system

Abstract

Provide a system. The present invention includes a means for accessing and collecting data from multiple data sources of a company; a means for storing the collected data in a data warehouse or data lake; means for analyzing the stored data and extracting key metrics and trends; A means for automatically generating presentation materials and financial statements based on the analysis results; A system including:

Description

[Technical Field]

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

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

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

[0004] Modern companies need to collect and analyze large amounts of data from a variety of sources and quickly create documents that will help them make business decisions. However, doing this manually requires a huge amount of time and effort and carries the risk of human error. In addition, processing the different formats of each data source requires advanced expertise, making data integration and analysis complex. Compiling analysis results into documents in an appropriate format is also difficult. The present invention aims to provide a data processing and document generation system that automates these tasks, improving efficiency and minimizing errors. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a data warehouse or data lake, a means for analyzing the stored data and extracting important indicators and trends, and a means for automatically generating presentation materials and financial statements based on the analysis results. Furthermore, the analysis means can clean the data, detect and remove fraudulent data, and aggregate the data, and also includes a means for users to review, correct, and approve the generated materials. This allows companies to process data efficiently and accurately and quickly create the necessary materials.

[0006] An "enterprise" is an organization that engages in commercial activities and is an economic entity that pursues profits by providing products and services.

[0007] "Data Source" means the point of origin or source where information or data is generated or provided, including databases, APIs, cloud services, etc.

[0008] "Collection" refers to the act of selecting and assembling data needed for a specific purpose.

[0009] A "data warehouse" is a database system that stores large amounts of data in an integrated and systematic manner and manages them in a way that allows them to be quickly accessed for analysis and reporting.

[0010] A "data lake" is a data management system for storing structured and unstructured data in its original format at high volumes and low cost.

[0011] "Analysis" refers to the computational processes used to prepare, transform, aggregate, and extract meaningful information and insights from collected data.

[0012] An "indicator" is a representation of numerical or categorical data used to measure or track a particular objective or goal.

[0013] A "trend" describes a regular pattern of fluctuation or movement in data or events.

[0014] "Presentation materials" are slides or documents that visually present information on a particular topic.

[0015] "Financial statements" are periodic reports summarizing a company's financial status, and include financial data such as revenues, expenses, and profits.

[0016] "Cleaning" refers to the process of detecting, correcting, or eliminating inaccurate, incomplete, or duplicate data from within a data set.

[0017] "Incorrect Data" means data that is erroneous, invalid, or unreliable.

[0018] "Aggregation" refers to the process of grouping data and calculating statistical information, totals, etc.

[0019] A "user" is a person or entity that operates a system or application and inputs or outputs information.

[0020] "Correction" means to correct or make correct any error, defect, or inaccuracy.

[0021] "Approval" refers to the act of checking and officially accepting various information and processing results. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] As an embodiment of the present invention, a system is configured as follows to collect data from multiple data sources of a company, store it in a data warehouse or data lake, and automatically compile the analysis results into documents.

[0044] Data collection

[0045] The server accesses each data source of the company (e.g., customer relationship management system, enterprise resource planning system, web analysis tool, etc.) and collects data. The collected data includes sales performance data, financial data, website traffic data, etc. The server obtains the necessary data using the API of each data source and temporarily stores it in memory.

[0046] Data storage

[0047] The server stores the collected data in a data warehouse or data lake. A data warehouse is a system for efficiently storing and quickly accessing structured data, while a data lake is a system for storing structured and unstructured data in its original form at high volume and low cost. The server converts the data into the appropriate format and stores it in these storage systems.

[0048] Data analysis

[0049] The server analyzes the collected and stored data. Using analytical tools (e.g., data visualization tools, BI tools), it performs processes such as cleaning the data, detecting and removing fraudulent data, and aggregating the data. For example, data cleaning involves detecting missing values ​​and outliers and correcting or removing them. Statistical methods and machine learning algorithms are used to detect fraudulent data. This results in reliable data.

[0050] Extracting indicators and trends

[0051] The server extracts key indicators (KPIs) and trends from the analysis results. For example, trends in sales or customer churn. This data is particularly important for business decisions. The server organizes this information and derives conclusions and insights.

[0052] Automatic generation of materials

[0053] The server automatically generates presentations and financial statements based on the extracted analysis results. For example, presentations include visually compiling key indicators into graphs and charts, while financial statements include creating reports containing detailed financial data such as revenue, expenses, and profits. This process involves inserting the results into appropriate formats using predefined templates.

[0054] Checking and correcting materials

[0055] Users can review the generated presentations and financial statements and make corrections as needed. They access the documents through the user interface, enter comments, and make corrections to data. This process ensures that the final documents are accurate and in the correct format.

