System

Abstract

A system is provided.SOLUTION: This system includes a means for allowing a user to input an analysis condition in a text format, a means for automatically collecting data from a data storage system, a means for confirming and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been confirmed, and a means for generating a report based on the analysis result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With current data storage systems, when extracting and analyzing the necessary data from multiple data sources, problems such as misaligned rows, differences in format, and missing data are likely to occur. Specialist knowledge of SQL and other languages ​​is also required, and specifying what content to analyze and how takes time and effort. Furthermore, each time a report is generated, the conditions must be changed and the data must be extracted again, resulting in inefficiency. These issues make data analysis a cumbersome process that is extremely difficult for users without specialized knowledge. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. Specifically, the system includes a means for a user to input analytical conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating a report based on the analysis results. The system also includes a means for automatically determining the period and type of data to be collected based on the conditions entered by the user in text format, a means for acquiring data from a local electronic spreadsheet file, a means for performing trend and correlation analysis based on the data analysis results and reflecting the analysis results in a report as graphs and comments, and a means for outputting the report in a format specified by the user. This system enables efficient data analysis even without specialized knowledge, significantly reducing the burden of reporting work.

[0006] "User" means any person or entity that uses the System to collect and analyze data.

[0007] "Text format" refers to an input format in which the content is described by a string of characters.

[0008] "Analysis conditions" are specific instructions and parameters for data collection and analysis specified by the user.

[0009] "Data storage system" is a general term for computer systems, databases, cloud storage, etc. that store and manage data.

[0010] "Automatically" means that a program or machine operates independently without human intervention.

[0011] "Data integrity" refers to a state in which the accuracy and consistency of data are ensured.

[0012] "Correction" refers to correcting an error or inconsistency and bringing it to a correct state.

[0013] "Data analysis" is the process of extracting information from collected data using statistical or mathematical methods.

[0014] A "report" is a document or material that summarizes the results of data analysis.

[0015] "Means" are methods or tools used to achieve a particular goal.

[0016] A "period" refers to a certain continuous span of time.

[0017] "Type" refers to different categories or characteristics of data classified according to certain criteria.

[0018] A "local electronic spreadsheet file" is a spreadsheet software file stored on a computer's local storage.

[0019] A "trend" indicates the long-term tendency or direction of change in data.

[0020] "Correlation analysis" is a method for analyzing the interrelationships and dependencies between two or more variables.

[0021] A "graph" is a diagram for visually displaying data.

[0022] "Comments" are descriptions of explanations or supplements to the analysis results.

[0023] "Format" refers to the specific presentation or file type of the data or report. [Brief explanation of the drawings]

[0024] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0025] 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.

[0026] First, the terms used in the following description will be explained.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] [First embodiment]

[0033] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0034] 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.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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."

[0045] ---

[0046] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows:

[0047] 1. User Input

[0048] Users enter analysis conditions in text format through the system's user interface (UI). For example, they might enter a condition such as, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0049] 2. Data Collection

[0050] The server analyzes the conditions entered by the user and activates the data collection engine, which accesses the specified data sources (corporate core systems, databases, cloud storage, local electronic spreadsheet files, etc.) and automatically collects the required data. For example, it retrieves relevant sales data from a sales database and also reads related data from a locally stored Excel file.

[0051] 3. Data integrity check

[0052] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[0053] 4. Data Analysis

[0054] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This process includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden increases in sales in specific categories. It also analyzes the correlation between sales data and advertising expenditure data and creates a report based on the results.

[0055] 5. Report generation and provision

[0056] The server generates a report based on the analysis results. The report includes a data summary, graphs, trend analysis results, and correlation comments. The report is output in a format specified by the user (PDF, Excel, PNG, etc.) and provided to the user via a dashboard. For example, the server can save the generated report in PDF format, and the user can download it from the dashboard to use as meeting material.

[0057] ---

[0058] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

[0059] The processing flow will be explained below.

[0060] Step 1: User Input

[0061] Users use the system's interface to enter analysis conditions in text format, such as "aggregate sales data from January 2023 to June 2023 and graph it by category." In addition, users can specify specific time periods and aggregation items.

[0062] Step 2: Condition analysis

[0063] The server analyzes the text conditions entered by the user and determines the type, period, and format of data to be collected. For example, the server generates specific analysis conditions such as "sales data," "January to June 2023," and "by category."

[0064] Step 3: Start the data collection engine

[0065] The server runs a data collection engine and accesses multiple data storage systems based on analysis criteria, including corporate systems, databases, cloud storage, and local electronic spreadsheets.

[0066] Step 4: Data collection

[0067] The server automatically collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. The collected data is temporarily stored on the server.

[0068] Step 5: Data integrity check

[0069] The server then performs a process to check the integrity of the collected data. This process involves standardizing the data format, filling in missing values, and deleting and merging duplicate data. For example, it standardizes different date formats (YYYY / MM / DD vs MM-DD-YYYY) and merges data with the same product name.

[0070] Step 6: Data analysis

[0071] The server then performs a specified analysis process on the data after verifying its integrity, which may include generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, the server may analyze monthly sales trends to detect sudden sales spikes in a particular category.

[0072] Step 7: Generate reports

[0073] The server generates a report based on the data analysis results. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.).

[0074] Step 8: Reporting

[0075] Users can download the generated report from the system dashboard. For example, users can access the dashboard and click the download link for the completed report to obtain the report in PDF format.

[0076] Example 1

[0077] 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."

[0078] Modern companies require systems that can effectively collect and analyze large amounts of data to support rapid and accurate decision-making. However, conventional systems require a great deal of effort to collect data and verify consistency, and are often only available to users with specific expertise. Furthermore, collecting data from multiple sources, unifying data in different formats, and creating visual reports of analysis results are all time-consuming. Furthermore, the lack of functionality for outputting reports in various formats creates a problem of reduced user convenience.

[0079] 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.

[0080] In this invention, the server includes a means for a user to input analytical conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, a means for generating a report based on the analysis results, and a means for outputting the report in a format specified by the user. This allows users without specialized knowledge to easily perform complex data collection and analysis, reduces the burden of reporting work, and enables quick and accurate decision-making based on data.

[0081] A "user" is a person who operates the system to input analytical conditions and instructs the output of a report.

[0082] "Text format" refers to the format of a string of characters that allows a user to input analytical conditions and instructions to the system.

[0083] "Analysis conditions" are information for specifying the period and items to be collected and analyzed.

[0084] "Data storage system" is a general term for systems that store data, such as a company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[0085] "Data collection" is the act of obtaining necessary data from designated data sources.

[0086] "Consistency check" is the process of creating a consistent data set by standardizing the format of collected data, filling in missing values, and deleting and integrating duplicate data.

[0087] "Data analysis" refers to the process of generating summaries, creating graphs, conducting trend analysis, and performing correlation analysis using data whose consistency has been confirmed.

[0088] "Report generation" is the act of creating a visually easy-to-understand report based on the results of data analysis.

[0089] "Report output" is the process of saving and providing the generated report in a format specified by the user, such as PDF, Excel, or PNG.

[0090] "Format" refers to the file type and data representation method specified for report output.

[0091] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows.

[0092] Users access the system's user interface (UI) through a web browser and enter analysis conditions in text format. This UI is built using HTML and JavaScript, and the entered conditions are sent to the server as an HTTP request. For example, a user might enter something like, "Please aggregate sales data from January 2023 to June 2023 and graph it by category."

[0093] The server analyzes the received request and launches the data collection engine. Implemented in Python or Java, the data collection engine accesses the company's core systems, cloud storage, and local electronic spreadsheet files (e.g., MySQL databases, AWS S3 buckets, Excel files, etc.) to collect the necessary data. For example, it retrieves sales data from January 2023 to June 2023 from a MySQL database and then reads related data from a locally stored Excel file.

[0094] The server performs preprocessing to check the integrity of the collected data. This includes standardizing data formats, filling in missing values, and deleting and merging duplicate data. For example, it converts date data stored in different formats into a standard format (YYYY-MM-DD) and merges duplicate product data into one.

[0095] Based on the data whose integrity has been confirmed, the server executes the specified analysis process. For data analysis, Python libraries such as Pandas and NumPy are used to analyze monthly sales trends and detect sudden increases in sales in specific categories. The server also calculates correlations between sales data and advertising expenditure data and analyzes the results.

[0096] The analysis results are compiled into a visually easy-to-read report during the report generation process. The server creates graphs using Matplotlib and Seaborn, and generates reports in PDF format using ReportLab. The reports include data summaries, graphs, trend analysis results, and correlation-based comments. The generated reports are uploaded to a dashboard and can be downloaded by users.

[0097] As a concrete example, consider the case where the user enters the following prompt sentence:

[0098] Example prompt sentence:

[0099] Please compile sales data from January 2023 to June 2023 and graph it by category. Also, please analyze the correlation with advertising expenses.

[0100] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

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

[0102] Step 1:

[0103] The user accesses the system's user interface (UI) through a web browser and enters the analysis conditions in text format. Specifically, the user enters "Aggregate sales data from January 2023 to June 2023 and graph it by category" into the UI text box and clicks the send button. This operation sends the analysis conditions to the server as an HTTP request. The input is the analysis conditions in text format, and the output is an HTTP request to the server.

[0104] Step 2:

[0105] The server analyzes the received HTTP request and starts the data collection engine. Specifically, the server extracts the conditions entered by the user from the request body and sets specific parameters for data collection based on them. For example, it analyzes the period and aggregation items and passes them to the data collection engine. The input is the analysis conditions in the HTTP request, and the output is the set data collection parameters.

[0106] Step 3:

[0107] The server collects the required data from the specified data source through the data collection engine. Specifically, the server connects to the MySQL database and issues a query such as "SELECT FROM sales WHERE date BETWEEN '2023-01-01' AND '2023-06-30'" to retrieve sales data. It also reads corresponding sales data from a local electronic spreadsheet file. The input is the data collection parameters, and the output is the collected raw data.

[0108] Step 4:

[0109] The server checks the integrity of the collected data and performs necessary preprocessing. Specifically, the server unifies different date formats (e.g., YYYY-MM-DD), removes duplicate data, and imputes missing values ​​with the mean or median. The input is the collected raw data, and the output is clean data that has been checked for integrity.

[0110] Step 5:

[0111] The server then executes the specified analysis process using the data whose integrity has been confirmed. Specifically, the server creates a data frame using the Pandas library and performs grouping and aggregation processes. It also uses Matplotlib to graph monthly sales trends and calculate the correlation between sales data and advertising expense data. The input is clean data, and the output is the analysis results.

[0112] Step 6:

[0113] The server generates a report based on the analysis results. Specifically, the server uses ReportLab to create a PDF report and embeds the generated graphs and analysis results in the report. The input is the analysis results, and the output is a PDF report.

[0114] Step 7:

[0115] The server provides the generated report to the user. Specifically, the server uploads the PDF report to the dashboard and provides a download link to the user. The user accesses the dashboard and downloads the PDF report for use. The input is the PDF report, and the output is a report link that the user can download.

[0116] (Application example 1)

[0117] 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."

[0118] Currently, corporate data analysis work is extremely complicated, and in many cases, analysts with specialized knowledge must manually collect data, check its consistency, and perform analysis. This process is time-consuming, labor-intensive, and inefficient. Many businesses also require real-time data analysis, but current systems make this difficult to achieve. In particular, sales representatives and customer support staff need an environment where they can view data in real time on their smartphones so they can quickly take action. A system that can solve this problem is needed.

[0119] 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.

[0120] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating a report based on the analysis results and displaying it on a smartphone application. This enables sales representatives and customer support to check sales data in real time and quickly take countermeasures.

[0121] "User" refers to a person or organization that operates the system, inputs analytical conditions, and checks data collection and analytical results.

[0122] "Text format" refers to the input method for analysis conditions and search queries expressed as character strings.

[0123] "Analysis conditions" are the standards and parameters for data collection and analysis specified by the user, including the period and aggregation items.

[0124] A "data storage system" is a system that stores data such as a company's core systems, databases, cloud storage, and local files.

[0125] "Means for automatically collecting data" refers to a system that automatically collects necessary data from designated data sources using a program.

[0126] "Means for checking and correcting data consistency" refers to a system for standardizing the format of collected data, completing missing values, and deleting and integrating duplicate data.

[0127] "Means for analyzing data whose consistency has been confirmed" refers to a system for conducting trend analysis and correlation analysis based on data whose consistency has been confirmed.

[0128] "Means for generating reports and displaying them on a smartphone application" refers to a mechanism for creating reports including graphs and charts based on the analysis results, allowing users to view them on a smartphone application.

[0129] This invention provides a system that allows users to input analytical conditions in text format, automatically collects data from multiple data storage systems, checks the consistency of the data, analyzes it, and finally generates a report that is displayed on a smartphone application.

[0130] The server receives analysis conditions in text format from the user through a user interface. This user interface includes fields for entering detailed parameters such as the analysis period and aggregation items. For example, a user might enter a condition such as "Aggregate sales data from January 2023 to June 2023 and graph it by category."

[0131] The server then launches a data collection engine to automatically collect the required data from designated data sources, such as enterprise systems, databases, cloud storage, local spreadsheets, etc. The collected data is often stored in different formats, so the server must convert it into a unified format.

[0132] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[0133] Once the integrity of the data has been confirmed, it is analyzed according to the specified analysis process. The server generates summaries, creates graphs, performs trend analysis, and performs correlation analysis. For example, it can analyze monthly sales trends to detect sudden increases in sales in a particular category. It can also analyze correlations between sales data and advertising spend data and create reports based on the results.

[0134] Finally, the server generates a report based on the analysis results and displays it on the smartphone application. This report includes a data summary, graphs, trend analysis results, and correlation comments. Users receive the report in the specified format (e.g., PDF, Excel, PNG, etc.) and can view it on the dashboard through the smartphone application.

[0135] Hardware and software used

[0136] The server uses the following hardware and software:

[0137] Hardware: Server computers, cloud storage, and users' smartphones

[0138] Software: Flask (web application framework), pandas (data analysis library), matplotlib (graph generation library)

[0139] Specific examples

[0140] For example, a sales representative at an online retailer might want to analyze data based on the following criteria:

[0141] "Analyze sales data by category from January 2023 to June 2023 and chart monthly sales trends."

[0142] Once these conditions are entered through the user interface, the server automatically collects sales data for the specified period from databases and cloud storage, checks the data for consistency, and then analyzes it.The final report is displayed on a smartphone application, allowing sales representatives to check the results in real time.

[0143] Prompt Sentence Examples

[0144] Period: January 2023 to June 2023

[0145] Aggregate item: Sales data by category

[0146] Expected output: Chart of monthly sales trends

[0147] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0148] Step 1:

[0149] The user inputs the analysis conditions in text format.

[0150] Input: Analysis period, aggregation items, specific analysis conditions (e.g., "Aggregate sales data from January 2023 to June 2023 and graph it by category").

[0151] How it works: You enter a condition in text format in an input field in the user interface and send it to the server.

[0152] Output: The analysis conditions are sent to the server.

[0153] Step 2:

[0154] The server analyzes the analysis conditions in text format received from the user.

[0155] Input: Analysis conditions entered by the user.

[0156] Operation: The server analyzes the text of the analysis conditions and extracts parameters such as the period for collecting data and the items to be aggregated.

[0157] Output: Parsed parameters (analysis period, aggregation items, etc.).

[0158] Step 3:

[0159] The server launches a data collection engine to automatically collect data from the specified data sources.

[0160] Input: Parsed parameters (analysis period, aggregation items, etc.).

[0161] How it works: The data collection engine starts and collects the relevant data from the company's core systems, databases, cloud storage, local electronic spreadsheets, etc.

[0162] Output: The raw data collected.

[0163] Step 4:

[0164] The server checks and corrects the integrity of the collected data.

[0165] Input: Raw data collected.

[0166] Operation: The server standardizes data formats, fills in missing values, and removes and consolidates duplicate data.

[0167] Output: Data with integrity checked.

[0168] Step 5:

[0169] The server performs analysis based on the data whose integrity has been confirmed.

[0170] Input: Data whose integrity has been checked.

[0171] Action: The server performs the specified analysis operations such as summary generation, graph creation, trend analysis, correlation analysis, etc.

