 6. Server: Extracts the required data from the temporary data store based on defined criteria, for example, running an SQL query to extract only data from a specific time period.

[1312] 7. Server: Format the extracted data and generate a PDF report. Add graphs and charts using tools like ReportLab.

[1313] 8. Server: Saves the completed report to cloud storage and generates a link to it.

[1314] 9. Server: Sends the link to the user via email or chat tool.

[1315] 10. User: Checks email, opens report, checks contents, makes necessary adjustments and sends command to server again.

[1316] This invention is a system that uses a generative AI model to analyze prompts, automatically collect, analyze, and extract data, and generate targeted reports to notify users, thereby significantly reducing the user's workload and improving work efficiency.

[1317] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1318] Step 1:

[1319] The user uses a terminal to enter a prompt that instructs the system to generate a specific report, for example, "Please generate this week's progress report." This prompt is then sent from the terminal to the server.

[1320] Input: The prompt text entered by the user

[1321] Output: The prompt sent to the server

[1322] Specific behavior: The user enters a prompt sentence into the input form and clicks the submit button.

[1323] Step 2:

[1324] The server receives and parses the prompt, using a generative AI model to understand the content of the prompt and identify the required action.

[1325] Input: The prompt sent to the server

[1326] Output: Analysis results (type of report to generate and required data source)

[1327] What it does: It uses a natural language processing library (e.g., NLTK or Spacy) to parse the prompt and identify the type of report to generate (e.g., weekly status report) and the data source (e.g., project management tool).

[1328] Step 3:

[1329] Connect to the data source using the credentials (such as an API key or database connection string) to access the data source identified by the server.

[1330] Input: Analysis results (required data source and credentials)

[1331] Output: Connection to a data source

[1332] Specific operation: Connect to a database server using a database connection string, or access a Web API using an API key.

[1333] Step 4:

[1334] The server retrieves the required data from the data source and stores it in a temporary data store for further processing.

[1335] Input: Data source (database, spreadsheet, etc.)

[1336] Output: Data saved to a temporary data store

[1337] What it does: For example, execute a SQL query to retrieve project progress data from a database and store it in a temporary data store (for example, Redis or a temporary file).

[1338] Step 5:

[1339] The server analyzes the content and format of the data stored in the temporary data store. For example, in the case of a CSV file, it reads the header information and determines the data type of each column.

[1340] Input: Data stored in a temporary data store

[1341] Output: Analysis results (data format and content)

[1342] Specific operation: Uses Python's pandas library to read a CSV file and parse it into a data frame.

[1343] Step 6:

[1344] The server defines the conditions for identifying the required data items based on the analysis results. The conditions are expressed as SQL queries and filtering logic.

[1345] Input: Analysis results (data format and content)

[1346] Output: Condition definition (SQL query or filtering logic)

[1347] Specific behavior: Generates a query like "SELECT task_name, progress FROM project_data WHERE date BETWEEN '2023-01-01' AND '2023-01-07'".

[1348] Step 7:

[1349] The server extracts the required data from the temporary data store based on defined criteria, for example, by running an SQL query to extract only data from a specific time period.

[1350] Input: Condition definition (SQL query or filtering logic)

[1351] Output: Extracted data

[1352] Specific behavior: Executes an SQL query to retrieve data that matches the specified criteria.

[1353] Step 8:

[1354] The server formats the extracted data and converts it to a suitable format for final output (PDF, Excel, etc.). For example, to generate a PDF report, use the ReportLab library.

[1355] Input: Extracted data

[1356] Output: Formatted data (output file)

[1357] What it does: Use ReportLab to add graphs and charts to PDF documents.

[1358] Step 9:

[1359] The server saves the generated output file in cloud storage and generates a link to it.

[1360] Input: Formatted data (output file)

[1361] Output: Cloud storage link

[1362] What it does: Uploads a file using the cloud storage API and gets its link.

[1363] Step 10:

[1364] The server will notify the user of the cloud storage link via email or chat tool.

[1365] Input: Cloud storage link

[1366] Output: Notification to user (email or chat)

[1367] Specific operation: Send a link to the user using an email sending service or chat API (e.g., Slack API).