[0056] Approval and Distribution of Materials

[0057] The user then approves the final revised and confirmed document, after which the device distributes the document to the relevant parties, which may include sending it via email, uploading it to cloud storage, or storing it in a database.

[0058] As a concrete example, consider the process by which a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. The data is then analyzed using a data visualization tool to extract important financial indicators and trends. Based on these results, the server automatically generates presentation materials and financial statements, which are then reviewed and revised by the user and finally distributed to the relevant parties.

[0059] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The server accesses each data source of the company and collects data. Specifically, it uses the APIs of different data sources (e.g., customer management systems, enterprise resource planning systems, web analytics tools) to obtain the required data. Each data source may require access authentication information and queries, so the server sets this information in advance.

[0063] Step 2:

[0064] The server temporarily holds the collected data in memory and stores it in a data warehouse or data lake. Here, the collected data is often provided in different formats, so the server converts the data into a unified format. This conversion process also includes cleaning the data, removing incomplete and duplicate data.

[0065] Step 3:

[0066] The server analyzes the stored data. First, it cleans the data, detecting missing values ​​and outliers and correcting or removing them. Next, it identifies and removes fraudulent data (e.g., abnormally high transaction amounts). After that, it aggregates the data and uses the aggregated results to calculate key performance indicators (KPIs). It also extracts trends based on past data and predicts customer behavior and market fluctuations.

[0067] Step 4:

[0068] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights based on these. During this process, data visualization tools are used to display the results in a visually understandable format.

[0069] Step 5:

[0070] The server automatically generates presentations and financial statements based on the extracted analysis results. The presentations visually display key indicators and trends as graphs and charts. The financial statements contain detailed financial data that allows management to make quick decisions. Templates are used to insert results in the appropriate format.

[0071] Step 6:

[0072] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary corrections. For example, the user can add explanations to graphs or correct annotations on data points. Once the corrections are complete, the user performs a final check of the documents.

[0073] Step 7:

[0074] The user approves the revised document. During the approval process, all revisions are checked to ensure they are properly reflected and officially accepted. The approved document is finally saved as an official document.

[0075] Step 8:

[0076] The device distributes the approved documents to the relevant parties via email, cloud storage sharing, or storing them in an internal company database, depending on the company's needs. This process ensures that all parties involved share the latest information and facilitates smooth decision-making.

[0077] These are the specific steps involved in the process, from data collection to analysis, document creation, and distribution. This system allows companies to obtain important management information efficiently and accurately.

[0078] Example 1

[0079] 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."

[0080] Modern companies need to efficiently manage and analyze large amounts of data collected from a wide variety of sources. However, organizing data provided in different formats and obtaining reliable analytical results is difficult. Furthermore, the process of quickly compiling the analytical results into reports and distributing them to relevant parties is time-consuming. There is a need to solve these issues and improve the efficiency of data processing and reporting.

[0081] 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.

[0082] In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a storage system, and a means for analyzing the stored data and extracting important indicators and trends, thereby enabling data collection from different data sources, data storage and analysis, and automatic generation of report materials.

[0083] "Multiple data sources of an enterprise" refers to multiple information sources that provide data in different formats, such as customer relationship management systems, enterprise resource planning systems, and web analytics tools used by an enterprise.

[0084] A "storage system" is a storage device such as a data warehouse or data lake for storing data efficiently and securely.

[0085] "Data cleaning" is the process of detecting, correcting, or removing missing or outlier values ​​from collected data.

[0086] "Incorrect data detection and removal" refers to the use of machine learning algorithms and statistical methods to identify inaccurate data and remove it from a dataset.

[0087] "Data aggregation" is the process of grouping scattered data points into specific metrics and conducting statistical analysis.

[0088] A "machine learning algorithm" is a mathematical model used to learn patterns in data analysis and perform predictions and clustering.

[0089] "Reliable data" is data whose accuracy and consistency are guaranteed after undergoing data cleaning and removal of inaccurate data.

[0090] "Report materials" are documents including presentation materials and financial statements generated based on the analysis results.

[0091] "End User" refers to the person or department responsible for reviewing, correcting, and ultimately approving the generated materials.

[0092] "Communication means" refers to an email system or cloud sharing service used to distribute the generated materials to relevant parties.

[0093] "Cloud storage" is an online storage service that stores data over the Internet and is accessible to multiple users.

[0094] As an embodiment of the present invention, a system is configured as follows, which collects data from a plurality of data sources of a company, stores the data in a storage system, and automatically compiles the analysis results into report materials.

[0095] Data collection

[0096] The server accesses each company's data source to collect data. It calls the API of each data source using pre-configured API keys and authentication information. During this process, sales performance data, financial data, web traffic data, etc. are collected from customer relationship management systems, enterprise resource planning systems, web analytics tools, etc. The server temporarily stores this data in memory.