[0172] Output: Analysis results.

[0173] Step 6:

[0174] The server generates a report based on the analysis results and displays it on a smartphone application.

[0175] Input: Analysis results.

[0176] Operation: The server creates a report containing graphs and charts based on the analysis results and sends it to a smartphone application. The user can view the report through the application.

[0177] Output: The report displayed on the user's smartphone.

[0178] 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.

[0179] ---

[0180] The big data aggregation system of the present invention not only automatically collects data from multiple data storage systems based on user input, analyzes the data, and generates reports, but also includes an emotion engine that recognizes user emotions and customizes the system's operation. Detailed embodiments are described below.

[0181] 1. User Input

[0182] Users enter analysis conditions in text format through the system's user interface (UI). For example, they can enter a condition such as "aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0183] 2. Emotion recognition

[0184] The server recognizes the user's emotion from the user's input using an emotion engine, which uses natural language processing and facial expression recognition technologies to determine the user's emotion (e.g., joy, sadness, anger, surprise, fear, etc.).

[0185] 3. Start the data collection engine

[0186] Based on the emotion engine's judgment results, the server activates the data collection engine and collects data from appropriate data sources based on the analysis conditions, including the company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[0187] 4. Data Collection

[0188] The server collects and temporarily stores the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It also filters the collected data based on the emotion engine.

[0189] 5. Data integrity check

[0190] The server performs processes to check the integrity of the collected data, including standardizing data formats, filling in missing values, and removing and merging duplicate data. It is also possible to adjust the priority of filtering and correction in this process based on the results of the emotion engine.

[0191] 6. Data Analysis

[0192] The server then performs the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Furthermore, it customizes the content and presentation of reports based on the results of the emotion engine.

[0193] 7. Report Generation and Delivery

[0194] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. It is output in the format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report are adjusted based on the results of the emotion engine. This allows users to receive a report that is easier to understand and tailored to their purpose.

[0195] 8. Feedback and Further Customization

[0196] Users can review the generated reports and provide further feedback, which the emotion engine analyzes in real time to further customize the system's behavior and report content.

[0197] ---

[0198] As described above, this invention achieves flexible and efficient data analysis that takes user emotions into consideration by integrating an emotion engine into a conventional data collection and analysis system, thereby reducing the burden on users and supporting more accurate decision-making.

[0199] The processing flow will be explained below.

[0200] Step 1: User Input

[0201] Users enter analysis conditions in text format using the system's user interface (UI). For example, they might enter, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0202] Step 2: Emotion Recognition

[0203] The server analyzes the user's input and behavior on the interface (e.g., typing speed, frequency of typos, etc.) and uses an emotion engine to recognize the user's emotions. For example, if the user types quickly, the emotion engine determines that the user is impatient.

[0204] Step 3: Condition analysis and customization

[0205] The server analyzes the conditions entered by the user and determines the type, period, and format of data to be collected. Furthermore, it customizes the analysis conditions and the display method of the results based on the results of the emotion engine. For example, if the user is in a hurry, the system adjusts to present important analysis results earlier.

[0206] Step 4: Start the data collection engine

[0207] The server runs the data collection engine and accesses data sources based on the analysis criteria, including enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[0208] Step 5: Data collection

[0209] The server collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It may also adjust the priority and speed of data collection based on the results of the emotion engine.

[0210] Step 6: Data integrity check

[0211] The server checks the integrity of the collected data, standardizes the data format, fills in missing values, and removes and merges duplicate data. Based on the results of the emotion engine, it adjusts the speed of this process and the strictness of the filtering.

[0212] Step 7: Data analysis

[0213] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Based on the results of the sentiment engine, it customizes the display and order of the analysis results.

[0214] Step 8: Generate reports

[0215] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report reflect the results of the emotion engine.

[0216] Step 9: Reporting

[0217] Users can download the generated report from the system's dashboard. For example, a user can access the dashboard and click the download link for the completed report to obtain a PDF version of the report. The report also includes feedback based on the user's emotional state.

[0218] Step 10: Feedback and customization

[0219] The user can review the generated report and provide further feedback to the system, for example, requesting additional analysis or detailed explanations of specific items. The server analyzes the user's feedback and the results of the emotion engine to further customize the system's behavior and report content for future use.

[0220] Example 2

[0221] 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."

[0222] Conventional big data aggregation systems do not consider user sentiment when verifying the integrity of collected data or analyzing it, which can lead to analysis results that do not match user expectations or requirements. Furthermore, handling large amounts of data places a heavy burden on users, preventing them from effectively utilizing the results of data analysis. Furthermore, there is a need for a flexible system that can incorporate user feedback in the processes of rapid data collection, analysis, and report generation.

[0223] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0224] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for recognizing user emotions and customizing system operation, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating reports based on the analysis results, thereby enabling flexible and efficient data analysis and report generation that takes user emotions into consideration.

[0225] The "means for the user to input analytical conditions in text format" refers to a device or software for inputting text data specified by the user into the system through an interface.

[0226] "Means for automatically collecting data from data storage systems" refers to devices or software that automatically retrieve the required data from different data sources.

[0227] "Means for recognizing user emotions and customizing system behavior" refers to a device or software that analyzes user emotions and adjusts system behavior and interface based on the results.

[0228] "Means for verifying and correcting the consistency of collected data" refers to devices or software that verify the format and content of extracted data and make appropriate corrections to ensure consistency.

[0229] The "means for analyzing data whose integrity has been confirmed" refers to a device or software for performing a specified analysis based on data whose integrity has been confirmed.

[0230] A "means for generating a report based on the analysis results" is a device or software that organizes the results of the data analysis and creates a visual or written report to provide to the user.

[0231] "Local spreadsheet files" are files created by spreadsheet software that are stored on a user's individual device or local storage.

[0232] The big data aggregation system of the present invention includes a process for automatically collecting data from multiple data storage systems based on user input and generating reports from the analysis results. In addition, it uses an emotion engine that recognizes user emotions and customizes the system's behavior, allowing users to obtain optimal analysis results based on their emotions.

[0233] The specific system configuration uses the following hardware and software:

[0234] User Interface (UI): A web-based interface implemented using HTML and JavaScript.

[0235] Emotion Engine: A software module that uses natural language processing (NLP) and facial expression recognition technologies and is implemented in Python.

[0236] Data Collection Engine: Includes Python scripts that collect data from enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[0237] Data integrity check module: A software module that uses Python and R to standardize data formats, complete missing values, and remove duplicate data.

[0238] Data analysis module: A software module that performs trend analysis of sales data and graphs sales data by category, using Python's pandas and matplotlib libraries.

[0239] Report generation module: Software that generates reports in PDF, Excel, or PNG format based on analysis results, using Python's ReportLab.

[0240] (Example)

[0241] The user enters text into the system's UI, saying, "Please aggregate sales data from January 2023 to June 2023 and graph it by category." If the user indicates an emotion, for example, "I'm in a hurry," the emotion engine analyzes this information and switches the operation of the entire system to "high-speed mode."

[0242] The server quickly and efficiently launches the data collection engine based on the analysis conditions and emotion recognition results. It collects the necessary data from the company's core systems and local Excel files, standardizes the format, and imputes missing values. After verifying data integrity, the data analysis module graphs monthly sales trends and sales data by category.

[0243] The server generates a visually easy-to-understand PDF report based on the analysis results and provides it to the user. If the user reviews the report and requests a more detailed analysis, they can enter their feedback into the system, which will use the emotion engine to refine the next analysis process.

[0244] Through the above process, this big data aggregation system can flexibly and efficiently meet user requirements and support more accurate decision-making.

[0245] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0246] Step 1:

[0247] The user inputs analysis conditions in text format through the system's UI.

[0248] Specifically, the user enters "Please aggregate sales data from January 2023 to June 2023 and graph it by category" and clicks the submit button.

[0249] Input: Analysis conditions (text format)

[0250] Output: Analysis conditions are sent to the server

[0251] Step 2:

[0252] The server receives the user's input and recognizes the user's emotions using an emotion engine.

[0253] Specifically, it uses Natural Language Processing (NLP) technology to analyze text and determine whether the user is in a hurry.

[0254] Input: Text data of analysis conditions

[0255] Output: User emotion data (e.g., hurry)

[0256] Step 3:

[0257] The server starts the data collection engine based on the determination results of the emotion engine and the analysis conditions.

[0258] Determine which data sources to acquire to complete the overall data collection process most efficiently. At this stage, develop a plan to collect data from your company's core systems, cloud storage, local electronic spreadsheets, etc.

[0259] Input: Emotion data, analysis conditions

[0260] Output: Execution plan for data collection

[0261] Step 4:

[0262] The server collects the data using a data collection engine.

[0263] Specifically, it sends API requests to the sales database and retrieves necessary data from cloud storage and the local file system.

[0264] Input: Execution plan for data collection

[0265] Output: Raw data collected (e.g. sales data)

[0266] Step 5:

[0267] The server checks the consistency of the collected data and performs correction processing.

[0268] Specifically, data cleaning processes are carried out, such as standardizing data formats, filling in missing values, and deleting duplicate data.

[0269] Input: Raw data collected

[0270] Output: Consistency checked and corrected data

[0271] Step 6:

[0272] The server performs analysis of the corrected data using a data analysis module.

[0273] Here, sales data trend analysis and category sales data graphing are performed using Python's pandas and matplotlib libraries.

[0274] Input: Corrected data

[0275] Output: Analysis results (e.g., sales graph by category)

[0276] Step 7:

[0277] The server generates a report based on the analysis results.

[0278] Specifically, the analysis results are compiled into a report in a visually easy-to-understand format (PDF, Excel, PNG, etc.), and a library such as ReportLab is used to generate PDF reports.

[0279] Input: Analysis results

[0280] Output: Report (e.g. PDF format)

[0281] Step 8:

[0282] The user reviews the generated report and provides any necessary feedback to the system.

[0283] For example, you can enter a request such as "I want more detailed analysis." This feedback will be used to improve the system as a whole.

[0284] Input: Feedback text data

[0285] Output: Feedback is sent to the server

[0286] Step 9:

[0287] The server receives the feedback and analyzes it using an emotion engine to further optimize the system's behavior and future analysis processes.

[0288] Based on the feedback, we will adjust future data analysis policies and algorithms.

[0289] Input: Feedback text data

[0290] Output: Adjusted system operating configuration

[0291] (Application example 2)

[0292] 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."

[0293] Conventional data collection and analysis systems mechanically process data and present results without considering user emotions, making it difficult to respond flexibly based on user intentions and emotions. Displaying personalized advertisements is also difficult, creating a need for improved user experience. Therefore, the present invention aims to improve the efficiency and quality of data analysis and advertisement display by recognizing user emotions and customizing system behavior based on those emotions.

[0294] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0295] In this invention, the server includes means for a user to input analysis conditions in text format, means for automatically collecting data from a data storage system, means for checking and correcting the consistency of the collected data, means for analyzing the data whose consistency has been checked, means for generating a report based on the analysis results, means for recognizing the user's emotions and customizing the operation of the system, and means for generating and displaying personalized advertisements based on the emotions. This allows the system to operate flexibly based on the user's emotions and intentions, making it possible to display more effective and personalized advertisements.

[0296] "Means for users to input analytical conditions in text format" refers to an interface that allows users to input analytical conditions and parameters using text.

[0297] "Means for automatically collecting data from a data storage system" refers to a function for automatically obtaining required data from a predefined data source.

[0298] "Means for verifying and correcting the consistency of collected data" refers to a function that checks whether collected data is accurate and consistent, and makes corrections or amendments as necessary.

[0299] "Means for analyzing data whose integrity has been checked" refers to a function for executing a specified analysis process on data whose integrity has been checked.

[0300] "Means for generating a report based on the analysis results" refers to a function that compiles the results of the analysis and outputs them as a report for the user.

[0301] "Means for recognizing user emotions and customizing system behavior" refers to the ability to detect the user's emotional state and adjust the system's behavior and output based on that information.

[0302] "Means for generating and displaying personalized advertisements based on emotions" refers to a function that reflects the user's emotional data to create and display advertisements that are optimally tailored to each individual user.

[0303] The system for implementing the present invention is configured using a server, a user terminal, and an emotion recognition engine. Each step and the necessary hardware and software will be described in detail below.

[0304] The server provides a means for users to input analysis conditions in text format. Through this interface, users input the period and items they want to analyze. For example, a condition might be entered such as, "Please aggregate sales data by category from January 2023 to June 2023."

[0305] The server has a means for automatically collecting data from data storage systems, such as corporate databases, cloud storage, and local electronic spreadsheet files. The data collection engine automatically collects the required data from these data sources.

[0306] The emotion recognition engine detects emotions from user input and facial expressions. The server uses this information to customize system behavior and filter and analyze data according to the user's psychological state. The emotion engine uses natural language processing technology and facial expression recognition software.

[0307] The integrity of the collected data is checked and corrected as necessary. This includes standardizing the data format, filling in missing values, and deleting and merging duplicate data. The Pandas library, which excels at manipulating data frames, is used for processing.

[0308] The data, once validated, is then analyzed according to a specified analysis process, which includes generating data summaries, creating graphs, and analyzing trends and correlations. The Scikit-learn and Matplotlib libraries are used as analytical tools.

[0309] Based on the analysis results, a report tailored to each user's individual feelings is generated, including adjusting the tone and level of difficulty of the data and outputting it in formats such as PDF, Excel, and PNG. ReportLab, for example, is used as a report generation tool.

[0310] Furthermore, it generates and displays personalized ads based on user emotions and data. This includes a function where the ad display engine takes into account user emotions and past behavioral data to select and display appropriate ads. The timing of ad display is controlled using HTML5 and JavaScript.

[0311] Specific examples

[0312] For example, when a user logs in using a smartphone and enters analysis criteria, a camera detects their facial expressions. If the user is recognized as "happy," entertainment-related advertisements are selected and displayed. At the same time, sales data is automatically collected from the database based on the user-specified period, appropriate trend analysis is performed, and easy-to-understand reports are generated.

[0313] Prompt Sentence Examples

[0314] Develop a system that analyzes a user's facial expressions in real time and displays the most appropriate advertisement based on their emotion. If the user is "Happy," it will display an entertaining advertisement, and if the user is "Sad," it will display an uplifting advertisement. Use OpenCV to capture the user's face with a camera, implement an emotion recognition algorithm, and select the appropriate advertisement from the advertisement database based on the results.

[0315] This allows for appropriate and efficient data analysis and advertising presentation, taking into account the user's psychological state.

[0316] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0317] Step 1:

[0318] The user enters the analysis conditions. The user enters the analysis conditions in text format (e.g., "Please summarize sales data from January 2023 to June 2023 by category") via the UI on their smartphone or PC. This input is then sent to the server.

[0319] Step 2:

[0320] The server performs emotion recognition. The server uses an emotion recognition engine to analyze the user's emotions based on the text entered by the user and the facial expressions captured by the smartphone camera. The analysis results (e.g., "Happy" or "Sad") are used for subsequent data collection and customization processing.

[0321] Step 3:

[0322] The server starts the data collection engine. Based on the emotion recognition results and the user's input conditions, the server collects the necessary data from the appropriate data source (e.g., core system, database, cloud storage, local electronic spreadsheet file). The data collection engine automatically acquires data according to the specified period and items.

[0323] Step 4:

[0324] The server checks and corrects the consistency of the collected data. The server unifies the format of the collected data, completes missing values, and removes duplicate data. Specifically, it uses the Pandas library to operate on data frames and checks consistency. The data input is the collected raw data, and the output is data whose consistency has been checked.

[0325] Step 5:

[0326] The server performs data analysis. Based on the data whose integrity has been confirmed, the server performs the specified analysis process (summary generation, graph creation, trend analysis, correlation analysis). For example, the analysis is performed using the Scikit-learn library or Matplotlib library. The input is the data whose integrity has been confirmed, and the output is the analysis results.

[0327] Step 6:

[0328] The server generates and provides reports. The server generates reports for users based on the results of data analysis. Based on the results of the emotion recognition engine, the tone and difficulty of the report can be adjusted and output in the format specified by the user (PDF, Excel, PNG). Specifically, the PDF report is generated using ReportLab. The input is the analysis results, and the output is a customized report.