[1368] Step 11:

[1369] The user receives a notification, clicks a link to download the output file (e.g., a PDF report), and reviews the contents.

[1370] Input: User notification

[1371] Output: The downloaded output file

[1372] What happens: User clicks on a link, downloads a file, and reviews its contents.

[1373] Step 12:

[1374] The user checks the content for any problems and instructs the server to provide feedback or make revisions as necessary.

[1375] Input: User feedback and rework instructions

[1376] Output: Redirect to server

[1377] Specific operation: Based on the review results, the user re-enters the necessary corrections as a prompt sentence and sends it to the server.

[1378] (Application example 1)

[1379] 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."

[1380] Modern logistics centers require a series of processes, including data collection, analysis, extraction, and output generation from a wide variety of data sources. However, doing all of this manually is extremely time-consuming and labor-intensive, resulting in errors and delays. It is also difficult to optimize inventory information and delivery routes in real time, reducing the efficiency of management operations. To solve these issues, a system is needed that automatically collects and analyzes data, and efficiently manages inventory and optimizes delivery routes.

[1381] 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.

[1382] In this invention, the server includes means for collecting data from data sources, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying a user of the generated output, means for analyzing logistics management information and calculating an optimal delivery route, and means for monitoring inventory information in real time and notifying necessary warnings, thereby enabling automated data management, efficient inventory management, and calculation of an optimal delivery route within a logistics center.

[1383] "Data Sources" are various information sources that serve as starting points for collecting data.

[1384] "Means for collecting data" refers to a function for obtaining necessary information from a specified data source.

[1385] "Means for analyzing data format" refers to the function of identifying the structure and type of collected data and processing it in an appropriate format.

[1386] "Means for extracting necessary data" refers to the function of extracting important information from the analyzed data based on specific conditions.

[1387] The "means for converting and saving into a specified format" is a function for converting extracted data into a specified format and saving it so that it can be referenced later.

[1388] "Means for notifying the user of the generated output" is a function that notifies the user of the final generated report or information.

[1389] "Means for analyzing logistics management information and calculating optimal delivery routes" is a function that uses data collected within the logistics center to derive efficient delivery routes.

[1390] "Means of monitoring inventory information in real time and notifying necessary warnings" refers to a function that constantly monitors the inventory status in the warehouse and immediately issues an alert if an abnormality occurs.

[1391] This invention is a system for automating and streamlining inventory management and delivery route optimization in logistics centers. This system combines various methods for data collection, analysis, extraction, output generation, and notification.

[1392] Hardware and software used

[1393] Hardware:

[1394] Smartphone (iOS / Android)

[1395] Logistics robots

[1396] IoT sensors (for inventory management)

[1397] GPS device (for shipping tracking)

[1398] software:

[1399] Database (PostgreSQL, MySQL)

[1400] Cloud storage (AWS S3, Google Drive)

[1401] API services (Google Maps API, Twilio for notifications)

[1402] AI / ML models (TensorFlow, PyTorch)

[1403] The server uses this hardware and software to perform the following processes.

[1404] Data collection

[1405] The server collects data from inventory sensors and GPS devices as data sources, thereby obtaining real-time inventory information and delivery route information within the distribution center. For example, sensors detect the current inventory status and input that information into a database.

[1406] Data analysis

[1407] The server analyzes the format of the collected data and extracts the necessary data, such as detailed information about a specific product from inventory data or analyzing GPS data to confirm the current delivery route and time.

[1408] Data extraction and output generation

[1409] The server converts the extracted data into a specified format and generates output, such as generating an inventory report in PDF format or calculating the optimal delivery route and saving it as an HTML report.

[1410] notification

[1411] The generated output is stored in cloud storage and the user is notified via email or chat using API services such as Twilio.

[1412] Specific examples

[1413] For example, if you want to generate a report on products that have significantly decreased in stock this week, the system collects data from sensors in real time, analyzes that data, extracts product information that falls within a specified decrease rate, compiles it into a report, and notifies the user.