[0097] Data storage

[0098] The server stores the collected data in a storage system, specifically a data warehouse such as Amazon Redshift to store structured data and a data lake such as Amazon S3 to store unstructured data. The server converts the data into an appropriate format (e.g., CSV or JSON) and uploads it to these storage systems.

[0099] Data analysis

[0100] The server then analyzes the collected and stored data. It uses data visualization tools such as Tableau and Power BI to perform the analysis. The server first cleans the data and uses statistical methods and machine learning algorithms to detect and correct missing values ​​and outliers. It then aggregates the data and creates graphs and charts to visualize key metrics.

[0101] Extracting indicators and trends

[0102] The server extracts important indicators (KPIs) and business trends from the analysis results. For example, trends in sales and customer attrition. This data is extremely important for making business decisions. The server stores the extracted indicators in a database and uses them to create reports.

[0103] Automatic generation of materials

[0104] The server automatically generates presentation materials and financial statements based on the extracted analysis results. Using templates such as Google Slides and Microsoft PowerPoint, important indicators are displayed visually in easy-to-understand graphs and charts. The generated materials can also be exported in PDF format and saved to cloud storage.

[0105] Checking and correcting materials

[0106] Users can review the generated presentations and financial statements and make corrections as needed. Users log in to a dedicated web interface to view the documents, add comments, and correct incorrect data.

[0107] Approval and Distribution of Materials

[0108] After the user has finalized and approved the document, the device distributes it to the relevant parties. Specifically, the document is sent and shared using an email system or cloud sharing service. In this way, the document that the end user has reviewed, corrected, and approved can be distributed to the relevant parties quickly and efficiently.

[0109] As a concrete example, consider the process when a company generates monthly financial statements. The server collects data from the customer management system and enterprise resource planning system and stores it in Amazon Redshift. It then analyzes the data using Tableau to extract monthly sales trends and customer churn trends. Based on this, the server automatically creates presentation materials and financial statements using Google Slides. The user reviews the materials, makes any necessary revisions, and distributes the final, approved materials to the relevant parties.

[0110] Example prompts for generative AI models

[0111] "Please automatically generate presentation materials and financial statements to analyze this month's sales trends and customer churn trends based on sales performance data and financial data collected from the company's customer relationship management system and enterprise resource planning system."

[0112] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[0113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0114] Step 1:

[0115] Data collection

[0116] The server accesses each company's data source and collects data. It uses pre-configured API keys and authentication information as input. Specifically, it performs the following operations:

[0117] The server makes an API call to retrieve sales performance data from the customer relationship management system.

[0118] Make another API call to retrieve financial data from an enterprise resource planning system.

[0119] Make yet another API call to get web traffic data from a web analytics tool.

[0120] As an output, the server temporarily stores the collected data in memory, thus completing the data collection from all data sources.

[0121] Step 2:

[0122] Data storage

[0123] The server stores the collected data in the storage system. As input, it uses the data collected in step 1. Specifically, it performs the following operations.

[0124] The server classifies the collected data into structured data and unstructured data.

[0125] Store structured data in Amazon Redshift (data warehouse) and unstructured data in Amazon S3 (data lake).

[0126] Convert the data into an appropriate format (e.g., CSV or JSON) and upload it to each storage system.

[0127] As an output, the server stores all data in a storage system.

[0128] Step 3:

[0129] Data analysis

[0130] The server analyzes the collected and stored data. It uses the data stored in step 2 as input. Specifically, it performs the following operations:

[0131] The server loads the data into a data visualization tool like Tableau or Power BI.

[0132] Perform data cleaning to detect, correct, or remove missing or outlier values, for example, by imputing missing values ​​with the mean using statistical methods or machine learning algorithms.

[0133] Apply machine learning algorithms to detect and filter out fraudulent data.

[0134] It performs the necessary aggregations and generates visuals such as bar graphs and line charts.

[0135] The output is a reliable analysis result.

[0136] Step 4:

[0137] Extracting indicators and trends

[0138] The server extracts key indicators and trends from the analysis results, using the analysis results obtained in step 3 as input. Specifically, it performs the following operations:

[0139] The server extracts important business trends such as sales trends and customer churn trends.

[0140] The extracted indicators are stored in a database for further processing.

[0141] The output is key metrics and business trends.

[0142] Step 5:

[0143] Automatic generation of materials

[0144] The server automatically generates presentation materials and financial statements based on the extracted analysis results. As input, it uses the indicators and trends obtained in step 4. Specifically, it performs the following operations:

[0145] The server loads Google Slides or Microsoft PowerPoint templates and prepares the slide structure.

[0146] Insert KPI graphs and charts into the template to make them visually easy to understand.