[0329] Step 7:

[0330] The server generates and displays personalized ads. Based on the user's emotions and past behavioral data, the server generates the optimal ad and displays it on the smartphone or PC. HTML5 and JavaScript are used to control the timing of ad display. The input is emotional data and past behavioral data, and the output is a personalized ad.

[0331] 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.

[0332] 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.

[0333] 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.

[0334] [Second embodiment]

[0335] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0336] 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.

[0337] 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).

[0338] 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.

[0339] 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.

[0340] 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).

[0341] 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.

[0342] 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.

[0343] 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.

[0344] 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.

[0345] 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.

[0346] 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."

[0347] ---

[0348] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows:

[0349] 1. User Input

[0350] Users enter analysis conditions in text format through the system's user interface (UI). For example, they might enter a condition such as, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0351] 2. Data Collection

[0352] The server analyzes the conditions entered by the user and activates the data collection engine, which accesses the specified data sources (corporate core systems, databases, cloud storage, local electronic spreadsheet files, etc.) and automatically collects the required data. For example, it retrieves relevant sales data from a sales database and also reads related data from a locally stored Excel file.

[0353] 3. Data integrity check

[0354] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[0355] 4. Data Analysis

[0356] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This process includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden increases in sales in specific categories. It also analyzes the correlation between sales data and advertising expenditure data and creates a report based on the results.

[0357] 5. Report generation and provision

[0358] The server generates a report based on the analysis results. The report includes a data summary, graphs, trend analysis results, and correlation comments. The report is output in a format specified by the user (PDF, Excel, PNG, etc.) and provided to the user via a dashboard. For example, the server can save the generated report in PDF format, and the user can download it from the dashboard to use as meeting material.

[0359] ---

[0360] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

[0361] The processing flow will be explained below.

[0362] Step 1: User Input

[0363] Users use the system's interface to enter analysis conditions in text format, such as "aggregate sales data from January 2023 to June 2023 and graph it by category." In addition, users can specify specific time periods and aggregation items.

[0364] Step 2: Condition analysis

[0365] The server analyzes the text conditions entered by the user and determines the type, period, and format of data to be collected. For example, the server generates specific analysis conditions such as "sales data," "January to June 2023," and "by category."

[0366] Step 3: Start the data collection engine

[0367] The server runs a data collection engine and accesses multiple data storage systems based on analysis criteria, including corporate systems, databases, cloud storage, and local electronic spreadsheets.

[0368] Step 4: Data collection

[0369] The server automatically collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. The collected data is temporarily stored on the server.

[0370] Step 5: Data integrity check

[0371] The server then performs a process to check the integrity of the collected data. This process involves standardizing the data format, filling in missing values, and deleting and merging duplicate data. For example, it standardizes different date formats (YYYY / MM / DD vs MM-DD-YYYY) and merges data with the same product name.

[0372] Step 6: Data analysis

[0373] The server then performs a specified analysis process on the data after verifying its integrity, which may include generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, the server may analyze monthly sales trends to detect sudden sales spikes in a particular category.

[0374] Step 7: Generate reports

[0375] The server generates a report based on the data analysis results. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.).

[0376] Step 8: Reporting

[0377] Users can download the generated report from the system dashboard. For example, users can access the dashboard and click the download link for the completed report to obtain the report in PDF format.

[0378] Example 1

[0379] 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."

[0380] Modern companies require systems that can effectively collect and analyze large amounts of data to support rapid and accurate decision-making. However, conventional systems require a great deal of effort to collect data and verify consistency, and are often only available to users with specific expertise. Furthermore, collecting data from multiple sources, unifying data in different formats, and creating visual reports of analysis results are all time-consuming. Furthermore, the lack of functionality for outputting reports in various formats creates a problem of reduced user convenience.

[0381] 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.

[0382] In this invention, the server includes a means for a user to input analytical conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, a means for generating a report based on the analysis results, and a means for outputting the report in a format specified by the user. This allows users without specialized knowledge to easily perform complex data collection and analysis, reduces the burden of reporting work, and enables quick and accurate decision-making based on data.

[0383] A "user" is a person who operates the system to input analytical conditions and instructs the output of a report.

[0384] "Text format" refers to the format of a string of characters that allows a user to input analytical conditions and instructions to the system.

[0385] "Analysis conditions" are information for specifying the period and items to be collected and analyzed.

[0386] "Data storage system" is a general term for systems that store data, such as a company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[0387] "Data collection" is the act of obtaining necessary data from designated data sources.

[0388] "Consistency check" is the process of creating a consistent data set by standardizing the format of collected data, filling in missing values, and deleting and integrating duplicate data.

[0389] "Data analysis" refers to the process of generating summaries, creating graphs, conducting trend analysis, and performing correlation analysis using data whose consistency has been confirmed.

[0390] "Report generation" is the act of creating a visually easy-to-understand report based on the results of data analysis.

[0391] "Report output" is the process of saving and providing the generated report in a format specified by the user, such as PDF, Excel, or PNG.

[0392] "Format" refers to the file type and data representation method specified for report output.

[0393] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows.

[0394] Users access the system's user interface (UI) through a web browser and enter analysis conditions in text format. This UI is built using HTML and JavaScript, and the entered conditions are sent to the server as an HTTP request. For example, a user might enter something like, "Please aggregate sales data from January 2023 to June 2023 and graph it by category."

[0395] The server analyzes the received request and launches the data collection engine. Implemented in Python or Java, the data collection engine accesses the company's core systems, cloud storage, and local electronic spreadsheet files (e.g., MySQL databases, AWS S3 buckets, Excel files, etc.) to collect the necessary data. For example, it retrieves sales data from January 2023 to June 2023 from a MySQL database and then reads related data from a locally stored Excel file.

[0396] The server performs preprocessing to check the integrity of the collected data. This includes standardizing data formats, filling in missing values, and deleting and merging duplicate data. For example, it converts date data stored in different formats into a standard format (YYYY-MM-DD) and merges duplicate product data into one.

[0397] Based on the data whose integrity has been confirmed, the server executes the specified analysis process. For data analysis, Python libraries such as Pandas and NumPy are used to analyze monthly sales trends and detect sudden increases in sales in specific categories. The server also calculates correlations between sales data and advertising expenditure data and analyzes the results.

[0398] The analysis results are compiled into a visually easy-to-read report during the report generation process. The server creates graphs using Matplotlib and Seaborn, and generates reports in PDF format using ReportLab. The reports include data summaries, graphs, trend analysis results, and correlation-based comments. The generated reports are uploaded to a dashboard and can be downloaded by users.

[0399] As a concrete example, consider the case where the user enters the following prompt sentence:

[0400] Example prompt sentence:

[0401] Please compile sales data from January 2023 to June 2023 and graph it by category. Also, please analyze the correlation with advertising expenses.

[0402] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

[0403] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0404] Step 1:

[0405] The user accesses the system's user interface (UI) through a web browser and enters the analysis conditions in text format. Specifically, the user enters "Aggregate sales data from January 2023 to June 2023 and graph it by category" into the UI text box and clicks the send button. This operation sends the analysis conditions to the server as an HTTP request. The input is the analysis conditions in text format, and the output is an HTTP request to the server.

[0406] Step 2:

[0407] The server analyzes the received HTTP request and starts the data collection engine. Specifically, the server extracts the conditions entered by the user from the request body and sets specific parameters for data collection based on them. For example, it analyzes the period and aggregation items and passes them to the data collection engine. The input is the analysis conditions in the HTTP request, and the output is the set data collection parameters.

[0408] Step 3:

[0409] The server collects the required data from the specified data source through the data collection engine. Specifically, the server connects to the MySQL database and issues a query such as "SELECT FROM sales WHERE date BETWEEN '2023-01-01' AND '2023-06-30'" to retrieve sales data. It also reads corresponding sales data from a local electronic spreadsheet file. The input is the data collection parameters, and the output is the collected raw data.

[0410] Step 4:

[0411] The server checks the integrity of the collected data and performs necessary preprocessing. Specifically, the server unifies different date formats (e.g., YYYY-MM-DD), removes duplicate data, and imputes missing values ​​with the mean or median. The input is the collected raw data, and the output is clean data that has been checked for integrity.

[0412] Step 5:

[0413] The server then executes the specified analysis process using the data whose integrity has been confirmed. Specifically, the server creates a data frame using the Pandas library and performs grouping and aggregation processes. It also uses Matplotlib to graph monthly sales trends and calculate the correlation between sales data and advertising expense data. The input is clean data, and the output is the analysis results.

[0414] Step 6:

[0415] The server generates a report based on the analysis results. Specifically, the server uses ReportLab to create a PDF report and embeds the generated graphs and analysis results in the report. The input is the analysis results, and the output is a PDF report.

[0416] Step 7:

[0417] The server provides the generated report to the user. Specifically, the server uploads the PDF report to the dashboard and provides a download link to the user. The user accesses the dashboard and downloads the PDF report for use. The input is the PDF report, and the output is a report link that the user can download.

[0418] (Application example 1)

[0419] 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."

[0420] Currently, corporate data analysis work is extremely complicated, and in many cases, analysts with specialized knowledge must manually collect data, check its consistency, and perform analysis. This process is time-consuming, labor-intensive, and inefficient. Many businesses also require real-time data analysis, but current systems make this difficult to achieve. In particular, sales representatives and customer support staff need an environment where they can view data in real time on their smartphones so they can quickly take action. A system that can solve this problem is needed.

[0421] 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.

[0422] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating a report based on the analysis results and displaying it on a smartphone application. This enables sales representatives and customer support to check sales data in real time and quickly take countermeasures.

[0423] "User" refers to a person or organization that operates the system, inputs analytical conditions, and checks data collection and analytical results.

[0424] "Text format" refers to the input method for analysis conditions and search queries expressed as character strings.

[0425] "Analysis conditions" are the standards and parameters for data collection and analysis specified by the user, including the period and aggregation items.

[0426] A "data storage system" is a system that stores data such as a company's core systems, databases, cloud storage, and local files.

[0427] "Means for automatically collecting data" refers to a system that automatically collects necessary data from designated data sources using a program.

[0428] "Means for checking and correcting data consistency" refers to a system for standardizing the format of collected data, completing missing values, and deleting and integrating duplicate data.

[0429] "Means for analyzing data whose consistency has been confirmed" refers to a system for conducting trend analysis and correlation analysis based on data whose consistency has been confirmed.

[0430] "Means for generating reports and displaying them on a smartphone application" refers to a mechanism for creating reports including graphs and charts based on the analysis results, allowing users to view them on a smartphone application.

[0431] This invention provides a system that allows users to input analytical conditions in text format, automatically collects data from multiple data storage systems, checks the consistency of the data, analyzes it, and finally generates a report that is displayed on a smartphone application.

[0432] The server receives analysis conditions in text format from the user through a user interface. This user interface includes fields for entering detailed parameters such as the analysis period and aggregation items. For example, a user might enter a condition such as "Aggregate sales data from January 2023 to June 2023 and graph it by category."

[0433] The server then launches a data collection engine to automatically collect the required data from designated data sources, such as enterprise systems, databases, cloud storage, local spreadsheets, etc. The collected data is often stored in different formats, so the server must convert it into a unified format.

[0434] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[0435] Once the integrity of the data has been confirmed, it is analyzed according to the specified analysis process. The server generates summaries, creates graphs, performs trend analysis, and performs correlation analysis. For example, it can analyze monthly sales trends to detect sudden increases in sales in a particular category. It can also analyze correlations between sales data and advertising spend data and create reports based on the results.

[0436] Finally, the server generates a report based on the analysis results and displays it on the smartphone application. This report includes a data summary, graphs, trend analysis results, and correlation comments. Users receive the report in the specified format (e.g., PDF, Excel, PNG, etc.) and can view it on the dashboard through the smartphone application.

[0437] Hardware and software used

[0438] The server uses the following hardware and software:

[0439] Hardware: Server computers, cloud storage, and users' smartphones

[0440] Software: Flask (web application framework), pandas (data analysis library), matplotlib (graph generation library)

[0441] Specific examples

[0442] For example, a sales representative at an online retailer might want to analyze data based on the following criteria:

[0443] "Analyze sales data by category from January 2023 to June 2023 and chart monthly sales trends."

[0444] Once these conditions are entered through the user interface, the server automatically collects sales data for the specified period from databases and cloud storage, checks the data for consistency, and then analyzes it.The final report is displayed on a smartphone application, allowing sales representatives to check the results in real time.

[0445] Prompt Sentence Examples

[0446] Period: January 2023 to June 2023

[0447] Aggregate item: Sales data by category

[0448] Expected output: Chart of monthly sales trends

[0449] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0450] Step 1:

[0451] The user inputs the analysis conditions in text format.

[0452] Input: Analysis period, aggregation items, specific analysis conditions (e.g., "Aggregate sales data from January 2023 to June 2023 and graph it by category").

[0453] How it works: You enter a condition in text format in an input field in the user interface and send it to the server.

[0454] Output: The analysis conditions are sent to the server.

[0455] Step 2:

[0456] The server analyzes the analysis conditions in text format received from the user.

[0457] Input: Analysis conditions entered by the user.

[0458] Operation: The server analyzes the text of the analysis conditions and extracts parameters such as the period for collecting data and the items to be aggregated.

[0459] Output: Parsed parameters (analysis period, aggregation items, etc.).

[0460] Step 3:

[0461] The server launches a data collection engine to automatically collect data from the specified data sources.

[0462] Input: Parsed parameters (analysis period, aggregation items, etc.).

[0463] How it works: The data collection engine starts and collects the relevant data from the company's core systems, databases, cloud storage, local electronic spreadsheets, etc.

[0464] Output: The raw data collected.

[0465] Step 4:

[0466] The server checks and corrects the integrity of the collected data.

[0467] Input: Raw data collected.

[0468] Operation: The server standardizes data formats, fills in missing values, and removes and consolidates duplicate data.

[0469] Output: Data with integrity checked.

[0470] Step 5:

[0471] The server performs analysis based on the data whose integrity has been confirmed.

[0472] Input: Data whose integrity has been checked.

[0473] Action: The server performs the specified analysis operations such as summary generation, graph creation, trend analysis, correlation analysis, etc.

[0474] Output: Analysis results.

[0475] Step 6:

[0476] The server generates a report based on the analysis results and displays it on a smartphone application.

[0477] Input: Analysis results.

[0478] Operation: The server creates a report containing graphs and charts based on the analysis results and sends it to a smartphone application. The user can view the report through the application.

[0479] Output: The report displayed on the user's smartphone.

[0480] 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.

[0481] ---

[0482] The big data aggregation system of the present invention not only automatically collects data from multiple data storage systems based on user input, analyzes the data, and generates reports, but also includes an emotion engine that recognizes user emotions and customizes the system's operation. Detailed embodiments are described below.

[0483] 1. User Input

[0484] Users enter analysis conditions in text format through the system's user interface (UI). For example, they can enter a condition such as "aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0485] 2. Emotion recognition

[0486] The server recognizes the user's emotion from the user's input using an emotion engine, which uses natural language processing and facial expression recognition technologies to determine the user's emotion (e.g., joy, sadness, anger, surprise, fear, etc.).

[0487] 3. Start the data collection engine

[0488] Based on the emotion engine's judgment results, the server activates the data collection engine and collects data from appropriate data sources based on the analysis conditions, including the company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[0489] 4. Data Collection

[0490] The server collects and temporarily stores the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It also filters the collected data based on the emotion engine.

[0491] 5. Data integrity check

[0492] The server performs processes to check the integrity of the collected data, including standardizing data formats, filling in missing values, and removing and merging duplicate data. It is also possible to adjust the priority of filtering and correction in this process based on the results of the emotion engine.

[0493] 6. Data Analysis

[0494] The server then performs the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Furthermore, it customizes the content and presentation of reports based on the results of the emotion engine.

[0495] 7. Report Generation and Delivery

[0496] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. It is output in the format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report are adjusted based on the results of the emotion engine. This allows users to receive a report that is easier to understand and tailored to their purpose.

[0497] 8. Feedback and Further Customization

[0498] Users can review the generated reports and provide further feedback, which the emotion engine analyzes in real time to further customize the system's behavior and report content.