[1414] Prompt Sentence Examples

[1415] "Please create a report on products that have significantly decreased based on this week's inventory status. For example, generate a PDF report containing a list of products whose inventory has decreased by 20% or more and the rate of decrease, and send it to the specified email address."

[1416] Such a system will make logistics center management more efficient and enable optimization of inventory and delivery routes.

[1417] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1418] Step 1:

[1419] Data collection

[1420] The server collects data from data sources such as inventory sensors and GPS devices. Specifically, it calls the sensor API and GPS API to obtain real-time data. The input is the API key and authentication information, and the output is stored in the database as inventory counts and delivery route information.

[1421] Step 2:

[1422] Data analysis

[1423] The server analyzes the format of the collected data. Specifically, it analyzes data formats such as CSV and JSON to check the field names and data types. The input is raw data from the database, and the output is structural information about the analyzed data. This process determines which data can be used and how.

[1424] Step 3:

[1425] Data Extraction

[1426] The server extracts the necessary information from the parsed data. Specifically, it executes SQL queries to extract data about specific products and delivery routes. The input is the parsed data, and the output is the extracted target data. This process identifies the necessary information and makes it available for the next step.

[1427] Step 4:

[1428] Output Generation

[1429] The server converts the extracted data into a specified format and generates the output. Specifically, it inserts the data into a report template and generates a report in PDF or HTML format. The input is the extracted data, and the output is the generated output file. This step creates a report in a format that is intuitive for the user.

[1430] Step 5:

[1431] notification

[1432] The server notifies the user of the generated output. Specifically, it sends a notification using Twilio or email API. The input is the generated output file and destination information, and the output is a notification to the user. This allows the user to immediately check the new report.

[1433] 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.

[1434] The present invention is a system that collects data from a data source, analyzes and extracts it, generates output in a specified format, and notifies a user, and further combines it with an emotion engine that recognizes the user's emotions. This system includes a data collection means, a data format analysis means, a data extraction means, an output conversion means, a notification means, and an emotion engine.

[1435] Overall system configuration

[1436] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. The emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system. Users issue instructions, check the results, and make adjustments as necessary.

[1437] System processing flow

[1438] Data collection

[1439] User: First, the user instructs the system to generate the required report (e.g., weekly report, monthly sales report). The emotion engine simultaneously recognizes the user's emotions.

[1440] Server: Receives user instructions and information from the emotion engine and checks a list of target data sources (e.g., databases, spreadsheets, cloud storage).

[1441] Server: Accesses each data source using the appropriate credentials (e.g., API key or database connection string) and collects the required data.

[1442] Server: Stores the collected data in a temporary data store.

[1443] Data analysis

[1444] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[1445] Server: Defines conditions for extracting necessary data items (e.g., project progress information, sales amount) from the analyzed data, taking into account the user's emotional state.

[1446] Data Extraction

[1447] Server: Extracts the required data from the temporary data store based on the defined conditions, which are adjusted accordingly based on the analysis results of the emotion engine.

[1448] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs, tables).

[1449] Output generation and notification

[1450] Server: Converts the formatted data into the specified format (e.g. PDF, Excel, HTML report) and saves it.

[1451] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine (for example, a brief notification when stress is high).

[1452] User: Receives a notification, downloads the generated output, and reviews it. Feedback based on emotions is also recorded.

[1453] Specific examples

[1454] Scenario: Weekly report generation and emotion recognition

[1455] 1. User: Instructs the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired).

[1456] 2. Server: Accessed with appropriate credentials to collect data from project management tools and spreadsheets.

[1457] 3. Server: Stores the data in a temporary data store and analyzes its format and content.

[1458] 4. Server: Using the results of the emotion engine, set conditions to identify the required data items. For example, if the user is feeling stressed, prioritize summary data.

[1459] 5. Server: Extract data based on criteria and organize the information needed for weekly reports.

[1460] 6. Server: Generates a weekly report in PDF format based on the formatted data.

[1461] 7. Server: Saves the completed report to cloud storage and sends a notification to the user reflecting the results of the emotion engine (e.g., a brief email notification with an encouraging message).