[0147] Export the generated documents in PDF format and temporarily save them in cloud storage.

[0148] As output, presentation materials and financial statements are generated.

[0149] Step 6:

[0150] Checking and correcting materials

[0151] The user checks the generated presentation materials and financial statements and makes any necessary corrections. The materials generated in step 5 are used as input. Specifically, the following operations are performed:

[0152] Users log in to a dedicated web interface to view the generated materials.

[0153] Users can add comments to documents and correct erroneous data if necessary.

[0154] When the user has completed the corrections, he or she presses the "Confirm" button.

[0155] The output is the corrected and verified material.

[0156] Step 7:

[0157] Approval and Distribution of Materials

[0158] The user finally approves the corrected and confirmed materials. The confirmed and corrected materials from step 6 are used as input. Specifically, the following operations are performed:

[0159] The user makes a final check of the materials and presses the "Approve" button.

[0160] The terminal sends the approved documents to the relevant parties by email.

[0161] The device uploads the materials to cloud storage and generates a sharing link.

[0162] The device notifies the relevant parties of the generated shared link and provides them with access to the materials.

[0163] The output is the final approved and distributed material.

[0164] (Application example 1)

[0165] 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."

[0166] Traditional factory operations required the manual collection and analysis of information from many data sources, which hindered efforts to improve production efficiency and reduce failure rates. It was particularly difficult to collect large amounts of data, properly analyze it, extract key indicators, and then quickly take specific action based on them. As a result, it was difficult for management and on-site managers to make decisions, hindering the optimization of operations.

[0167] 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.

[0168] In this invention, the server includes: means for accessing multiple data sources within a company to collect data; means for storing the collected data in a data warehouse or data lake; means for analyzing the stored data and extracting important indicators and trends; and means for automatically generating reports based on the analysis results and analyzing production efficiency and failure rates based on data from equipment and sensors within the factory. This automates data collection and analysis from each data source, enabling the rapid extraction and reporting of important indicators and trends. Furthermore, the generated reports can be reviewed, revised, and approved by the user, supporting optimal decision-making and achieving more efficient factory operations and reduced failure rates.

[0169] "Data sources" refers to the multiple information sources that a company has, such as customer relationship management systems, enterprise resource planning systems, web analytics tools, and equipment and sensors in factories.

[0170] A "data warehouse" is a system for efficiently storing large amounts of structured data and enabling fast access.

[0171] A "data lake" is a system that stores structured and unstructured data in its original form at high volume and low cost.

[0172] "Analysis" refers to the process of cleaning, transforming, aggregating, detecting and removing fraudulent data from collected and stored data, and extracting important indicators and trends.

[0173] "Indicators" are important numerical values ​​or indicators extracted as a result of data analysis, and include, for example, production efficiency, failure rate, inventory turnover rate, etc.

[0174] "Trend" refers to patterns or trends in data that are revealed through data analysis, such as changes in sales or an increasing trend in breakdowns.

[0175] A "report" is a document automatically generated based on the analysis results, which includes detailed information on production efficiency and failure rates.

[0176] "User" refers to the person responsible for reviewing generated reports, making corrections and approvals, and ultimately distributing the materials.

[0177] "System" refers to an integrated set of equipment and software for carrying out a series of processes including data collection, data storage, data analysis, extraction of indicators and trends, report generation, and user review, correction, and approval.

[0178] As an embodiment of the present invention, a specific system configuration of a factory operations management assistant application will be described. This system collects information from multiple data sources within a company and stores it in a data warehouse or data lake. It also analyzes the collected data to extract important indicators and trends and automatically generates reports.

[0179] System Configuration

[0180] Data collection

[0181] The server collects data from each piece of equipment and sensor in the factory via API. This data collection is performed using a Python script, which obtains the necessary data from the IoT sensors via REST API and temporarily stores it in memory.

[0182] Data storage

[0183] The server stores the collected data in a data warehouse or data lake. Specifically, it uses Python scripts to store the data in AWS (registered trademark) S3 and then in AWS Redshift (a data warehouse). This allows for efficient and low-cost management of large amounts of data.

[0184] Data analysis

[0185] The server analyzes the data using BI and data visualization tools, particularly Tableau, for data cleansing, analysis, and dashboard creation, and utilizes machine learning libraries such as scikit-learn to detect fraudulent data.

[0186] Extracting indicators and trends

[0187] Extract important KPIs from the analysis results, such as production efficiency, failure rate, and inventory turnover. By linking Python and Tableau, extract these indicators and clarify trends.

[0188] Automatic generation of materials

[0189] The server automatically generates reports based on the extracted KPIs and trends, and the reports are created according to predefined templates and presented in a visually easy-to-understand format.