[0499] ---

[0500] As described above, this invention achieves flexible and efficient data analysis that takes user emotions into consideration by integrating an emotion engine into a conventional data collection and analysis system, thereby reducing the burden on users and supporting more accurate decision-making.

[0501] The processing flow will be explained below.

[0502] Step 1: User Input

[0503] Users enter analysis conditions in text format using the system's user interface (UI). For example, they might enter, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0504] Step 2: Emotion Recognition

[0505] The server analyzes the user's input and behavior on the interface (e.g., typing speed, frequency of typos, etc.) and uses an emotion engine to recognize the user's emotions. For example, if the user types quickly, the emotion engine determines that the user is impatient.

[0506] Step 3: Condition analysis and customization

[0507] The server analyzes the conditions entered by the user and determines the type, period, and format of data to be collected. Furthermore, it customizes the analysis conditions and the display method of the results based on the results of the emotion engine. For example, if the user is in a hurry, the system adjusts to present important analysis results earlier.

[0508] Step 4: Start the data collection engine

[0509] The server runs the data collection engine and accesses data sources based on the analysis criteria, including enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[0510] Step 5: Data collection

[0511] The server collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It may also adjust the priority and speed of data collection based on the results of the emotion engine.

[0512] Step 6: Data integrity check

[0513] The server checks the integrity of the collected data, standardizes the data format, fills in missing values, and removes and merges duplicate data. Based on the results of the emotion engine, it adjusts the speed of this process and the strictness of the filtering.

[0514] Step 7: Data analysis

[0515] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Based on the results of the sentiment engine, it customizes the display and order of the analysis results.

[0516] Step 8: Generate reports

[0517] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report reflect the results of the emotion engine.

[0518] Step 9: Reporting

[0519] Users can download the generated report from the system's dashboard. For example, a user can access the dashboard and click the download link for the completed report to obtain a PDF version of the report. The report also includes feedback based on the user's emotional state.

[0520] Step 10: Feedback and customization

[0521] The user can review the generated report and provide further feedback to the system, for example, requesting additional analysis or detailed explanations of specific items. The server analyzes the user's feedback and the results of the emotion engine to further customize the system's behavior and report content for future use.

[0522] Example 2

[0523] 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."

[0524] Conventional big data aggregation systems do not consider user sentiment when verifying the integrity of collected data or analyzing it, which can lead to analysis results that do not match user expectations or requirements. Furthermore, handling large amounts of data places a heavy burden on users, preventing them from effectively utilizing the results of data analysis. Furthermore, there is a need for a flexible system that can incorporate user feedback in the processes of rapid data collection, analysis, and report generation.

[0525] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0526] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for recognizing user emotions and customizing system operation, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating reports based on the analysis results, thereby enabling flexible and efficient data analysis and report generation that takes user emotions into consideration.

[0527] The "means for the user to input analytical conditions in text format" refers to a device or software for inputting text data specified by the user into the system through an interface.

[0528] "Means for automatically collecting data from data storage systems" refers to devices or software that automatically retrieve the required data from different data sources.

[0529] "Means for recognizing user emotions and customizing system behavior" refers to a device or software that analyzes user emotions and adjusts system behavior and interface based on the results.

[0530] "Means for verifying and correcting the consistency of collected data" refers to devices or software that verify the format and content of extracted data and make appropriate corrections to ensure consistency.

[0531] The "means for analyzing data whose integrity has been confirmed" refers to a device or software for performing a specified analysis based on data whose integrity has been confirmed.

[0532] A "means for generating a report based on the analysis results" is a device or software that organizes the results of the data analysis and creates a visual or written report to provide to the user.

[0533] "Local spreadsheet files" are files created by spreadsheet software that are stored on a user's individual device or local storage.

[0534] The big data aggregation system of the present invention includes a process for automatically collecting data from multiple data storage systems based on user input and generating reports from the analysis results. In addition, it uses an emotion engine that recognizes user emotions and customizes the system's behavior, allowing users to obtain optimal analysis results based on their emotions.

[0535] The specific system configuration uses the following hardware and software:

[0536] User Interface (UI): A web-based interface implemented using HTML and JavaScript.

[0537] Emotion Engine: A software module that uses natural language processing (NLP) and facial expression recognition technologies and is implemented in Python.

[0538] Data Collection Engine: Includes Python scripts that collect data from enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[0539] Data integrity check module: A software module that uses Python and R to standardize data formats, complete missing values, and remove duplicate data.

[0540] Data analysis module: A software module that performs trend analysis of sales data and graphs sales data by category, using Python's pandas and matplotlib libraries.

[0541] Report generation module: Software that generates reports in PDF, Excel, or PNG format based on analysis results, using Python's ReportLab.

[0542] (Example)

[0543] The user enters text into the system's UI, saying, "Please aggregate sales data from January 2023 to June 2023 and graph it by category." If the user indicates an emotion, for example, "I'm in a hurry," the emotion engine analyzes this information and switches the operation of the entire system to "high-speed mode."

[0544] The server quickly and efficiently launches the data collection engine based on the analysis conditions and emotion recognition results. It collects the necessary data from the company's core systems and local Excel files, standardizes the format, and imputes missing values. After verifying data integrity, the data analysis module graphs monthly sales trends and sales data by category.

[0545] The server generates a visually easy-to-understand PDF report based on the analysis results and provides it to the user. If the user reviews the report and requests a more detailed analysis, they can enter their feedback into the system, which will use the emotion engine to refine the next analysis process.

[0546] Through the above process, this big data aggregation system can flexibly and efficiently meet user requirements and support more accurate decision-making.

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

[0548] Step 1:

[0549] The user inputs analysis conditions in text format through the system's UI.

[0550] Specifically, the user enters "Please aggregate sales data from January 2023 to June 2023 and graph it by category" and clicks the submit button.

[0551] Input: Analysis conditions (text format)

[0552] Output: Analysis conditions are sent to the server

[0553] Step 2:

[0554] The server receives the user's input and recognizes the user's emotions using an emotion engine.

[0555] Specifically, it uses Natural Language Processing (NLP) technology to analyze text and determine whether the user is in a hurry.

[0556] Input: Text data of analysis conditions

[0557] Output: User emotion data (e.g., hurry)

[0558] Step 3:

[0559] The server starts the data collection engine based on the determination results of the emotion engine and the analysis conditions.

[0560] Determine which data sources to acquire to complete the overall data collection process most efficiently. At this stage, develop a plan to collect data from your company's core systems, cloud storage, local electronic spreadsheets, etc.

[0561] Input: Emotion data, analysis conditions

[0562] Output: Execution plan for data collection

[0563] Step 4:

[0564] The server collects the data using a data collection engine.

[0565] Specifically, it sends API requests to the sales database and retrieves necessary data from cloud storage and the local file system.

[0566] Input: Execution plan for data collection

[0567] Output: Raw data collected (e.g. sales data)

[0568] Step 5:

[0569] The server checks the consistency of the collected data and performs correction processing.

[0570] Specifically, data cleaning processes are carried out, such as standardizing data formats, filling in missing values, and deleting duplicate data.

[0571] Input: Raw data collected

[0572] Output: Consistency checked and corrected data

[0573] Step 6:

[0574] The server performs analysis of the corrected data using a data analysis module.

[0575] Here, sales data trend analysis and category sales data graphing are performed using Python's pandas and matplotlib libraries.

[0576] Input: Corrected data

[0577] Output: Analysis results (e.g., sales graph by category)

[0578] Step 7:

[0579] The server generates a report based on the analysis results.

[0580] Specifically, the analysis results are compiled into a report in a visually easy-to-understand format (PDF, Excel, PNG, etc.), and a library such as ReportLab is used to generate PDF reports.

[0581] Input: Analysis results

[0582] Output: Report (e.g. PDF format)

[0583] Step 8:

[0584] The user reviews the generated report and provides any necessary feedback to the system.

[0585] For example, you can enter a request such as "I want more detailed analysis." This feedback will be used to improve the system as a whole.

[0586] Input: Feedback text data

[0587] Output: Feedback is sent to the server

[0588] Step 9:

[0589] The server receives the feedback and analyzes it using an emotion engine to further optimize the system's behavior and future analysis processes.

[0590] Based on the feedback, we will adjust future data analysis policies and algorithms.

[0591] Input: Feedback text data

[0592] Output: Adjusted system operating configuration

[0593] (Application example 2)

[0594] 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."

[0595] Conventional data collection and analysis systems mechanically process data and present results without considering user emotions, making it difficult to respond flexibly based on user intentions and emotions. Displaying personalized advertisements is also difficult, creating a need for improved user experience. Therefore, the present invention aims to improve the efficiency and quality of data analysis and advertisement display by recognizing user emotions and customizing system behavior based on those emotions.

[0596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0597] In this invention, the server includes means for a user to input analysis conditions in text format, means for automatically collecting data from a data storage system, means for checking and correcting the consistency of the collected data, means for analyzing the data whose consistency has been checked, means for generating a report based on the analysis results, means for recognizing the user's emotions and customizing the operation of the system, and means for generating and displaying personalized advertisements based on the emotions. This allows the system to operate flexibly based on the user's emotions and intentions, making it possible to display more effective and personalized advertisements.

[0598] "Means for users to input analytical conditions in text format" refers to an interface that allows users to input analytical conditions and parameters using text.

[0599] "Means for automatically collecting data from a data storage system" refers to a function for automatically obtaining required data from a predefined data source.

[0600] "Means for verifying and correcting the consistency of collected data" refers to a function that checks whether collected data is accurate and consistent, and makes corrections or amendments as necessary.

[0601] "Means for analyzing data whose integrity has been checked" refers to a function for executing a specified analysis process on data whose integrity has been checked.

[0602] "Means for generating a report based on the analysis results" refers to a function that compiles the results of the analysis and outputs them as a report for the user.

[0603] "Means for recognizing user emotions and customizing system behavior" refers to the ability to detect the user's emotional state and adjust the system's behavior and output based on that information.

[0604] "Means for generating and displaying personalized advertisements based on emotions" refers to a function that reflects the user's emotional data to create and display advertisements that are optimally tailored to each individual user.

[0605] The system for implementing the present invention is configured using a server, a user terminal, and an emotion recognition engine. Each step and the necessary hardware and software will be described in detail below.

[0606] The server provides a means for users to input analysis conditions in text format. Through this interface, users input the period and items they want to analyze. For example, a condition might be entered such as, "Please aggregate sales data by category from January 2023 to June 2023."

[0607] The server has a means for automatically collecting data from data storage systems, such as corporate databases, cloud storage, and local electronic spreadsheet files. The data collection engine automatically collects the required data from these data sources.

[0608] The emotion recognition engine detects emotions from user input and facial expressions. The server uses this information to customize system behavior and filter and analyze data according to the user's psychological state. The emotion engine uses natural language processing technology and facial expression recognition software.

[0609] The integrity of the collected data is checked and corrected as necessary. This includes standardizing the data format, filling in missing values, and deleting and merging duplicate data. The Pandas library, which excels at manipulating data frames, is used for processing.

[0610] The data, once validated, is then analyzed according to a specified analysis process, which includes generating data summaries, creating graphs, and analyzing trends and correlations. The Scikit-learn and Matplotlib libraries are used as analytical tools.

[0611] Based on the analysis results, a report tailored to each user's individual feelings is generated, including adjusting the tone and level of difficulty of the data and outputting it in formats such as PDF, Excel, and PNG. ReportLab, for example, is used as a report generation tool.

[0612] Furthermore, it generates and displays personalized ads based on user emotions and data. This includes a function where the ad display engine takes into account user emotions and past behavioral data to select and display appropriate ads. The timing of ad display is controlled using HTML5 and JavaScript.

[0613] Specific examples

[0614] For example, when a user logs in using a smartphone and enters analysis criteria, a camera detects their facial expressions. If the user is recognized as "happy," entertainment-related advertisements are selected and displayed. At the same time, sales data is automatically collected from the database based on the user-specified period, appropriate trend analysis is performed, and easy-to-understand reports are generated.

[0615] Prompt Sentence Examples

[0616] Develop a system that analyzes a user's facial expressions in real time and displays the most appropriate advertisement based on their emotion. If the user is "Happy," it will display an entertaining advertisement, and if the user is "Sad," it will display an uplifting advertisement. Use OpenCV to capture the user's face with a camera, implement an emotion recognition algorithm, and select the appropriate advertisement from the advertisement database based on the results.

[0617] This allows for appropriate and efficient data analysis and advertising presentation, taking into account the user's psychological state.

[0618] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0619] Step 1:

[0620] The user enters the analysis conditions. The user enters the analysis conditions in text format (e.g., "Please summarize sales data from January 2023 to June 2023 by category") via the UI on their smartphone or PC. This input is then sent to the server.

[0621] Step 2:

[0622] The server performs emotion recognition. The server uses an emotion recognition engine to analyze the user's emotions based on the text entered by the user and the facial expressions captured by the smartphone camera. The analysis results (e.g., "Happy" or "Sad") are used for subsequent data collection and customization processing.

[0623] Step 3:

[0624] The server starts the data collection engine. Based on the emotion recognition results and the user's input conditions, the server collects the necessary data from the appropriate data source (e.g., core system, database, cloud storage, local electronic spreadsheet file). The data collection engine automatically acquires data according to the specified period and items.

[0625] Step 4:

[0626] The server checks and corrects the consistency of the collected data. The server unifies the format of the collected data, completes missing values, and removes duplicate data. Specifically, it uses the Pandas library to operate on data frames and checks consistency. The data input is the collected raw data, and the output is data whose consistency has been checked.

[0627] Step 5:

[0628] The server performs data analysis. Based on the data whose integrity has been confirmed, the server performs the specified analysis process (summary generation, graph creation, trend analysis, correlation analysis). For example, the analysis is performed using the Scikit-learn library or Matplotlib library. The input is the data whose integrity has been confirmed, and the output is the analysis results.

[0629] Step 6:

[0630] The server generates and provides reports. The server generates reports for users based on the results of data analysis. Based on the results of the emotion recognition engine, the tone and difficulty of the report can be adjusted and output in the format specified by the user (PDF, Excel, PNG). Specifically, the PDF report is generated using ReportLab. The input is the analysis results, and the output is a customized report.

[0631] Step 7:

[0632] The server generates and displays personalized ads. Based on the user's emotions and past behavioral data, the server generates the optimal ad and displays it on the smartphone or PC. HTML5 and JavaScript are used to control the timing of ad display. The input is emotional data and past behavioral data, and the output is a personalized ad.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] [Third embodiment]

[0637] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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).

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] 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.

[0648] 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."

[0649] ---

[0650] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows:

[0651] 1. User Input

[0652] Users enter analysis conditions in text format through the system's user interface (UI). For example, they might enter a condition such as, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0653] 2. Data Collection

[0654] The server analyzes the conditions entered by the user and activates the data collection engine, which accesses the specified data sources (corporate core systems, databases, cloud storage, local electronic spreadsheet files, etc.) and automatically collects the required data. For example, it retrieves relevant sales data from a sales database and also reads related data from a locally stored Excel file.

[0655] 3. Data integrity check

[0656] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[0657] 4. Data Analysis

[0658] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This process includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden increases in sales in specific categories. It also analyzes the correlation between sales data and advertising expenditure data and creates a report based on the results.

[0659] 5. Report generation and provision

[0660] The server generates a report based on the analysis results. The report includes a data summary, graphs, trend analysis results, and correlation comments. The report is output in a format specified by the user (PDF, Excel, PNG, etc.) and provided to the user via a dashboard. For example, the server can save the generated report in PDF format, and the user can download it from the dashboard to use as meeting material.

[0661] ---

[0662] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

[0663] The processing flow will be explained below.

[0664] Step 1: User Input

[0665] Users use the system's interface to enter analysis conditions in text format, such as "aggregate sales data from January 2023 to June 2023 and graph it by category." In addition, users can specify specific time periods and aggregation items.

[0666] Step 2: Condition analysis

[0667] The server analyzes the text conditions entered by the user and determines the type, period, and format of data to be collected. For example, the server generates specific analysis conditions such as "sales data," "January to June 2023," and "by category."

[0668] Step 3: Start the data collection engine

[0669] The server runs a data collection engine and accesses multiple data storage systems based on analysis criteria, including corporate systems, databases, cloud storage, and local electronic spreadsheets.