[1462] 8. User: Checks email, opens report, examines content, makes adjustments as needed, and provides emotional feedback to the system.

[1463] The system dynamically responds to the user's emotional state and aims to improve the user experience while streamlining the entire process from data collection to output generation.

[1464] The processing flow will be explained below.

[1465] Step 1:

[1466] User: Instructs the system to generate the required report (e.g., weekly report, monthly sales report). Through a dedicated interface, the user specifies the data source, output format, report conditions, etc. Furthermore, the emotion engine recognizes the user's emotions in real time.

[1467] Step 2:

[1468] Server: Receives user instructions and sentiment analysis results from the sentiment engine, and checks a list of target data sources, including databases, spreadsheets, cloud storage, etc.

[1469] Step 3:

[1470] Server: Access each data source using the appropriate authentication information (API key, database connection string, etc.). After successful authentication at this stage, check the access permissions for each data source.

[1471] Step 4:

[1472] Server: Collects the required data from each data source and stores it in a temporary data store, for example by executing SQL queries or calling APIs to retrieve the data.

[1473] Step 5:

[1474] Server: Analyzes the content and format of the stored data. Checks the file format (CSV, Excel, SQL database, etc.) and extracts headers and metadata for the required information.

[1475] Step 6:

[1476] Server: Based on the content of the analyzed data, define the conditions for extracting the necessary data items (e.g., project progress information, sales amount). At this time, set conditions according to the user's emotions based on the analysis results of the emotion engine.

[1477] Step 7:

[1478] Server: Extracts the required data from the temporary data store based on the defined criteria. For example, it applies SQL queries and filtering logic to select the target data. This selection process is also adjusted based on the results of the emotion engine.

[1479] Step 8:

[1480] Server: Organizes the extracted data and processes it to convert it into a format suitable for final output (e.g., graphs, tables), specifically by aggregating the data and formatting field names.

[1481] Step 9:

[1482] Server: Convert the formatted data into the specified format (e.g. PDF, Excel, HTML report) and save it. Here, you can use a PDF generation library or an Excel generation library.

[1483] Step 10:

[1484] Server: Notifies the user of the generated output. At this time, the notification method and message content are optimized based on the results of the emotion engine. For example, if the user is feeling stressed, a concise and easy-to-understand notification is sent.

[1485] Step 11:

[1486] User: The user who receives the notification can check the generated output from the specified location, download the file, and check the contents.

[1487] Step 12:

[1488] User: Adjusts the output as needed and gives final approval, with the emotion engine recording the user's feedback for further analysis.

[1489] Through these steps, the system can adapt to the user's emotional state and efficiently process data from collection to output generation, saving the user time and effort and providing a better user experience.

[1490] Example 2

[1491] 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."

[1492] Conventional data collection and analysis systems were unable to take into account the user's emotional state, making it difficult to respond flexibly to the user's psychological conditions, such as stress and fatigue. Furthermore, they were limited to simple data collection and analysis and lacked functionality to improve the user experience. This resulted in a heavy burden on the user and reduced system usage efficiency.

[1493] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, and means for extracting necessary data from the analyzed data. This makes it possible to analyze the user's emotions in real time and adjust the operation of the entire system based on the results.

[1494] A "data source" is the source from which data is collected, including databases, spreadsheets, cloud storage, etc.

[1495] "Collection" is the act of obtaining necessary information from a data source.

[1496] "Analysis" is the process of examining and interpreting collected data to understand its content and form.

[1497] "Extraction" is the act of extracting necessary information from analyzed data.

[1498] "Format" means a particular form or standard for storing or displaying data.

[1499] "Notification" is the act of communicating generated output to a user.

[1500] An "emotion engine" is a software or hardware function that analyzes a user's emotional state in real time and provides the results.

[1501] "Adjustment" is the act of dynamically changing the behavior and settings of the entire system based on the results of the emotion engine.

[1502] "Authentication information" refers to the information required to access a data source, including API keys and database connection strings.

[1503] "Filtering logic" refers to logical conditions or algorithms for selecting target data based on collected data.

[1504] "Output" means the final product of the analyzed, extracted, and transformed data, presented in the form of reports and / or graphs.