[0190] User confirmation and correction

[0191] Users can view and edit the generated reports through a web interface, using a web framework such as Django to make it easier for users to add comments and edit the reports.

[0192] Approval and Distribution of Materials

[0193] After the user checks and modifies the report, they finally approve it. Approved documents are distributed to the relevant parties, sent via email, or uploaded to cloud storage.

[0194] Specific examples

[0195] For example, when managing a factory's production efficiency, this system works as follows: First, data from each production line is collected, stored in AWS S3, and managed using AWS Redshift. The data is then analyzed using Tableau to extract trends in production efficiency and failure rates. Based on this, reports are automatically generated, and managers can review, modify, and ultimately approve the reports through a Django-based web interface.

[0196] Prompt Sentence Examples

[0197] "Please develop an app that analyzes production efficiency and failure rate data within the factory and automatically generates monthly reports. The app will collect, save, analyze, extract KPIs, and automatically generate reports, and provide an interface that allows managers to easily check and modify the data."

[0198] In this way, the system of the present invention helps optimize factory operations, enabling efficient data management and analysis, and rapid report generation.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] The server collects data from each piece of equipment and sensor in the factory. Specifically, it runs a Python script to obtain production data from each IoT sensor through a REST API. The input is the API endpoint and authentication information of each sensor. After collecting the data, this data is temporarily stored in memory. The output is a set of collected production data.

[0202] Step 2:

[0203] The server stores the collected data in a data warehouse or data lake. Specifically, a Python script is used to store the data in AWS S3 and then ingest it into AWS Redshift. The input is the production data collected in step 1, and the output is the data stored in AWS S3 and AWS Redshift. This process includes data format conversion and operations for storing it in appropriate storage.

[0204] Step 3:

[0205] The server analyzes the stored data. First, it cleanses the data using Tableau to detect and remove missing values ​​and outliers. Next, it applies a machine learning model using the scikit-learn library to detect fraudulent data. The input is the data stored in AWS Redshift, and the output is the analyzed data after cleansing and fraud detection.

[0206] Step 4:

[0207] The server extracts key metrics and trends. Python scripts and Tableau are used in conjunction with the server to calculate KPIs (e.g., production efficiency, failure rate, inventory turnover) and derive trends. The cleansed and fraud-detected data is used as input. The output is the extracted key metrics and their trend data.

[0208] Step 5:

[0209] The server automatically generates reports based on the analysis results. It uses Python and Tableau to create reports according to predefined templates. It uses extracted KPIs and trend data as input. The output is an automatically generated report. The report summarizes the data in a visually easy-to-understand format.

[0210] Step 6:

[0211] Users can view and modify the generated reports through a web interface. Using an interface based on the Django framework, users can check the report content and add data and comments as needed. The input is the automatically generated report, and the output is the reviewed and modified report.

[0212] Step 7:

[0213] The user approves the revised report, and the server distributes it to the relevant parties. The approved report is sent by email or uploaded to cloud storage. The input is the reviewed and revised report, and the output is the final, distributed report. Through this process, the relevant parties can quickly obtain the latest production information.

[0214] 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.

[0215] As an embodiment of the present invention, a system is configured as follows: it collects data from multiple corporate data sources, stores and analyzes it in a data warehouse or data lake, and automatically generates materials based on the analysis results. In addition, by combining it with an emotion engine that recognizes the user's emotions, the content and expression of the materials are adjusted according to the user's emotions.

[0216] Data collection

[0217] The server accesses each data source of the company and collects data. For example, it obtains the necessary data using APIs of customer management systems, enterprise resource planning systems, web analytics tools, etc. The data from each data source is temporarily stored in memory.

[0218] Data storage

[0219] The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, cleans incomplete and duplicate data, and stores it.

[0220] Data analysis

[0221] The server analyzes the data stored on it, cleaning it, detecting and removing fraudulent data, aggregating it, and extracting key performance indicators (KPIs) and trends.

[0222] Automatic generation of materials

[0223] The server automatically generates presentation materials and financial statements based on the analysis results. It creates presentation materials that visually display key indicators and trends, and financial statements that include detailed financial data. It uses templates to insert results in the appropriate format.

[0224] Checking and correcting materials

[0225] The user checks the generated presentation materials and financial statements. The user accesses the materials, reviews them, and makes corrections as necessary. Once corrections are complete, the user performs a final check of the materials.

[0226] Approval and Distribution of Materials

[0227] The user approves the revised document. The approval process checks whether all revisions are reflected and officially accepts the document. The approved document is saved as an official document. The terminal distributes the document to the relevant parties.

[0228] Incorporating an emotion engine

[0229] The server collects user feedback and uses an emotion engine to recognize the user's emotions. For example, if a user expresses dissatisfaction or concern about the content of a presentation, the emotion engine analyzes that emotion and instructs the system to adjust the content and expression of the presentation. Specifically, the system makes adjustments based on the user's emotions, such as changing the tone of the presentation or adding additional explanations.