[0670] Step 4: Data collection

[0671] The server automatically collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. The collected data is temporarily stored on the server.

[0672] Step 5: Data integrity check

[0673] The server then performs a process to check the integrity of the collected data. This process involves standardizing the data format, filling in missing values, and deleting and merging duplicate data. For example, it standardizes different date formats (YYYY / MM / DD vs MM-DD-YYYY) and merges data with the same product name.

[0674] Step 6: Data analysis

[0675] The server then performs a specified analysis process on the data after verifying its integrity, which may include generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, the server may analyze monthly sales trends to detect sudden sales spikes in a particular category.

[0676] Step 7: Generate reports

[0677] The server generates a report based on the data analysis results. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.).

[0678] Step 8: Reporting

[0679] Users can download the generated report from the system dashboard. For example, users can access the dashboard and click the download link for the completed report to obtain the report in PDF format.

[0680] Example 1

[0681] 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."

[0682] Modern companies require systems that can effectively collect and analyze large amounts of data to support rapid and accurate decision-making. However, conventional systems require a great deal of effort to collect data and verify consistency, and are often only available to users with specific expertise. Furthermore, collecting data from multiple sources, unifying data in different formats, and creating visual reports of analysis results are all time-consuming. Furthermore, the lack of functionality for outputting reports in various formats creates a problem of reduced user convenience.

[0683] 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.

[0684] In this invention, the server includes a means for a user to input analytical conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, a means for generating a report based on the analysis results, and a means for outputting the report in a format specified by the user. This allows users without specialized knowledge to easily perform complex data collection and analysis, reduces the burden of reporting work, and enables quick and accurate decision-making based on data.

[0685] A "user" is a person who operates the system to input analytical conditions and instructs the output of a report.

[0686] "Text format" refers to the format of a string of characters that allows a user to input analytical conditions and instructions to the system.

[0687] "Analysis conditions" are information for specifying the period and items to be collected and analyzed.

[0688] "Data storage system" is a general term for systems that store data, such as a company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[0689] "Data collection" is the act of obtaining necessary data from designated data sources.

[0690] "Consistency check" is the process of creating a consistent data set by standardizing the format of collected data, filling in missing values, and deleting and integrating duplicate data.

[0691] "Data analysis" refers to the process of generating summaries, creating graphs, conducting trend analysis, and performing correlation analysis using data whose consistency has been confirmed.

[0692] "Report generation" is the act of creating a visually easy-to-understand report based on the results of data analysis.

[0693] "Report output" is the process of saving and providing the generated report in a format specified by the user, such as PDF, Excel, or PNG.

[0694] "Format" refers to the file type and data representation method specified for report output.

[0695] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows.

[0696] Users access the system's user interface (UI) through a web browser and enter analysis conditions in text format. This UI is built using HTML and JavaScript, and the entered conditions are sent to the server as an HTTP request. For example, a user might enter something like, "Please aggregate sales data from January 2023 to June 2023 and graph it by category."

[0697] The server analyzes the received request and launches the data collection engine. Implemented in Python or Java, the data collection engine accesses the company's core systems, cloud storage, and local electronic spreadsheet files (e.g., MySQL databases, AWS S3 buckets, Excel files, etc.) to collect the necessary data. For example, it retrieves sales data from January 2023 to June 2023 from a MySQL database and then reads related data from a locally stored Excel file.

[0698] The server performs preprocessing to check the integrity of the collected data. This includes standardizing data formats, filling in missing values, and deleting and merging duplicate data. For example, it converts date data stored in different formats into a standard format (YYYY-MM-DD) and merges duplicate product data into one.

[0699] Based on the data whose integrity has been confirmed, the server executes the specified analysis process. For data analysis, Python libraries such as Pandas and NumPy are used to analyze monthly sales trends and detect sudden increases in sales in specific categories. The server also calculates correlations between sales data and advertising expenditure data and analyzes the results.

[0700] The analysis results are compiled into a visually easy-to-read report during the report generation process. The server creates graphs using Matplotlib and Seaborn, and generates reports in PDF format using ReportLab. The reports include data summaries, graphs, trend analysis results, and correlation-based comments. The generated reports are uploaded to a dashboard and can be downloaded by users.

[0701] As a concrete example, consider the case where the user enters the following prompt sentence:

[0702] Example prompt sentence:

[0703] Please compile sales data from January 2023 to June 2023 and graph it by category. Also, please analyze the correlation with advertising expenses.

[0704] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

[0705] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0706] Step 1:

[0707] The user accesses the system's user interface (UI) through a web browser and enters the analysis conditions in text format. Specifically, the user enters "Aggregate sales data from January 2023 to June 2023 and graph it by category" into the UI text box and clicks the send button. This operation sends the analysis conditions to the server as an HTTP request. The input is the analysis conditions in text format, and the output is an HTTP request to the server.

[0708] Step 2:

[0709] The server analyzes the received HTTP request and starts the data collection engine. Specifically, the server extracts the conditions entered by the user from the request body and sets specific parameters for data collection based on them. For example, it analyzes the period and aggregation items and passes them to the data collection engine. The input is the analysis conditions in the HTTP request, and the output is the set data collection parameters.

[0710] Step 3:

[0711] The server collects the required data from the specified data source through the data collection engine. Specifically, the server connects to the MySQL database and issues a query such as "SELECT FROM sales WHERE date BETWEEN '2023-01-01' AND '2023-06-30'" to retrieve sales data. It also reads corresponding sales data from a local electronic spreadsheet file. The input is the data collection parameters, and the output is the collected raw data.

[0712] Step 4:

[0713] The server checks the integrity of the collected data and performs necessary preprocessing. Specifically, the server unifies different date formats (e.g., YYYY-MM-DD), removes duplicate data, and imputes missing values ​​with the mean or median. The input is the collected raw data, and the output is clean data that has been checked for integrity.

[0714] Step 5:

[0715] The server then executes the specified analysis process using the data whose integrity has been confirmed. Specifically, the server creates a data frame using the Pandas library and performs grouping and aggregation processes. It also uses Matplotlib to graph monthly sales trends and calculate the correlation between sales data and advertising expense data. The input is clean data, and the output is the analysis results.

[0716] Step 6:

[0717] The server generates a report based on the analysis results. Specifically, the server uses ReportLab to create a PDF report and embeds the generated graphs and analysis results in the report. The input is the analysis results, and the output is a PDF report.

[0718] Step 7:

[0719] The server provides the generated report to the user. Specifically, the server uploads the PDF report to the dashboard and provides a download link to the user. The user accesses the dashboard and downloads the PDF report for use. The input is the PDF report, and the output is a report link that the user can download.

[0720] (Application example 1)

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

[0722] Currently, corporate data analysis work is extremely complicated, and in many cases, analysts with specialized knowledge must manually collect data, check its consistency, and perform analysis. This process is time-consuming, labor-intensive, and inefficient. Many businesses also require real-time data analysis, but current systems make this difficult to achieve. In particular, sales representatives and customer support staff need an environment where they can view data in real time on their smartphones so they can quickly take action. A system that can solve this problem is needed.

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

[0724] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating a report based on the analysis results and displaying it on a smartphone application. This enables sales representatives and customer support to check sales data in real time and quickly take countermeasures.

[0725] "User" refers to a person or organization that operates the system, inputs analytical conditions, and checks data collection and analytical results.

[0726] "Text format" refers to the input method for analysis conditions and search queries expressed as character strings.

[0727] "Analysis conditions" are the standards and parameters for data collection and analysis specified by the user, including the period and aggregation items.

[0728] A "data storage system" is a system that stores data such as a company's core systems, databases, cloud storage, and local files.

[0729] "Means for automatically collecting data" refers to a system that automatically collects necessary data from designated data sources using a program.

[0730] "Means for checking and correcting data consistency" refers to a system for standardizing the format of collected data, completing missing values, and deleting and integrating duplicate data.

[0731] "Means for analyzing data whose consistency has been confirmed" refers to a system for conducting trend analysis and correlation analysis based on data whose consistency has been confirmed.

[0732] "Means for generating reports and displaying them on a smartphone application" refers to a mechanism for creating reports including graphs and charts based on the analysis results, allowing users to view them on a smartphone application.

[0733] This invention provides a system that allows users to input analytical conditions in text format, automatically collects data from multiple data storage systems, checks the consistency of the data, analyzes it, and finally generates a report that is displayed on a smartphone application.

[0734] The server receives analysis conditions in text format from the user through a user interface. This user interface includes fields for entering detailed parameters such as the analysis period and aggregation items. For example, a user might enter a condition such as "Aggregate sales data from January 2023 to June 2023 and graph it by category."

[0735] The server then launches a data collection engine to automatically collect the required data from designated data sources, such as enterprise systems, databases, cloud storage, local spreadsheets, etc. The collected data is often stored in different formats, so the server must convert it into a unified format.

[0736] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[0737] Once the integrity of the data has been confirmed, it is analyzed according to the specified analysis process. The server generates summaries, creates graphs, performs trend analysis, and performs correlation analysis. For example, it can analyze monthly sales trends to detect sudden increases in sales in a particular category. It can also analyze correlations between sales data and advertising spend data and create reports based on the results.

[0738] Finally, the server generates a report based on the analysis results and displays it on the smartphone application. This report includes a data summary, graphs, trend analysis results, and correlation comments. Users receive the report in the specified format (e.g., PDF, Excel, PNG, etc.) and can view it on the dashboard through the smartphone application.

[0739] Hardware and software used

[0740] The server uses the following hardware and software:

[0741] Hardware: Server computers, cloud storage, and users' smartphones

[0742] Software: Flask (web application framework), pandas (data analysis library), matplotlib (graph generation library)

[0743] Specific examples

[0744] For example, a sales representative at an online retailer might want to analyze data based on the following criteria:

[0745] "Analyze sales data by category from January 2023 to June 2023 and chart monthly sales trends."

[0746] Once these conditions are entered through the user interface, the server automatically collects sales data for the specified period from databases and cloud storage, checks the data for consistency, and then analyzes it.The final report is displayed on a smartphone application, allowing sales representatives to check the results in real time.

[0747] Prompt Sentence Examples

[0748] Period: January 2023 to June 2023

[0749] Aggregate item: Sales data by category

[0750] Expected output: Chart of monthly sales trends

[0751] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0752] Step 1:

[0753] The user inputs the analysis conditions in text format.

[0754] Input: Analysis period, aggregation items, specific analysis conditions (e.g., "Aggregate sales data from January 2023 to June 2023 and graph it by category").

[0755] How it works: You enter a condition in text format in an input field in the user interface and send it to the server.

[0756] Output: The analysis conditions are sent to the server.

[0757] Step 2:

[0758] The server analyzes the analysis conditions in text format received from the user.

[0759] Input: Analysis conditions entered by the user.

[0760] Operation: The server analyzes the text of the analysis conditions and extracts parameters such as the period for collecting data and the items to be aggregated.

[0761] Output: Parsed parameters (analysis period, aggregation items, etc.).

[0762] Step 3:

[0763] The server launches a data collection engine to automatically collect data from the specified data sources.

[0764] Input: Parsed parameters (analysis period, aggregation items, etc.).

[0765] How it works: The data collection engine starts and collects the relevant data from the company's core systems, databases, cloud storage, local electronic spreadsheets, etc.

[0766] Output: The raw data collected.

[0767] Step 4:

[0768] The server checks and corrects the integrity of the collected data.

[0769] Input: Raw data collected.

[0770] Operation: The server standardizes data formats, fills in missing values, and removes and consolidates duplicate data.

[0771] Output: Data with integrity checked.

[0772] Step 5:

[0773] The server performs analysis based on the data whose integrity has been confirmed.

[0774] Input: Data whose integrity has been checked.

[0775] Action: The server performs the specified analysis operations such as summary generation, graph creation, trend analysis, correlation analysis, etc.

[0776] Output: Analysis results.

[0777] Step 6:

[0778] The server generates a report based on the analysis results and displays it on a smartphone application.

[0779] Input: Analysis results.

[0780] Operation: The server creates a report containing graphs and charts based on the analysis results and sends it to a smartphone application. The user can view the report through the application.

[0781] Output: The report displayed on the user's smartphone.

[0782] 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.

[0783] ---

[0784] The big data aggregation system of the present invention not only automatically collects data from multiple data storage systems based on user input, analyzes the data, and generates reports, but also includes an emotion engine that recognizes user emotions and customizes the system's operation. Detailed embodiments are described below.

[0785] 1. User Input

[0786] Users enter analysis conditions in text format through the system's user interface (UI). For example, they can enter a condition such as "aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0787] 2. Emotion recognition

[0788] The server recognizes the user's emotion from the user's input using an emotion engine, which uses natural language processing and facial expression recognition technologies to determine the user's emotion (e.g., joy, sadness, anger, surprise, fear, etc.).

[0789] 3. Start the data collection engine

[0790] Based on the emotion engine's judgment results, the server activates the data collection engine and collects data from appropriate data sources based on the analysis conditions, including the company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[0791] 4. Data Collection

[0792] The server collects and temporarily stores the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It also filters the collected data based on the emotion engine.

[0793] 5. Data integrity check

[0794] The server performs processes to check the integrity of the collected data, including standardizing data formats, filling in missing values, and removing and merging duplicate data. It is also possible to adjust the priority of filtering and correction in this process based on the results of the emotion engine.

[0795] 6. Data Analysis

[0796] The server then performs the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Furthermore, it customizes the content and presentation of reports based on the results of the emotion engine.

[0797] 7. Report Generation and Delivery

[0798] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. It is output in the format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report are adjusted based on the results of the emotion engine. This allows users to receive a report that is easier to understand and tailored to their purpose.

[0799] 8. Feedback and Further Customization

[0800] Users can review the generated reports and provide further feedback, which the emotion engine analyzes in real time to further customize the system's behavior and report content.

[0801] ---

[0802] As described above, this invention achieves flexible and efficient data analysis that takes user emotions into consideration by integrating an emotion engine into a conventional data collection and analysis system, thereby reducing the burden on users and supporting more accurate decision-making.

[0803] The processing flow will be explained below.

[0804] Step 1: User Input

[0805] Users enter analysis conditions in text format using the system's user interface (UI). For example, they might enter, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0806] Step 2: Emotion Recognition

[0807] The server analyzes the user's input and behavior on the interface (e.g., typing speed, frequency of typos, etc.) and uses an emotion engine to recognize the user's emotions. For example, if the user types quickly, the emotion engine determines that the user is impatient.

[0808] Step 3: Condition analysis and customization

[0809] The server analyzes the conditions entered by the user and determines the type, period, and format of data to be collected. Furthermore, it customizes the analysis conditions and the display method of the results based on the results of the emotion engine. For example, if the user is in a hurry, the system adjusts to present important analysis results earlier.

[0810] Step 4: Start the data collection engine

[0811] The server runs the data collection engine and accesses data sources based on the analysis criteria, including enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[0812] Step 5: Data collection

[0813] The server collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It may also adjust the priority and speed of data collection based on the results of the emotion engine.

[0814] Step 6: Data integrity check

[0815] The server checks the integrity of the collected data, standardizes the data format, fills in missing values, and removes and merges duplicate data. Based on the results of the emotion engine, it adjusts the speed of this process and the strictness of the filtering.

[0816] Step 7: Data analysis

[0817] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Based on the results of the sentiment engine, it customizes the display and order of the analysis results.

[0818] Step 8: Generate reports

[0819] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report reflect the results of the emotion engine.

[0820] Step 9: Reporting

[0821] Users can download the generated report from the system's dashboard. For example, a user can access the dashboard and click the download link for the completed report to obtain a PDF version of the report. The report also includes feedback based on the user's emotional state.

[0822] Step 10: Feedback and customization

[0823] The user can review the generated report and provide further feedback to the system, for example, requesting additional analysis or detailed explanations of specific items. The server analyzes the user's feedback and the results of the emotion engine to further customize the system's behavior and report content for future use.

[0824] Example 2

[0825] 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."

[0826] Conventional big data aggregation systems do not consider user sentiment when verifying the integrity of collected data or analyzing it, which can lead to analysis results that do not match user expectations or requirements. Furthermore, handling large amounts of data places a heavy burden on users, preventing them from effectively utilizing the results of data analysis. Furthermore, there is a need for a flexible system that can incorporate user feedback in the processes of rapid data collection, analysis, and report generation.