[1505] This invention is a system that collects, analyzes, and extracts data from data sources, generates output in a specified format, and notifies a user. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, it is possible to respond flexibly while taking into account the user's psychological state. This system includes data collection means, data format analysis means, data extraction means, output conversion means, notification means, and an emotion engine.

[1506] Overall system configuration

[1507] The system functions through collaboration between the server, devices, and users. The server is the center of data processing and emotion analysis, collecting data in response to user instructions, analyzing it, converting it, and sending notifications. Furthermore, the emotion engine analyzes user emotions in real time and uses the results to adjust the behavior of the entire system.

[1508] Hardware and software used

[1509] Specifically, data collection involves software that accesses databases and cloud storage using API keys and database connection strings. Data analysis and transformation is performed using the Python pandas library, and output is generated using tools such as PDF generation tools (e.g., ReportLab) and Excel file creation tools (e.g., openpyxl). The emotion engine includes software for analyzing user emotions in real time. This emotion engine performs emotion analysis using machine learning models.

[1510] Specific examples

[1511] Take the example of weekly report generation and emotion recognition. A user requests the generation of a weekly report. The emotion engine recognizes the user's current emotion (e.g., stressed or tired). The server collects data from project management tools or spreadsheets, accessing them with appropriate credentials. The collected data is stored in a temporary data store and analyzed for format and content. Based on the results of the emotion engine, conditions are set to identify the required data items. For example, if the user is feeling stressed, summary data is prioritized.

[1512] Based on these settings, data is extracted and the information required for the weekly report is organized. A weekly report in PDF format is generated based on the formatted data. The completed report is saved in cloud storage, and a notification reflecting the results of the emotion engine is sent to the user. For example, a brief email notification containing an encouraging message is sent.

[1513] Prompt Sentence Examples

[1514] Below are some example prompts to be input to the generative AI model of this system:

[1515] Follow the steps below to generate a weekly report. Also use the sentiment engine to analyze user sentiment and take the results into account in your data extraction and notifications.

[1516] 1. Collect weekly data from your project management tool.

[1517] 2. Analyze the data format to identify the required items.

[1518] 3. Set the conditions for data extraction taking into account the user's emotions.

[1519] 4. Generate weekly reports in PDF format.

[1520] 5. Save the report to cloud storage and notify the user.

[1521] This example and prompts provide a detailed understanding of the process by which the system takes the user's emotions into account when collecting data and generating output.

[1522] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1523] Step 1: User Instructions

[1524] User: The user instructs the system to generate a weekly report. As input, the user enters the command "generate a weekly report." The emotion engine recognizes the user's current emotion (e.g., stress or fatigue). This command is sent to the server.

[1525] Specific operation: A user accesses the system dashboard and clicks the report generation button. The emotion engine then collects and analyzes emotion data from the user's facial expressions and voice.

[1526] Step 2: Accessing the Data Source

[1527] Server: Takes as input the user's instructions and emotion engine's emotion data. The server checks the list of data sources and prepares access. It identifies the authentication information to use (API key, database connection string).

[1528] What happens: The server loads the list of database URLs and API keys and performs authentication for each data source.

[1529] Step 3: Collect and store data

[1530] Server: Accesses data sources using API keys and database connection strings to collect data. Authentication information for each data source and the data to be collected are given as input. The collected data is stored in a temporary data store.

[1531] What happens: The server connects to the database using an API, sends SQL queries or API requests to retrieve data, and stores that data in a temporary data store.

[1532] Step 4: Parsing the data format

[1533] Server: Analyzes the content and format of the temporarily stored data. As input, it receives the data stored in the temporary data store. It checks the file format (CSV, Excel, SQL database, etc.) and extracts the headers and metadata for the required information.

[1534] What happens: The server reads the header line of the data file, runs an algorithm to identify the file format, and analyzes the data content using the Python pandas library.

[1535] Step 5: Define data conditions

[1536] Server: Defines the conditions for extracting necessary data items from the analyzed data, taking into account the user's emotional state. The emotion engine's emotional data and the analyzed data are given as input. Specific conditions are set.