[0230] Specific examples

[0231] Consider a case where a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. It then analyzes the data using a data visualization tool to extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the extracted results. The generated materials are reviewed by the user, and after recognizing the user's emotions through an emotion engine, the content of the materials is adjusted as necessary. Finally, the user approves the materials, and the terminal distributes them to the relevant parties.

[0232] In this way, by incorporating an emotion engine, it becomes possible to create more user-friendly documents, and a system can be provided that supports efficient and effective decision-making in companies.

[0233] The processing flow will be explained below.

[0234] Step 1:

[0235] The server accesses each data source of the company and collects the necessary data. For example, it retrieves sales performance data using the API of a customer management system, financial data from an enterprise resource planning system, and website traffic data from a web analytics tool. This data is temporarily stored in memory.

[0236] Step 2:

[0237] The server stores the collected data in a data warehouse or data lake. The data is often provided in different formats, and the server converts the data into a unified format. The conversion process also includes cleaning the data, removing incomplete and duplicate data.

[0238] Step 3:

[0239] The server analyzes the stored data. First, it cleans the data, then detects and removes any irregularities (e.g., abnormally high transaction amounts), then aggregates the data and calculates key performance indicators (KPIs). It also extracts trends based on past data.

[0240] Step 4:

[0241] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights. During this process, data visualization tools are used to display the results in a visually understandable format.

[0242] Step 5:

[0243] The server automatically generates presentations and financial statements based on the extracted analysis results. Presentations include visual displays of key indicators and trends as graphs and charts, while financial statements include detailed financial data. Templates are used to insert results in the appropriate format.

[0244] Step 6:

[0245] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary edits. For example, the user can add explanations to graphs or edit annotations for data points. Once edits are complete, the user performs a final review of the documents.

[0246] Step 7:

[0247] The emotion engine receives user feedback and recognizes the user's emotions. For example, if the user expresses dissatisfaction or concern, the emotion engine analyzes that emotion. Based on the user's emotions, the engine suggests modifications based on the user's emotions, such as changing the tone of the material or adding additional explanations.

[0248] Step 8:

[0249] The user reviews the revised document again and makes any necessary final adjustments. If the user is satisfied with the results of the revisions, they approve the document. This process ensures that the document is finally completed accurately and in the appropriate format.

[0250] Step 9:

[0251] The user reviews the final approved material and officially accepts it. The approved material is finally saved as an official document.

[0252] Step 10:

[0253] The terminal distributes approved documents to the relevant parties. Distribution methods include sending emails, uploading to cloud storage, and saving to the company's internal database. This allows all parties involved to share the latest information and facilitates smooth decision-making.

[0254] These are the specific steps in a company's data collection, analysis, document creation, and distribution. This system makes it possible to create documents that take user emotions into account, allowing companies to obtain important management information more efficiently and accurately.

[0255] Example 2

[0256] 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."

[0257] Modern companies possess large amounts of data, but it is difficult to efficiently collect, store, and analyze that data, and automatically generate materials to help with decision-making. Furthermore, because the content of the generated materials does not change based on the user's emotions, there is no guarantee that the materials will be easy for users to understand or presented in an appropriate tone.

[0258] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a data warehouse or data lake, a means for analyzing the stored data and extracting important indicators and trends, a means for automatically generating materials based on the analysis results, a means for acquiring user feedback and analyzing emotions, and a means for adjusting the content of the generated materials based on the emotion analysis results. This enables efficient use of data and flexible generation of materials according to user emotions.

[0259] A "data source" is a system or database that provides information held by a company.

[0260] A "data warehouse" is a structured database that integrates various data from inside and outside a company and is used for analysis and report generation.

[0261] A "data lake" is a data storage facility that stores large amounts of data in various formats in an unstructured state, allowing it to be analyzed and processed.

[0262] "Analytical tools" refer to techniques and methods for examining and processing data to extract important indicators and trends.

[0263] "Key indicators" are the key metrics used to evaluate a company's performance or achievements.

[0264] "Trends" describe changes or patterns in data, identifying long-term trends or short-term anomalies.

[0265] "Means for automatically generating materials" refers to technologies and methods for automatically creating presentation materials and reports based on analysis results.

[0266] "User feedback" refers to opinions and impressions provided by users regarding the generated materials.

[0267] "Means for analyzing emotions" refers to techniques and methods for detecting and analyzing the emotional state from user feedback.

[0268] "Emotion analysis result" refers to the result of analyzing the user's emotional state.

[0269] "Means for adjusting the content of materials" refers to techniques or methods that change the expression or tone of generated materials according to the user's emotions based on the results of emotion analysis.