[0827] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0828] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for recognizing user emotions and customizing system operation, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating reports based on the analysis results, thereby enabling flexible and efficient data analysis and report generation that takes user emotions into consideration.

[0829] The "means for the user to input analytical conditions in text format" refers to a device or software for inputting text data specified by the user into the system through an interface.

[0830] "Means for automatically collecting data from data storage systems" refers to devices or software that automatically retrieve the required data from different data sources.

[0831] "Means for recognizing user emotions and customizing system behavior" refers to a device or software that analyzes user emotions and adjusts system behavior and interface based on the results.

[0832] "Means for verifying and correcting the consistency of collected data" refers to devices or software that verify the format and content of extracted data and make appropriate corrections to ensure consistency.

[0833] The "means for analyzing data whose integrity has been confirmed" refers to a device or software for performing a specified analysis based on data whose integrity has been confirmed.

[0834] A "means for generating a report based on the analysis results" is a device or software that organizes the results of the data analysis and creates a visual or written report to provide to the user.

[0835] "Local spreadsheet files" are files created by spreadsheet software that are stored on a user's individual device or local storage.

[0836] The big data aggregation system of the present invention includes a process for automatically collecting data from multiple data storage systems based on user input and generating reports from the analysis results. In addition, it uses an emotion engine that recognizes user emotions and customizes the system's behavior, allowing users to obtain optimal analysis results based on their emotions.

[0837] The specific system configuration uses the following hardware and software:

[0838] User Interface (UI): A web-based interface implemented using HTML and JavaScript.

[0839] Emotion Engine: A software module that uses natural language processing (NLP) and facial expression recognition technologies and is implemented in Python.

[0840] Data Collection Engine: Includes Python scripts that collect data from enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[0841] Data integrity check module: A software module that uses Python and R to standardize data formats, complete missing values, and remove duplicate data.

[0842] Data analysis module: A software module that performs trend analysis of sales data and graphs sales data by category, using Python's pandas and matplotlib libraries.

[0843] Report generation module: Software that generates reports in PDF, Excel, or PNG format based on analysis results, using Python's ReportLab.

[0844] (Example)

[0845] The user enters text into the system's UI, saying, "Please aggregate sales data from January 2023 to June 2023 and graph it by category." If the user indicates an emotion, for example, "I'm in a hurry," the emotion engine analyzes this information and switches the operation of the entire system to "high-speed mode."

[0846] The server quickly and efficiently launches the data collection engine based on the analysis conditions and emotion recognition results. It collects the necessary data from the company's core systems and local Excel files, standardizes the format, and imputes missing values. After verifying data integrity, the data analysis module graphs monthly sales trends and sales data by category.

[0847] The server generates a visually easy-to-understand PDF report based on the analysis results and provides it to the user. If the user reviews the report and requests a more detailed analysis, they can enter their feedback into the system, which will use the emotion engine to refine the next analysis process.

[0848] Through the above process, this big data aggregation system can flexibly and efficiently meet user requirements and support more accurate decision-making.

[0849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0850] Step 1:

[0851] The user inputs analysis conditions in text format through the system's UI.

[0852] Specifically, the user enters "Please aggregate sales data from January 2023 to June 2023 and graph it by category" and clicks the submit button.

[0853] Input: Analysis conditions (text format)

[0854] Output: Analysis conditions are sent to the server

[0855] Step 2:

[0856] The server receives the user's input and recognizes the user's emotions using an emotion engine.

[0857] Specifically, it uses Natural Language Processing (NLP) technology to analyze text and determine whether the user is in a hurry.

[0858] Input: Text data of analysis conditions

[0859] Output: User emotion data (e.g., hurry)

[0860] Step 3:

[0861] The server starts the data collection engine based on the determination results of the emotion engine and the analysis conditions.

[0862] Determine which data sources to acquire to complete the overall data collection process most efficiently. At this stage, develop a plan to collect data from your company's core systems, cloud storage, local electronic spreadsheets, etc.

[0863] Input: Emotion data, analysis conditions

[0864] Output: Execution plan for data collection

[0865] Step 4:

[0866] The server collects the data using a data collection engine.

[0867] Specifically, it sends API requests to the sales database and retrieves necessary data from cloud storage and the local file system.

[0868] Input: Execution plan for data collection

[0869] Output: Raw data collected (e.g. sales data)

[0870] Step 5:

[0871] The server checks the consistency of the collected data and performs correction processing.

[0872] Specifically, data cleaning processes are carried out, such as standardizing data formats, filling in missing values, and deleting duplicate data.

[0873] Input: Raw data collected

[0874] Output: Consistency checked and corrected data

[0875] Step 6:

[0876] The server performs analysis of the corrected data using a data analysis module.

[0877] Here, sales data trend analysis and category sales data graphing are performed using Python's pandas and matplotlib libraries.

[0878] Input: Corrected data

[0879] Output: Analysis results (e.g., sales graph by category)

[0880] Step 7:

[0881] The server generates a report based on the analysis results.

[0882] Specifically, the analysis results are compiled into a report in a visually easy-to-understand format (PDF, Excel, PNG, etc.), and a library such as ReportLab is used to generate PDF reports.

[0883] Input: Analysis results

[0884] Output: Report (e.g. PDF format)

[0885] Step 8:

[0886] The user reviews the generated report and provides any necessary feedback to the system.

[0887] For example, you can enter a request such as "I want more detailed analysis." This feedback will be used to improve the system as a whole.

[0888] Input: Feedback text data

[0889] Output: Feedback is sent to the server

[0890] Step 9:

[0891] The server receives the feedback and analyzes it using an emotion engine to further optimize the system's behavior and future analysis processes.

[0892] Based on the feedback, we will adjust future data analysis policies and algorithms.

[0893] Input: Feedback text data

[0894] Output: Adjusted system operating configuration

[0895] (Application example 2)

[0896] 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."

[0897] Conventional data collection and analysis systems mechanically process data and present results without considering user emotions, making it difficult to respond flexibly based on user intentions and emotions. Displaying personalized advertisements is also difficult, creating a need for improved user experience. Therefore, the present invention aims to improve the efficiency and quality of data analysis and advertisement display by recognizing user emotions and customizing system behavior based on those emotions.

[0898] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0899] In this invention, the server includes means for a user to input analysis conditions in text format, means for automatically collecting data from a data storage system, means for checking and correcting the consistency of the collected data, means for analyzing the data whose consistency has been checked, means for generating a report based on the analysis results, means for recognizing the user's emotions and customizing the operation of the system, and means for generating and displaying personalized advertisements based on the emotions. This allows the system to operate flexibly based on the user's emotions and intentions, making it possible to display more effective and personalized advertisements.

[0900] "Means for users to input analytical conditions in text format" refers to an interface that allows users to input analytical conditions and parameters using text.

[0901] "Means for automatically collecting data from a data storage system" refers to a function for automatically obtaining required data from a predefined data source.

[0902] "Means for verifying and correcting the consistency of collected data" refers to a function that checks whether collected data is accurate and consistent, and makes corrections or amendments as necessary.

[0903] "Means for analyzing data whose integrity has been checked" refers to a function for executing a specified analysis process on data whose integrity has been checked.

[0904] "Means for generating a report based on the analysis results" refers to a function that compiles the results of the analysis and outputs them as a report for the user.

[0905] "Means for recognizing user emotions and customizing system behavior" refers to the ability to detect the user's emotional state and adjust the system's behavior and output based on that information.

[0906] "Means for generating and displaying personalized advertisements based on emotions" refers to a function that reflects the user's emotional data to create and display advertisements that are optimally tailored to each individual user.

[0907] The system for implementing the present invention is configured using a server, a user terminal, and an emotion recognition engine. Each step and the necessary hardware and software will be described in detail below.

[0908] The server provides a means for users to input analysis conditions in text format. Through this interface, users input the period and items they want to analyze. For example, a condition might be entered such as, "Please aggregate sales data by category from January 2023 to June 2023."

[0909] The server has a means for automatically collecting data from data storage systems, such as corporate databases, cloud storage, and local electronic spreadsheet files. The data collection engine automatically collects the required data from these data sources.

[0910] The emotion recognition engine detects emotions from user input and facial expressions. The server uses this information to customize system behavior and filter and analyze data according to the user's psychological state. The emotion engine uses natural language processing technology and facial expression recognition software.

[0911] The integrity of the collected data is checked and corrected as necessary. This includes standardizing the data format, filling in missing values, and deleting and merging duplicate data. The Pandas library, which excels at manipulating data frames, is used for processing.

[0912] The data, once validated, is then analyzed according to a specified analysis process, which includes generating data summaries, creating graphs, and analyzing trends and correlations. The Scikit-learn and Matplotlib libraries are used as analytical tools.

[0913] Based on the analysis results, a report tailored to each user's individual feelings is generated, including adjusting the tone and level of difficulty of the data and outputting it in formats such as PDF, Excel, and PNG. ReportLab, for example, is used as a report generation tool.

[0914] Furthermore, it generates and displays personalized ads based on user emotions and data. This includes a function where the ad display engine takes into account user emotions and past behavioral data to select and display appropriate ads. The timing of ad display is controlled using HTML5 and JavaScript.

[0915] Specific examples

[0916] For example, when a user logs in using a smartphone and enters analysis criteria, a camera detects their facial expressions. If the user is recognized as "happy," entertainment-related advertisements are selected and displayed. At the same time, sales data is automatically collected from the database based on the user-specified period, appropriate trend analysis is performed, and easy-to-understand reports are generated.

[0917] Prompt Sentence Examples

[0918] Develop a system that analyzes a user's facial expressions in real time and displays the most appropriate advertisement based on their emotion. If the user is "Happy," it will display an entertaining advertisement, and if the user is "Sad," it will display an uplifting advertisement. Use OpenCV to capture the user's face with a camera, implement an emotion recognition algorithm, and select the appropriate advertisement from the advertisement database based on the results.

[0919] This allows for appropriate and efficient data analysis and advertising presentation, taking into account the user's psychological state.

[0920] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0921] Step 1:

[0922] The user enters the analysis conditions. The user enters the analysis conditions in text format (e.g., "Please summarize sales data from January 2023 to June 2023 by category") via the UI on their smartphone or PC. This input is then sent to the server.

[0923] Step 2:

[0924] The server performs emotion recognition. The server uses an emotion recognition engine to analyze the user's emotions based on the text entered by the user and the facial expressions captured by the smartphone camera. The analysis results (e.g., "Happy" or "Sad") are used for subsequent data collection and customization processing.

[0925] Step 3:

[0926] The server starts the data collection engine. Based on the emotion recognition results and the user's input conditions, the server collects the necessary data from the appropriate data source (e.g., core system, database, cloud storage, local electronic spreadsheet file). The data collection engine automatically acquires data according to the specified period and items.

[0927] Step 4:

[0928] The server checks and corrects the consistency of the collected data. The server unifies the format of the collected data, completes missing values, and removes duplicate data. Specifically, it uses the Pandas library to operate on data frames and checks consistency. The data input is the collected raw data, and the output is data whose consistency has been checked.

[0929] Step 5:

[0930] The server performs data analysis. Based on the data whose integrity has been confirmed, the server performs the specified analysis process (summary generation, graph creation, trend analysis, correlation analysis). For example, the analysis is performed using the Scikit-learn library or Matplotlib library. The input is the data whose integrity has been confirmed, and the output is the analysis results.

[0931] Step 6:

[0932] The server generates and provides reports. The server generates reports for users based on the results of data analysis. Based on the results of the emotion recognition engine, the tone and difficulty of the report can be adjusted and output in the format specified by the user (PDF, Excel, PNG). Specifically, the PDF report is generated using ReportLab. The input is the analysis results, and the output is a customized report.

[0933] Step 7:

[0934] The server generates and displays personalized ads. Based on the user's emotions and past behavioral data, the server generates the optimal ad and displays it on the smartphone or PC. HTML5 and JavaScript are used to control the timing of ad display. The input is emotional data and past behavioral data, and the output is a personalized ad.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] [Fourth embodiment]

[0939] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0940] 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.

[0941] 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).

[0942] 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.

[0943] 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.

[0944] 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).

[0945] 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.

[0946] 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.

[0947] 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.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] 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."

[0952] ---

[0953] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows:

[0954] 1. User Input

[0955] Users enter analysis conditions in text format through the system's user interface (UI). For example, they might enter a condition such as, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[0956] 2. Data Collection

[0957] The server analyzes the conditions entered by the user and activates the data collection engine, which accesses the specified data sources (corporate core systems, databases, cloud storage, local electronic spreadsheet files, etc.) and automatically collects the required data. For example, it retrieves relevant sales data from a sales database and also reads related data from a locally stored Excel file.

[0958] 3. Data integrity check

[0959] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[0960] 4. Data Analysis

[0961] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This process includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden increases in sales in specific categories. It also analyzes the correlation between sales data and advertising expenditure data and creates a report based on the results.

[0962] 5. Report generation and provision

[0963] The server generates a report based on the analysis results. The report includes a data summary, graphs, trend analysis results, and correlation comments. The report is output in a format specified by the user (PDF, Excel, PNG, etc.) and provided to the user via a dashboard. For example, the server can save the generated report in PDF format, and the user can download it from the dashboard to use as meeting material.

[0964] ---

[0965] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

[0966] The processing flow will be explained below.

[0967] Step 1: User Input

[0968] Users use the system's interface to enter analysis conditions in text format, such as "aggregate sales data from January 2023 to June 2023 and graph it by category." In addition, users can specify specific time periods and aggregation items.

[0969] Step 2: Condition analysis

[0970] The server analyzes the text conditions entered by the user and determines the type, period, and format of data to be collected. For example, the server generates specific analysis conditions such as "sales data," "January to June 2023," and "by category."

[0971] Step 3: Start the data collection engine

[0972] The server runs a data collection engine and accesses multiple data storage systems based on analysis criteria, including corporate systems, databases, cloud storage, and local electronic spreadsheets.

[0973] Step 4: Data collection

[0974] The server automatically collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. The collected data is temporarily stored on the server.

[0975] Step 5: Data integrity check

[0976] The server then performs a process to check the integrity of the collected data. This process involves standardizing the data format, filling in missing values, and deleting and merging duplicate data. For example, it standardizes different date formats (YYYY / MM / DD vs MM-DD-YYYY) and merges data with the same product name.

[0977] Step 6: Data analysis

[0978] The server then performs a specified analysis process on the data after verifying its integrity, which may include generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, the server may analyze monthly sales trends to detect sudden sales spikes in a particular category.

[0979] Step 7: Generate reports

[0980] The server generates a report based on the data analysis results. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.).

[0981] Step 8: Reporting

[0982] Users can download the generated report from the system dashboard. For example, users can access the dashboard and click the download link for the completed report to obtain the report in PDF format.

[0983] Example 1

[0984] 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."

[0985] Modern companies require systems that can effectively collect and analyze large amounts of data to support rapid and accurate decision-making. However, conventional systems require a great deal of effort to collect data and verify consistency, and are often only available to users with specific expertise. Furthermore, collecting data from multiple sources, unifying data in different formats, and creating visual reports of analysis results are all time-consuming. Furthermore, the lack of functionality for outputting reports in various formats creates a problem of reduced user convenience.

[0986] 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.

[0987] In this invention, the server includes a means for a user to input analytical conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, a means for generating a report based on the analysis results, and a means for outputting the report in a format specified by the user. This allows users without specialized knowledge to easily perform complex data collection and analysis, reduces the burden of reporting work, and enables quick and accurate decision-making based on data.

[0988] A "user" is a person who operates the system to input analytical conditions and instructs the output of a report.

[0989] "Text format" refers to the format of a string of characters that allows a user to input analytical conditions and instructions to the system.

[0990] "Analysis conditions" are information for specifying the period and items to be collected and analyzed.

[0991] "Data storage system" is a general term for systems that store data, such as a company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[0992] "Data collection" is the act of obtaining necessary data from designated data sources.

[0993] "Consistency check" is the process of creating a consistent data set by standardizing the format of collected data, filling in missing values, and deleting and integrating duplicate data.