[1537] How it works: The server dynamically sets the conditions for data extraction queries based on information from the emotion engine. For example, if stress is high, summary data is prioritized.

[1538] Step 6: Extract the data

[1539] Server: Extracts the required data from the temporary data store based on the defined conditions. As input, the set conditions and the data stored in the temporary data store are given. As a result, the required data is retrieved.

[1540] Specific operation: Executes a data extraction query and retrieves target data from multiple tables by joining them.

[1541] Step 7: Data processing and organization

[1542] Server: Organizes the extracted data and processes it to convert it into a format suitable for the final output (e.g., graphs or tables). The extracted data is given as input. The result is formatted data.

[1543] How it works: The server aggregates the data and converts it into a data frame using the Python pandas library. Libraries such as matplotlib and seaborn are used to visualize the data.

[1544] Step 8: Generate output

[1545] Server: Converts and saves the formatted data in a specified format (e.g. PDF, Excel, HTML report). As input, the formatted data is given. As a result, the final output file is generated.

[1546] Specific operation: The server generates PDF or Excel files using a generative AI model library (e.g., ReportLab or openpyxl).

[1547] Step 9: Optimizing notifications

[1548] Server: When notifying the user of the generated output, the notification method and message content are optimized based on the results of the emotion engine. The emotion engine data and the generated output are given as input. As a result, the appropriate notification method and message content are set.

[1549] What happens: The server uses an email notification API (e.g., SendGrid or SMTP) to send an optimized message to the user, such as a brief notification email with an encouraging message.

[1550] Step 10: Check the output

[1551] User: Upon receiving a notification, downloads the generated output and checks its contents. The notified output link is given as input. As a result, the user checks the output and provides feedback if necessary.

[1552] Specific operations: The user accesses the cloud storage, downloads the output file, checks its contents, and inputs and submits feedback through the system interface.

[1553] (Application example 2)

[1554] 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."

[1555] In modern virtual stores, product recommendations and customer support tailored to the customer's emotional state are important for improving customer satisfaction. However, conventional systems have difficulty recognizing customer emotions in real time and providing optimal services based on that information.

[1556] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting data from a data source, means for analyzing the format of the collected data, means for extracting necessary data from the analyzed data, means for converting the extracted data into a specified format and saving it, means for notifying the user of the generated output, emotion recognition means for recognizing the user's emotions in real time, and means for adjusting the operation of the entire system based on the emotion information obtained by the emotion recognition means. This makes it possible to provide product recommendations and support according to the customer's emotional state.

[1557] "Data Source" means a source of data, such as a database, spreadsheet, or cloud storage.

[1558] A "data collection method" is a method that has the function of obtaining the necessary data from a data source, such as using an API call or a database query.

[1559] The "data format analysis means" is a means having a function for analyzing the structure and format of collected data, and recognizes file formats and extracts metadata.

[1560] "Data extraction means" refers to a means that has the function of extracting specific necessary information from the analyzed data, applying filtering logic and search conditions.

[1561] An "output conversion means" is a means that has the function of converting extracted data into a specified format and saving it, such as PDF, Excel, or HTML.

[1562] "Notification means" refers to a means that has the function of notifying the user of the generated output, such as email, app notification, or message delivery.

[1563] "Emotion recognition means" refers to a means that has the function of identifying a user's emotions in real time and acquiring that information, and utilizes a facial recognition camera and emotion analysis software.

[1564] The "means for adjusting the operation of the entire system" is a means for adjusting other functions and behaviors of the system based on the emotional information acquired by the emotional recognition means, and customizes the content of the service according to the emotional state.

[1565] This invention realizes a system that provides product recommendations and customer support in a virtual store according to the emotional state of the customer. The system operates using smart glasses or a head-mounted display worn by the user, analyzes the emotional state in real time through emotion recognition means, and adjusts the operation of the entire system based on that information.

[1566] Hardware and Software Configuration

[1567] Hardware:

[1568] Cameras (built into smart glasses or head-mounted displays)

[1569] Server (performs data processing and sentiment analysis)

[1570] User's device (smartphone, tablet, etc.)