[0270] The present invention relates to a system that collects, stores, and analyzes data from multiple corporate data sources and automatically generates materials based on the collected data. The purpose of the present invention is to provide effective materials by analyzing user feedback and adjusting the content of the materials according to the user's emotions.

[0271] Data collection

[0272] The server accesses data sources such as a company's customer relationship management system, enterprise resource planning system, and web analytics tool. It uses APIs to retrieve the required data from these systems. For example, it uses a REST API to retrieve customer information from the customer relationship management system and collect financial data from the enterprise resource planning system. This data is temporarily stored in memory.

[0273] Data formatting and storage

[0274] The server converts the collected data into a unified format (for example, CSV or JSON format). Using a data processing library such as Python's Pandas, the data is cleaned to remove incomplete and duplicate data. The cleaned data is stored in a data warehouse such as Amazon Redshift or a data lake such as Apache Hadoop.

[0275] Data analysis

[0276] The server performs data analysis. It uses data analysis libraries such as Python's NumPy and Scikit-learn to perform statistical processing of the data, calculate significant indicators, and detect and remove fraudulent data. It also extracts KPIs and trends. For example, it can extract monthly trends in sales or fluctuations in customer satisfaction.

[0277] Automatic generation of materials

[0278] The server automatically generates presentation materials and financial statements using Microsoft PowerPoint templates based on the analysis results. Graphs and tables are created and inserted into the templates using the Python-pptx library. For example, a graph showing sales over time or a pie chart showing customer satisfaction can be generated.

[0279] Checking and correcting materials

[0280] Users can check the generated data in a web browser and make any necessary corrections. The corrections are recorded using the comment function. For example, users can add feedback such as "Please update the values ​​in this section to the latest ones."

[0281] Approval and Distribution of Materials

[0282] The user then performs a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The distributed document is then saved as an official document.

[0283] Incorporating an emotion engine

[0284] The server collects user feedback and analyzes the user's emotions using an emotion engine such as IBM Watson® Tone Analyzer. The collected emotion data is used to adjust the tone and content of the material. For example, if the user provides feedback that "this content is too difficult," the material can be changed to simpler language.

[0285] Specific examples

[0286] When a company generates monthly financial statements, the server collects data from CRM, ERP, and web analytics tools and stores it in a data warehouse. It then uses a Python library to analyze the data and extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the analysis results. The generated materials are then reviewed by the user in a web browser, and feedback is collected through an emotion engine to adjust the tone of the materials. Finally, the user approves the materials, and the terminal distributes them to relevant parties.

[0287] Prompt Sentence Examples

[0288] "We want to automatically generate monthly financial statements. How can we gather data from our customer management system, enterprise resource planning system, and web analytics tools to create presentations and financial statements that include key metrics and trends?"

[0289] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0290] Step 1: Data collection

[0291] The server runs a regularly scheduled job and sends API requests to each of the company's data sources (e.g., customer management system, enterprise resource planning system, web analytics tool). The API endpoint URL and authentication information are used as input. The data returned in JSON or CSV format is obtained as output. Specific operations include, for example, obtaining customer purchase history and inquiry information from the customer management system.

[0292] Step 2: Data Formatting and Storage

[0293] The server temporarily stores the acquired data in memory and converts data in different formats into a unified format (for example, CSV or JSON). It uses Python's Pandas library to clean the data and remove incomplete and duplicate data. The input is raw data acquired from each data source. The output is cleaned data in a unified format, which is stored in Amazon Redshift or Apache Hadoop. Specifically, it removes duplicate records and imputes missing values.

[0294] Step 3: Data analysis

[0295] The server reads the saved data and performs statistical processing using Python's NumPy and data analysis libraries such as Scikit-learn. It uses the cleaned data as input and extracts key indicators (KPIs) and trends as output. Specifically, it calculates monthly trends in sales and fluctuations in customer satisfaction, and aggregates important KPIs.

[0296] Step 4: Automatic generation of materials

[0297] The server uses Microsoft PowerPoint templates based on the analysis results to create presentation materials and financial statements. Graphs and tables are inserted into the templates using the Python-pptx library. The input is the indicators and trends obtained through data analysis, and the output is a visually easy-to-understand PowerPoint document. Specific operations include generating graphs showing sales over time and pie charts of customer satisfaction and inserting them into the templates.

[0298] Step 5: Check and correct the materials

[0299] The user checks the generated document on a web browser and makes corrections if necessary. The input is the generated document itself, and the output is a revised version that includes feedback from the user. Specifically, the comment function is used to add feedback such as "Please update the values ​​in this section to the latest ones."