[0994] "Data analysis" refers to the process of generating summaries, creating graphs, conducting trend analysis, and performing correlation analysis using data whose consistency has been confirmed.

[0995] "Report generation" is the act of creating a visually easy-to-understand report based on the results of data analysis.

[0996] "Report output" is the process of saving and providing the generated report in a format specified by the user, such as PDF, Excel, or PNG.

[0997] "Format" refers to the file type and data representation method specified for report output.

[0998] This big data aggregation system automatically collects data from multiple data storage systems based on user input, analyzes the data after verifying its consistency, and finally generates a report. The system of the present invention is implemented as follows.

[0999] Users access the system's user interface (UI) through a web browser and enter analysis conditions in text format. This UI is built using HTML and JavaScript, and the entered conditions are sent to the server as an HTTP request. For example, a user might enter something like, "Please aggregate sales data from January 2023 to June 2023 and graph it by category."

[1000] The server analyzes the received request and launches the data collection engine. Implemented in Python or Java, the data collection engine accesses the company's core systems, cloud storage, and local electronic spreadsheet files (e.g., MySQL databases, AWS S3 buckets, Excel files, etc.) to collect the necessary data. For example, it retrieves sales data from January 2023 to June 2023 from a MySQL database and then reads related data from a locally stored Excel file.

[1001] The server performs preprocessing to check the integrity of the collected data. This includes standardizing data formats, filling in missing values, and deleting and merging duplicate data. For example, it converts date data stored in different formats into a standard format (YYYY-MM-DD) and merges duplicate product data into one.

[1002] Based on the data whose integrity has been confirmed, the server executes the specified analysis process. For data analysis, Python libraries such as Pandas and NumPy are used to analyze monthly sales trends and detect sudden increases in sales in specific categories. The server also calculates correlations between sales data and advertising expenditure data and analyzes the results.

[1003] The analysis results are compiled into a visually easy-to-read report during the report generation process. The server creates graphs using Matplotlib and Seaborn, and generates reports in PDF format using ReportLab. The reports include data summaries, graphs, trend analysis results, and correlation-based comments. The generated reports are uploaded to a dashboard and can be downloaded by users.

[1004] As a concrete example, consider the case where the user enters the following prompt sentence:

[1005] Example prompt sentence:

[1006] Please compile sales data from January 2023 to June 2023 and graph it by category. Also, please analyze the correlation with advertising expenses.

[1007] This system allows users without specialized knowledge to easily collect and analyze complex data, significantly improving the efficiency of data analysis work, thereby reducing the burden of reporting work and enabling quick and accurate data-based decision-making.

[1008] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1009] Step 1:

[1010] The user accesses the system's user interface (UI) through a web browser and enters the analysis conditions in text format. Specifically, the user enters "Aggregate sales data from January 2023 to June 2023 and graph it by category" into the UI text box and clicks the send button. This operation sends the analysis conditions to the server as an HTTP request. The input is the analysis conditions in text format, and the output is an HTTP request to the server.

[1011] Step 2:

[1012] The server analyzes the received HTTP request and starts the data collection engine. Specifically, the server extracts the conditions entered by the user from the request body and sets specific parameters for data collection based on them. For example, it analyzes the period and aggregation items and passes them to the data collection engine. The input is the analysis conditions in the HTTP request, and the output is the set data collection parameters.

[1013] Step 3:

[1014] The server collects the required data from the specified data source through the data collection engine. Specifically, the server connects to the MySQL database and issues a query such as "SELECT FROM sales WHERE date BETWEEN '2023-01-01' AND '2023-06-30'" to retrieve sales data. It also reads corresponding sales data from a local electronic spreadsheet file. The input is the data collection parameters, and the output is the collected raw data.

[1015] Step 4:

[1016] The server checks the integrity of the collected data and performs necessary preprocessing. Specifically, the server unifies different date formats (e.g., YYYY-MM-DD), removes duplicate data, and imputes missing values ​​with the mean or median. The input is the collected raw data, and the output is clean data that has been checked for integrity.

[1017] Step 5:

[1018] The server then executes the specified analysis process using the data whose integrity has been confirmed. Specifically, the server creates a data frame using the Pandas library and performs grouping and aggregation processes. It also uses Matplotlib to graph monthly sales trends and calculate the correlation between sales data and advertising expense data. The input is clean data, and the output is the analysis results.

[1019] Step 6:

[1020] The server generates a report based on the analysis results. Specifically, the server uses ReportLab to create a PDF report and embeds the generated graphs and analysis results in the report. The input is the analysis results, and the output is a PDF report.

[1021] Step 7:

[1022] The server provides the generated report to the user. Specifically, the server uploads the PDF report to the dashboard and provides a download link to the user. The user accesses the dashboard and downloads the PDF report for use. The input is the PDF report, and the output is a report link that the user can download.

[1023] (Application example 1)

[1024] 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."

[1025] Currently, corporate data analysis work is extremely complicated, and in many cases, analysts with specialized knowledge must manually collect data, check its consistency, and perform analysis. This process is time-consuming, labor-intensive, and inefficient. Many businesses also require real-time data analysis, but current systems make this difficult to achieve. In particular, sales representatives and customer support staff need an environment where they can view data in real time on their smartphones so they can quickly take action. A system that can solve this problem is needed.

[1026] 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.

[1027] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating a report based on the analysis results and displaying it on a smartphone application. This enables sales representatives and customer support to check sales data in real time and quickly take countermeasures.

[1028] "User" refers to a person or organization that operates the system, inputs analytical conditions, and checks data collection and analytical results.

[1029] "Text format" refers to the input method for analysis conditions and search queries expressed as character strings.

[1030] "Analysis conditions" are the standards and parameters for data collection and analysis specified by the user, including the period and aggregation items.

[1031] A "data storage system" is a system that stores data such as a company's core systems, databases, cloud storage, and local files.

[1032] "Means for automatically collecting data" refers to a system that automatically collects necessary data from designated data sources using a program.

[1033] "Means for checking and correcting data consistency" refers to a system for standardizing the format of collected data, completing missing values, and deleting and integrating duplicate data.

[1034] "Means for analyzing data whose consistency has been confirmed" refers to a system for conducting trend analysis and correlation analysis based on data whose consistency has been confirmed.

[1035] "Means for generating reports and displaying them on a smartphone application" refers to a mechanism for creating reports including graphs and charts based on the analysis results, allowing users to view them on a smartphone application.

[1036] This invention provides a system that allows users to input analytical conditions in text format, automatically collects data from multiple data storage systems, checks the consistency of the data, analyzes it, and finally generates a report that is displayed on a smartphone application.

[1037] The server receives analysis conditions in text format from the user through a user interface. This user interface includes fields for entering detailed parameters such as the analysis period and aggregation items. For example, a user might enter a condition such as "Aggregate sales data from January 2023 to June 2023 and graph it by category."

[1038] The server then launches a data collection engine to automatically collect the required data from designated data sources, such as enterprise systems, databases, cloud storage, local spreadsheets, etc. The collected data is often stored in different formats, so the server must convert it into a unified format.

[1039] The server checks the integrity of the collected data. This includes standardizing data formats, filling in missing values, and removing and merging duplicate data. For example, it standardizes date data stored in different formats or data for the same product name obtained from multiple sources into a standard format.

[1040] Once the integrity of the data has been confirmed, it is analyzed according to the specified analysis process. The server generates summaries, creates graphs, performs trend analysis, and performs correlation analysis. For example, it can analyze monthly sales trends to detect sudden increases in sales in a particular category. It can also analyze correlations between sales data and advertising spend data and create reports based on the results.

[1041] Finally, the server generates a report based on the analysis results and displays it on the smartphone application. This report includes a data summary, graphs, trend analysis results, and correlation comments. Users receive the report in the specified format (e.g., PDF, Excel, PNG, etc.) and can view it on the dashboard through the smartphone application.

[1042] Hardware and software used

[1043] The server uses the following hardware and software:

[1044] Hardware: Server computers, cloud storage, and users' smartphones

[1045] Software: Flask (web application framework), pandas (data analysis library), matplotlib (graph generation library)

[1046] Specific examples

[1047] For example, a sales representative at an online retailer might want to analyze data based on the following criteria:

[1048] "Analyze sales data by category from January 2023 to June 2023 and chart monthly sales trends."

[1049] Once these conditions are entered through the user interface, the server automatically collects sales data for the specified period from databases and cloud storage, checks the data for consistency, and then analyzes it.The final report is displayed on a smartphone application, allowing sales representatives to check the results in real time.

[1050] Prompt Sentence Examples

[1051] Period: January 2023 to June 2023

[1052] Aggregate item: Sales data by category

[1053] Expected output: Chart of monthly sales trends

[1054] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1055] Step 1:

[1056] The user inputs the analysis conditions in text format.

[1057] Input: Analysis period, aggregation items, specific analysis conditions (e.g., "Aggregate sales data from January 2023 to June 2023 and graph it by category").

[1058] How it works: You enter a condition in text format in an input field in the user interface and send it to the server.

[1059] Output: The analysis conditions are sent to the server.

[1060] Step 2:

[1061] The server analyzes the analysis conditions in text format received from the user.

[1062] Input: Analysis conditions entered by the user.

[1063] Operation: The server analyzes the text of the analysis conditions and extracts parameters such as the period for collecting data and the items to be aggregated.

[1064] Output: Parsed parameters (analysis period, aggregation items, etc.).

[1065] Step 3:

[1066] The server launches a data collection engine to automatically collect data from the specified data sources.

[1067] Input: Parsed parameters (analysis period, aggregation items, etc.).

[1068] How it works: The data collection engine starts and collects the relevant data from the company's core systems, databases, cloud storage, local electronic spreadsheets, etc.

[1069] Output: The raw data collected.

[1070] Step 4:

[1071] The server checks and corrects the integrity of the collected data.

[1072] Input: Raw data collected.

[1073] Operation: The server standardizes data formats, fills in missing values, and removes and consolidates duplicate data.

[1074] Output: Data with integrity checked.

[1075] Step 5:

[1076] The server performs analysis based on the data whose integrity has been confirmed.

[1077] Input: Data whose integrity has been checked.

[1078] Action: The server performs the specified analysis operations such as summary generation, graph creation, trend analysis, correlation analysis, etc.

[1079] Output: Analysis results.

[1080] Step 6:

[1081] The server generates a report based on the analysis results and displays it on a smartphone application.

[1082] Input: Analysis results.

[1083] Operation: The server creates a report containing graphs and charts based on the analysis results and sends it to a smartphone application. The user can view the report through the application.

[1084] Output: The report displayed on the user's smartphone.

[1085] 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.

[1086] ---

[1087] The big data aggregation system of the present invention not only automatically collects data from multiple data storage systems based on user input, analyzes the data, and generates reports, but also includes an emotion engine that recognizes user emotions and customizes the system's operation. Detailed embodiments are described below.

[1088] 1. User Input

[1089] Users enter analysis conditions in text format through the system's user interface (UI). For example, they can enter a condition such as "aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[1090] 2. Emotion recognition

[1091] The server recognizes the user's emotion from the user's input using an emotion engine, which uses natural language processing and facial expression recognition technologies to determine the user's emotion (e.g., joy, sadness, anger, surprise, fear, etc.).

[1092] 3. Start the data collection engine

[1093] Based on the emotion engine's judgment results, the server activates the data collection engine and collects data from appropriate data sources based on the analysis conditions, including the company's core systems, databases, cloud storage, and local electronic spreadsheet files.

[1094] 4. Data Collection

[1095] The server collects and temporarily stores the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It also filters the collected data based on the emotion engine.

[1096] 5. Data integrity check

[1097] The server performs processes to check the integrity of the collected data, including standardizing data formats, filling in missing values, and removing and merging duplicate data. It is also possible to adjust the priority of filtering and correction in this process based on the results of the emotion engine.

[1098] 6. Data Analysis

[1099] The server then performs the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Furthermore, it customizes the content and presentation of reports based on the results of the emotion engine.

[1100] 7. Report Generation and Delivery

[1101] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. It is output in the format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report are adjusted based on the results of the emotion engine. This allows users to receive a report that is easier to understand and tailored to their purpose.

[1102] 8. Feedback and Further Customization

[1103] Users can review the generated reports and provide further feedback, which the emotion engine analyzes in real time to further customize the system's behavior and report content.

[1104] ---

[1105] As described above, this invention achieves flexible and efficient data analysis that takes user emotions into consideration by integrating an emotion engine into a conventional data collection and analysis system, thereby reducing the burden on users and supporting more accurate decision-making.

[1106] The processing flow will be explained below.

[1107] Step 1: User Input

[1108] Users enter analysis conditions in text format using the system's user interface (UI). For example, they might enter, "Aggregate sales data from January 2023 to June 2023 and graph it by category." They can also specify detailed parameters such as the period and aggregation items.

[1109] Step 2: Emotion Recognition

[1110] The server analyzes the user's input and behavior on the interface (e.g., typing speed, frequency of typos, etc.) and uses an emotion engine to recognize the user's emotions. For example, if the user types quickly, the emotion engine determines that the user is impatient.

[1111] Step 3: Condition analysis and customization

[1112] The server analyzes the conditions entered by the user and determines the type, period, and format of data to be collected. Furthermore, it customizes the analysis conditions and the display method of the results based on the results of the emotion engine. For example, if the user is in a hurry, the system adjusts to present important analysis results earlier.

[1113] Step 4: Start the data collection engine

[1114] The server runs the data collection engine and accesses data sources based on the analysis criteria, including enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[1115] Step 5: Data collection

[1116] The server collects the necessary data from each data source. For example, it retrieves sales data from a sales database and reads related data from a local Excel file. It may also adjust the priority and speed of data collection based on the results of the emotion engine.

[1117] Step 6: Data integrity check

[1118] The server checks the integrity of the collected data, standardizes the data format, fills in missing values, and removes and merges duplicate data. Based on the results of the emotion engine, it adjusts the speed of this process and the strictness of the filtering.

[1119] Step 7: Data analysis

[1120] The server then executes the specified analysis process based on the data whose integrity has been confirmed. This includes generating summaries, creating graphs, analyzing trends, and analyzing correlations. For example, it analyzes monthly sales trends to detect sudden sales spikes in specific categories. Based on the results of the sentiment engine, it customizes the display and order of the analysis results.

[1121] Step 8: Generate reports

[1122] The server generates a report based on the results of the data analysis. The report includes a data summary, graphs, trend results, and correlation analysis results. The report is output in a format specified by the user (PDF, Excel, PNG, etc.), and the tone and difficulty of the report reflect the results of the emotion engine.

[1123] Step 9: Reporting

[1124] Users can download the generated report from the system's dashboard. For example, a user can access the dashboard and click the download link for the completed report to obtain a PDF version of the report. The report also includes feedback based on the user's emotional state.

[1125] Step 10: Feedback and customization

[1126] The user can review the generated report and provide further feedback to the system, for example, requesting additional analysis or detailed explanations of specific items. The server analyzes the user's feedback and the results of the emotion engine to further customize the system's behavior and report content for future use.

[1127] Example 2

[1128] 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."

[1129] Conventional big data aggregation systems do not consider user sentiment when verifying the integrity of collected data or analyzing it, which can lead to analysis results that do not match user expectations or requirements. Furthermore, handling large amounts of data places a heavy burden on users, preventing them from effectively utilizing the results of data analysis. Furthermore, there is a need for a flexible system that can incorporate user feedback in the processes of rapid data collection, analysis, and report generation.

[1130] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1131] In this invention, the server includes a means for a user to input analysis conditions in text format, a means for automatically collecting data from a data storage system, a means for recognizing user emotions and customizing system operation, a means for checking and correcting the consistency of the collected data, a means for analyzing the data whose consistency has been checked, and a means for generating reports based on the analysis results, thereby enabling flexible and efficient data analysis and report generation that takes user emotions into consideration.

[1132] The "means for the user to input analytical conditions in text format" refers to a device or software for inputting text data specified by the user into the system through an interface.

[1133] "Means for automatically collecting data from data storage systems" refers to devices or software that automatically retrieve the required data from different data sources.

[1134] "Means for recognizing user emotions and customizing system behavior" refers to a device or software that analyzes user emotions and adjusts system behavior and interface based on the results.