[1571] software:

[1572] OpenCV (a library that provides face recognition functionality)

[1573] EmotionRecognitionModule (software for emotion analysis)

[1574] DataSourceModule (data collection and filtering software)

[1575] OutputFormatModule (software that converts data output formats)

[1576] Program processing

[1577] The server first acquires video data using the camera installed on the user's device and performs real-time emotion analysis using emotion recognition means. Based on the analysis results, it collects, analyzes, and extracts appropriate data. Next, it converts the extracted data into a specified format (e.g., a product recommendation list) and notifies the user of the results. The notification content is customized based on the user's emotional state.

[1578] Specific examples

[1579] For example, when a user enters a virtual store, the camera installed in the smart glasses captures the user's face, and if the emotion recognition means determines that the user is smiling (happy), the server will prioritize displaying a list of new products. Conversely, if the user is feeling stressed, the server will display a list of products with a relaxing effect (aroma candles, relaxation gadgets, etc.).

[1580] Usage example

[1581] Example prompt sentence:

[1582] When a user wears smart glasses and enters a virtual store, please capture their face with a camera and perform real-time emotion analysis. If the emotion is "smile", please suggest a new product list. If the emotion is "stress", please suggest a product list with a relaxing effect.

[1583] By using this system, high-quality customer support can be provided in a virtual store according to the customer's emotional state, resulting in improved customer satisfaction.

[1584] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1585] Step 1:

[1586] A user puts on smart glasses and enters a virtual store. The device's camera captures the user's face. The captured video data is sent to the server in real time. The input is the user's face video data, and the output is the video data sent to the server.

[1587] Step 2:

[1588] The server receives the video data and uses OpenCV to recognize the user's face. It then uses the EmotionRecognitionModule to analyze the user's emotions. The input is video data, and face recognition and emotion analysis are performed as data processing. The output is the user's emotional information (e.g., smiling, stress, etc.).

[1589] Step 3:

[1590] The server determines the next data processing instructions based on the obtained emotional information. Specifically, it sets conditions such as prioritizing a list of new products if the person is smiling, or a list of products with a relaxing effect if the person is under stress. The input is emotional information, and the output is the data processing instructions.

[1591] Step 4:

[1592] The server uses the DataSourceModule to collect the required data from the appropriate data source based on the configured instructions. Examples include collecting data from a product database or cloud storage. The input is the data processing instructions, and the data is collected as data processing. The output is the collected product data.

[1593] Step 5:

[1594] The server analyzes the format of the collected data. Using data format analysis means, it analyzes and extracts the data structure and necessary information. The input is the collected product data, and format analysis is performed as data calculation. The output is the analyzed data.

[1595] Step 6:

[1596] The server extracts necessary data from the analyzed data. Using the data extraction method, it filters appropriate product information based on the emotion information. The input is the analyzed data, and filtering logic is applied as data processing. The output is the extracted product information.

[1597] Step 7:

[1598] The server converts the extracted data into the specified format and saves it using OutputFormatModule. For example, converting a recommended product list into PDF or HTML format. The input is the extracted product information, and format conversion is performed as data processing. The output is the formatted output.

[1599] Step 8:

[1600] The server notifies the user of the generated output. Based on the results of the emotion recognition means, the notification method and message content are optimized. For example, if stress is high, a simple notification is sent. The input is the formatted output, and the output is the notification to the user.

[1601] Step 9:

[1602] The user receives a notification and checks the provided product list. If necessary, the user can provide feedback to the system using prompt sentences. The input feedback from the user helps improve the system.

[1603] In this way, the present invention realizes a system that can provide optimal product recommendations and support in a virtual store according to the emotional state of the customer.

[1604] 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.

[1605] 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.

[1606] 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.

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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).

[1611] 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.

[1612] 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."

[1613] 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.

[1614] 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).

[1615] 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.

[1616] 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.

[1617] 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.

[1618] 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.

[1619] 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.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] 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.

[1624] 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.

[1625] The following is further disclosed regarding the above embodiment.