[1135] "Means for verifying and correcting the consistency of collected data" refers to devices or software that verify the format and content of extracted data and make appropriate corrections to ensure consistency.

[1136] The "means for analyzing data whose integrity has been confirmed" refers to a device or software for performing a specified analysis based on data whose integrity has been confirmed.

[1137] A "means for generating a report based on the analysis results" is a device or software that organizes the results of the data analysis and creates a visual or written report to provide to the user.

[1138] "Local spreadsheet files" are files created by spreadsheet software that are stored on a user's individual device or local storage.

[1139] The big data aggregation system of the present invention includes a process for automatically collecting data from multiple data storage systems based on user input and generating reports from the analysis results. In addition, it uses an emotion engine that recognizes user emotions and customizes the system's behavior, allowing users to obtain optimal analysis results based on their emotions.

[1140] The specific system configuration uses the following hardware and software:

[1141] User Interface (UI): A web-based interface implemented using HTML and JavaScript.

[1142] Emotion Engine: A software module that uses natural language processing (NLP) and facial expression recognition technologies and is implemented in Python.

[1143] Data Collection Engine: Includes Python scripts that collect data from enterprise systems, databases, cloud storage, and local electronic spreadsheets.

[1144] Data integrity check module: A software module that uses Python and R to standardize data formats, complete missing values, and remove duplicate data.

[1145] Data analysis module: A software module that performs trend analysis of sales data and graphs sales data by category, using Python's pandas and matplotlib libraries.

[1146] Report generation module: Software that generates reports in PDF, Excel, or PNG format based on analysis results, using Python's ReportLab.

[1147] (Example)

[1148] The user enters text into the system's UI, saying, "Please aggregate sales data from January 2023 to June 2023 and graph it by category." If the user indicates an emotion, for example, "I'm in a hurry," the emotion engine analyzes this information and switches the operation of the entire system to "high-speed mode."

[1149] The server quickly and efficiently launches the data collection engine based on the analysis conditions and emotion recognition results. It collects the necessary data from the company's core systems and local Excel files, standardizes the format, and imputes missing values. After verifying data integrity, the data analysis module graphs monthly sales trends and sales data by category.

[1150] The server generates a visually easy-to-understand PDF report based on the analysis results and provides it to the user. If the user reviews the report and requests a more detailed analysis, they can enter their feedback into the system, which will use the emotion engine to refine the next analysis process.

[1151] Through the above process, this big data aggregation system can flexibly and efficiently meet user requirements and support more accurate decision-making.

[1152] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1153] Step 1:

[1154] The user inputs analysis conditions in text format through the system's UI.

[1155] Specifically, the user enters "Please aggregate sales data from January 2023 to June 2023 and graph it by category" and clicks the submit button.

[1156] Input: Analysis conditions (text format)

[1157] Output: Analysis conditions are sent to the server

[1158] Step 2:

[1159] The server receives the user's input and recognizes the user's emotions using an emotion engine.

[1160] Specifically, it uses Natural Language Processing (NLP) technology to analyze text and determine whether the user is in a hurry.

[1161] Input: Text data of analysis conditions

[1162] Output: User emotion data (e.g., hurry)

[1163] Step 3:

[1164] The server starts the data collection engine based on the determination results of the emotion engine and the analysis conditions.

[1165] Determine which data sources to acquire to complete the overall data collection process most efficiently. At this stage, develop a plan to collect data from your company's core systems, cloud storage, local electronic spreadsheets, etc.

[1166] Input: Emotion data, analysis conditions

[1167] Output: Execution plan for data collection

[1168] Step 4:

[1169] The server collects the data using a data collection engine.

[1170] Specifically, it sends API requests to the sales database and retrieves necessary data from cloud storage and the local file system.

[1171] Input: Execution plan for data collection

[1172] Output: Raw data collected (e.g. sales data)

[1173] Step 5:

[1174] The server checks the consistency of the collected data and performs correction processing.

[1175] Specifically, data cleaning processes are carried out, such as standardizing data formats, filling in missing values, and deleting duplicate data.

[1176] Input: Raw data collected

[1177] Output: Consistency checked and corrected data

[1178] Step 6:

[1179] The server performs analysis of the corrected data using a data analysis module.

[1180] Here, sales data trend analysis and category sales data graphing are performed using Python's pandas and matplotlib libraries.

[1181] Input: Corrected data

[1182] Output: Analysis results (e.g., sales graph by category)

[1183] Step 7:

[1184] The server generates a report based on the analysis results.

[1185] Specifically, the analysis results are compiled into a report in a visually easy-to-understand format (PDF, Excel, PNG, etc.), and a library such as ReportLab is used to generate PDF reports.

[1186] Input: Analysis results

[1187] Output: Report (e.g. PDF format)

[1188] Step 8:

[1189] The user reviews the generated report and provides any necessary feedback to the system.

[1190] For example, you can enter a request such as "I want more detailed analysis." This feedback will be used to improve the system as a whole.

[1191] Input: Feedback text data

[1192] Output: Feedback is sent to the server

[1193] Step 9:

[1194] The server receives the feedback and analyzes it using an emotion engine to further optimize the system's behavior and future analysis processes.

[1195] Based on the feedback, we will adjust future data analysis policies and algorithms.

[1196] Input: Feedback text data

[1197] Output: Adjusted system operating configuration

[1198] (Application example 2)

[1199] 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."

[1200] Conventional data collection and analysis systems mechanically process data and present results without considering user emotions, making it difficult to respond flexibly based on user intentions and emotions. Displaying personalized advertisements is also difficult, creating a need for improved user experience. Therefore, the present invention aims to improve the efficiency and quality of data analysis and advertisement display by recognizing user emotions and customizing system behavior based on those emotions.

[1201] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1202] In this invention, the server includes means for a user to input analysis conditions in text format, means for automatically collecting data from a data storage system, means for checking and correcting the consistency of the collected data, means for analyzing the data whose consistency has been checked, means for generating a report based on the analysis results, means for recognizing the user's emotions and customizing the operation of the system, and means for generating and displaying personalized advertisements based on the emotions. This allows the system to operate flexibly based on the user's emotions and intentions, making it possible to display more effective and personalized advertisements.

[1203] "Means for users to input analytical conditions in text format" refers to an interface that allows users to input analytical conditions and parameters using text.

[1204] "Means for automatically collecting data from a data storage system" refers to a function for automatically obtaining required data from a predefined data source.

[1205] "Means for verifying and correcting the consistency of collected data" refers to a function that checks whether collected data is accurate and consistent, and makes corrections or amendments as necessary.

[1206] "Means for analyzing data whose integrity has been checked" refers to a function for executing a specified analysis process on data whose integrity has been checked.

[1207] "Means for generating a report based on the analysis results" refers to a function that compiles the results of the analysis and outputs them as a report for the user.

[1208] "Means for recognizing user emotions and customizing system behavior" refers to the ability to detect the user's emotional state and adjust the system's behavior and output based on that information.

[1209] "Means for generating and displaying personalized advertisements based on emotions" refers to a function that reflects the user's emotional data to create and display advertisements that are optimally tailored to each individual user.

[1210] The system for implementing the present invention is configured using a server, a user terminal, and an emotion recognition engine. Each step and the necessary hardware and software will be described in detail below.

[1211] The server provides a means for users to input analysis conditions in text format. Through this interface, users input the period and items they want to analyze. For example, a condition might be entered such as, "Please aggregate sales data by category from January 2023 to June 2023."

[1212] The server has a means for automatically collecting data from data storage systems, such as corporate databases, cloud storage, and local electronic spreadsheet files. The data collection engine automatically collects the required data from these data sources.

[1213] The emotion recognition engine detects emotions from user input and facial expressions. The server uses this information to customize system behavior and filter and analyze data according to the user's psychological state. The emotion engine uses natural language processing technology and facial expression recognition software.

[1214] The integrity of the collected data is checked and corrected as necessary. This includes standardizing the data format, filling in missing values, and deleting and merging duplicate data. The Pandas library, which excels at manipulating data frames, is used for processing.

[1215] The data, once validated, is then analyzed according to a specified analysis process, which includes generating data summaries, creating graphs, and analyzing trends and correlations. The Scikit-learn and Matplotlib libraries are used as analytical tools.

[1216] Based on the analysis results, a report tailored to each user's individual feelings is generated, including adjusting the tone and level of difficulty of the data and outputting it in formats such as PDF, Excel, and PNG. ReportLab, for example, is used as a report generation tool.

[1217] Furthermore, it generates and displays personalized ads based on user emotions and data. This includes a function where the ad display engine takes into account user emotions and past behavioral data to select and display appropriate ads. The timing of ad display is controlled using HTML5 and JavaScript.

[1218] Specific examples

[1219] For example, when a user logs in using a smartphone and enters analysis criteria, a camera detects their facial expressions. If the user is recognized as "happy," entertainment-related advertisements are selected and displayed. At the same time, sales data is automatically collected from the database based on the user-specified period, appropriate trend analysis is performed, and easy-to-understand reports are generated.

[1220] Prompt Sentence Examples

[1221] Develop a system that analyzes a user's facial expressions in real time and displays the most appropriate advertisement based on their emotion. If the user is "Happy," it will display an entertaining advertisement, and if the user is "Sad," it will display an uplifting advertisement. Use OpenCV to capture the user's face with a camera, implement an emotion recognition algorithm, and select the appropriate advertisement from the advertisement database based on the results.

[1222] This allows for appropriate and efficient data analysis and advertising presentation, taking into account the user's psychological state.

[1223] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1224] Step 1:

[1225] The user enters the analysis conditions. The user enters the analysis conditions in text format (e.g., "Please summarize sales data from January 2023 to June 2023 by category") via the UI on their smartphone or PC. This input is then sent to the server.

[1226] Step 2:

[1227] The server performs emotion recognition. The server uses an emotion recognition engine to analyze the user's emotions based on the text entered by the user and the facial expressions captured by the smartphone camera. The analysis results (e.g., "Happy" or "Sad") are used for subsequent data collection and customization processing.

[1228] Step 3:

[1229] The server starts the data collection engine. Based on the emotion recognition results and the user's input conditions, the server collects the necessary data from the appropriate data source (e.g., core system, database, cloud storage, local electronic spreadsheet file). The data collection engine automatically acquires data according to the specified period and items.

[1230] Step 4:

[1231] The server checks and corrects the consistency of the collected data. The server unifies the format of the collected data, completes missing values, and removes duplicate data. Specifically, it uses the Pandas library to operate on data frames and checks consistency. The data input is the collected raw data, and the output is data whose consistency has been checked.

[1232] Step 5:

[1233] The server performs data analysis. Based on the data whose integrity has been confirmed, the server performs the specified analysis process (summary generation, graph creation, trend analysis, correlation analysis). For example, the analysis is performed using the Scikit-learn library or Matplotlib library. The input is the data whose integrity has been confirmed, and the output is the analysis results.

[1234] Step 6:

[1235] The server generates and provides reports. The server generates reports for users based on the results of data analysis. Based on the results of the emotion recognition engine, the tone and difficulty of the report can be adjusted and output in the format specified by the user (PDF, Excel, PNG). Specifically, the PDF report is generated using ReportLab. The input is the analysis results, and the output is a customized report.

[1236] Step 7:

[1237] The server generates and displays personalized ads. Based on the user's emotions and past behavioral data, the server generates the optimal ad and displays it on the smartphone or PC. HTML5 and JavaScript are used to control the timing of ad display. The input is emotional data and past behavioral data, and the output is a personalized ad.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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.

[1242] 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.

[1243] 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.

[1244] 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).

[1245] 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.

[1246] 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."

[1247] 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.

[1248] 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).

[1249] 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.

[1250] 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.

[1251] 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.

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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.

[1256] 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.

[1257] 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.

[1258] 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.

[1259] The following is further disclosed regarding the above embodiment.

[1260] (Claim 1)

[1261] A means for users to input analytical conditions in text format;

[1262] means for automatically collecting data from a data storage system;

[1263] A means of checking and correcting the integrity of the collected data;

[1264] a means for analyzing the integrity-checked data;

[1265] a means for generating reports based on the analysis results;

[1266] A system including:

[1267] (Claim 2)

[1268] 10. The system of claim 1, further comprising means for automatically determining the duration and type of data to collect based on conditions specified by a user in text form.

[1269] (Claim 3)

[1270] 10. The system of claim 1, further comprising means for obtaining data from a local electronic spreadsheet file as a source of data to be collected.

[1271] (Claim 4)

[1272] The system according to claim 1, further comprising means for performing trend and correlation analysis based on the data analysis results and reflecting the analysis results in a report as graphs and comments.

[1273] (Claim 5)

[1274] 10. The system of claim 1, further comprising means for outputting the report in a user-specified format.

[1275] "Example 1"

[1276] (Claim 1)

[1277] A means for users to input analytical conditions in text format;

[1278] means for automatically collecting data from a data storage system;

[1279] A means of checking and correcting the integrity of the collected data;

[1280] a means for analyzing the integrity-checked data;

[1281] a means for generating reports based on the analysis results;

[1282] a means for outputting reports in a user-specified format;

[1283] A system including:

[1284] (Claim 2)

[1285] 10. The system of claim 1, further comprising means for automatically determining the duration and type of data to collect based on conditions specified by a user in text form.

[1286] (Claim 3)

[1287] 10. The system of claim 1, further comprising means for obtaining data from a local electronic spreadsheet file as a source of data to be collected.

[1288] "Application Example 1"

[1289] (Claim 1)

[1290] A means for users to input analytical conditions in text format;

[1291] means for automatically collecting data from a data storage system;

[1292] A means of checking and correcting the integrity of the collected data;

[1293] a means for analyzing the integrity-checked data;

[1294] A method for generating reports based on the analysis results and displaying them on a smartphone application.

[1295] A system including:

[1296] (Claim 2)

[1297] 10. The system of claim 1, further comprising means for automatically determining the duration and type of data to collect based on conditions specified by a user in text form.

[1298] (Claim 3)

[1299] 10. The system of claim 1, further comprising means for obtaining data from a local electronic spreadsheet file as a source of data to be collected.

[1300] "Example 2: Combining Emotion Engines"

[1301] (Claim 1)

[1302] A means for users to input analytical conditions in text format;

[1303] means for automatically collecting data from a data storage system;

[1304] A means of recognizing user emotions and customizing system behavior;

[1305] A means of checking and correcting the integrity of the collected data;

[1306] a means for analyzing the integrity-checked data;

[1307] a means for generating reports based on the analysis results;

[1308] A system including:

[1309] (Claim 2)

[1310] 10. The system of claim 1, further comprising means for automatically determining the duration and type of data to collect based on conditions specified by a user in text form.

[1311] (Claim 3)

[1312] 10. The system of claim 1, further comprising means for obtaining data from a local electronic spreadsheet file as a source of data to be collected.

[1313] "Application example 2 when combining emotion engines"

[1314] (Claim 1)

[1315] A means for users to input analytical conditions in text format;

[1316] means for automatically collecting data from a data storage system;

[1317] A means of checking and correcting the integrity of the collected data;

[1318] a means for analyzing the integrity-checked data;

[1319] a means for generating reports based on the analysis results;

[1320] A means of recognizing user emotions and customizing system behavior;

[1321] means for generating and displaying personalized advertisements based on emotions;

[1322] A system including:

[1323] (Claim 2)

[1324] 10. The system of claim 1, further comprising means for automatically determining the duration and type of data to collect based on conditions specified by a user in text form.

[1325] (Claim 3)

[1326] 10. The system of claim 1, further comprising means for obtaining data from a local electronic spreadsheet file as a source of data to be collected. [Explanation of symbols]

[1327] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to input analytical conditions in text format; means for automatically collecting data from a data storage system; A means of checking and correcting the integrity of the collected data; a means for analyzing the integrity-checked data; a means for generating reports based on the analysis results; A system including:

2. 10. The system of claim 1, further comprising means for automatically determining the period and type of data to be collected based on conditions specified by a user in text form.

3. 10. The system of claim 1, further comprising means for obtaining data from a local electronic spreadsheet file as a source of data to be collected.

4. The system according to claim 1, further comprising means for performing trend and correlation analysis based on the data analysis results and reflecting the analysis results in a report as graphs and comments.

5. 10. The system of claim 1, further comprising means for outputting the report in a user-specified format.

Images