[1626] (Claim 1)

[1627] a means of collecting data from a data source;

[1628] a means for analyzing the format of the collected data;

[1629] A means for extracting necessary data from the analyzed data;

[1630] A means for converting the extracted data into a specified format and saving it;

[1631] a means for notifying the user of the generated output;

[1632] A system including:

[1633] (Claim 2)

[1634] 10. The system of claim 1, further comprising means for accessing the data source using appropriate authentication information depending on the type of data source.

[1635] (Claim 3)

[1636] 10. The system of claim 1, further comprising means for applying filtering logic to select target data based on the collected data.

[1637] "Example 1"

[1638] (Claim 1)

[1639] a means of collecting data from a data source;

[1640] a means for analyzing the format of the collected data;

[1641] A means for extracting necessary data from the analyzed data;

[1642] A means for converting the extracted data into a specified format and saving it;

[1643] a means for notifying the user of the generated output;

[1644] means for receiving and parsing a natural language prompt;

[1645] a means of securely accessing data sources using credentials;

[1646] A system including:

[1647] (Claim 2)

[1648] 10. The system of claim 1, further comprising means for accessing the data source using appropriate authentication information depending on the type of data source.

[1649] (Claim 3)

[1650] 10. The system of claim 1, further comprising means for applying filtering logic to select target data based on the collected data.

[1651] "Application Example 1"

[1652] (Claim 1)

[1653] a means of collecting data from a data source;

[1654] a means for analyzing the format of the collected data;

[1655] A means for extracting necessary data from the analyzed data;

[1656] A means for converting the extracted data into a specified format and saving it;

[1657] a means for notifying the user of the generated output;

[1658] A means of analyzing logistics management information and calculating optimal delivery routes;

[1659] A means of monitoring inventory information in real time and sending necessary warnings;

[1660] A system including:

[1661] (Claim 2)

[1662] 10. The system of claim 1, further comprising means for accessing the data source using appropriate authentication information depending on the type of data source.

[1663] (Claim 3)

[1664] 10. The system of claim 1, further comprising means for applying filtering logic to select target data based on the collected data.

[1665] "Example 2: Combining Emotion Engines"

[1666] (Claim 1)

[1667] a means of collecting data from a data source;

[1668] a means for analyzing the format of the collected data;

[1669] A means for extracting necessary data from the analyzed data;

[1670] A means for converting the extracted data into a specified format and saving it;

[1671] a means for notifying the user of the generated output;

[1672] an emotion engine means for analyzing the user's emotions in real time;

[1673] a means of using the results of the emotion engine to adjust the behavior of the entire system;

[1674] A system including:

[1675] (Claim 2)

[1676] 10. The system of claim 1, further comprising means for accessing the data source using appropriate authentication information depending on the type of data source.

[1677] (Claim 3)

[1678] 10. The system of claim 1, further comprising means for applying filtering logic to select target data based on the collected data.

[1679] "Application example 2 when combining emotion engines"

[1680] (Claim 1)

[1681] a means of collecting data from a data source;

[1682] a means for analyzing the format of the collected data;

[1683] A means for extracting necessary data from the analyzed data;

[1684] A means for converting the extracted data into a specified format and saving it;

[1685] a means for notifying the user of the generated output;

[1686] emotion recognition means for recognizing the user's emotions in real time;

[1687] means for adjusting the operation of the entire system based on the emotion information obtained by the emotion recognition means;

[1688] A system including:

[1689] (Claim 2)

[1690] 10. The system of claim 1, further comprising means for accessing the data source using appropriate authentication information depending on the type of data source.

[1691] (Claim 3)

[1692] 10. The system of claim 1, further comprising means for applying filtering logic to select target data based on the collected data. [Explanation of symbols]

[1693] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting data from a data source; a means for analyzing the format of the collected data; A means for extracting necessary data from the analyzed data; A means for converting the extracted data into a specified format and saving it; a means for notifying the user of the generated output; A system including:

2. The system of claim 1 , further comprising means for accessing the data source using appropriate authentication information depending on the type of data source.

3. The system of claim 1 , further comprising means for applying filtering logic to select target data based on the collected data.

Images