[0300] Step 6: Approve and distribute materials

[0301] The user makes a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The input is the revised and approved document, and the output is the official document distributed to the relevant parties. The specific operation is to click the approval button and send the document by email.

[0302] Step 7: Incorporating the Emotion Engine

[0303] The server collects user feedback and reactions during the document review and analyzes the user's emotions using an emotion engine such as IBM Watson Tone Analyzer. The input is the user's feedback comments and reaction data, and the output is the analyzed emotion data. The server then adjusts the tone and content of the document based on this emotion data. Specifically, if the server receives feedback that "this content is too difficult," it changes the tone of the document to be simpler.

[0304] (Application example 2)

[0305] 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."

[0306] Conventional content delivery systems have a problem in that it is difficult to improve user satisfaction because they do not take user emotions into consideration when proposing content or adjusting display methods. In particular, they only provide simple recommendations based on the user's viewing history and interaction data, and are unable to respond to the user's instantaneous emotional state. As a result, the viewing experience is uniform, and flexible content delivery according to the user's preferences and emotions cannot be achieved.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing multiple data sources of a company to collect data, means for storing the collected data in a data warehouse or data lake, means for analyzing the stored data and extracting important indicators and trends, means for automatically generating presentation materials and financial statements based on the analysis results, and means for recognizing the user's emotions and adjusting the content and expression of the materials. This makes it possible to propose flexible and personalized content according to the user's emotions, significantly improving the quality of the viewing experience.

[0308] "Enterprise data sources" refers to sources that store and provide various information, such as an enterprise's internal customer management system, enterprise resource planning system, and web analytics tools.

[0309] A "data warehouse" is a centralized data management system that organizes large amounts of collected data in a unified format and efficiently stores and analyzes them.

[0310] A "data lake" is a data storage system that stores huge amounts of raw data and allows it to be analyzed and used as needed.

[0311] "Key metrics" are numbers or data points that are important to monitor in a business or operation, such as sales or profit margins.

[0312] "Trend" refers to a certain pattern, flow, or fluctuation found in analyzing data, including market trends and user behavior patterns.

[0313] "Data cleaning" is the process of removing incomplete, duplicate, and incorrect information from collected data to make it accurate and consistent.

[0314] "Detecting and removing invalid data" is the act of finding and removing intentionally or accidentally generated incorrect or anomalous data from a dataset.

[0315] "Data aggregation" refers to the classification and totalization of collected data and the compilation of statistical data.

[0316] "Presentation materials" refer to materials that visually organize and effectively communicate analysis results, important indicators, and trends.

[0317] "Financial statements" refer to official documents prepared to detail a company's financial position and performance.

[0318] "Recognizing the user's emotions" means analyzing the user's emotional state at that time from their specific feedback and interaction data.

[0319] "Adjusting the content and expression of the material" refers to the act of modifying the tone, language, and layout of the material based on user sentiment and feedback.

[0320] As an embodiment of the present invention, a system is configured to recognize a user's emotions in a content distribution service and provide personalized content. Specific embodiments are described below.

[0321] System configuration

[0322] The system mainly consists of the following means:

[0323] 1. Data collection methods: In content distribution services, servers access multiple data sources from companies to collect user viewing history, interaction data, etc. This is done using APIs for customer management systems and web analytics tools.

[0324] 2. Data storage: The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, and cleans incomplete and duplicate data before storing it.

[0325] 3. Data Analysis: The server analyzes the stored data and extracts important indicators and trends. This process involves data cleaning, detecting and removing invalid data, and aggregating the data.

[0326] 4. Material and content generation means: This system has a means for automatically generating presentation materials and financial statements based on the analysis results. Furthermore, this invention also includes a means for automatically adjusting content suggestions and display methods using the same analysis results.

[0327] 5. Emotion Recognition: The server uses an emotion analysis engine to recognize the user's emotions using user feedback and interaction data. For example, it uses an API such as Emotion Engine.

[0328] 6. Means for adjusting content and expression: Having means for adjusting the content and expression of materials and content based on the user's emotions.

[0329] Hardware and Software

[0330] Hardware: servers, storage systems to set up a data warehouse or data lake, and network infrastructure

[0331] Software: Data management tools, sentiment analysis engines (e.g., Emotion Engine), data visualization tools

[0332] Processing flow

[0333] The server first collects data such as user viewing history and interaction data and temporarily stores it in memory. It then converts this data into a unified format and stores it in a data warehouse or data lake. It then cleans the data and performs analysis to extract key indicators and trends. Based on the extracted results, it automatically generates and suggests materials and content.

[0334] Using user feedback and interaction data, a sentiment analysis engine can recognize user emotions and adjust the content and presentation of materials and content accordingly, using sentiment analysis tools such as Emotion Engine.

[0335] Specific examples

[0336] In a content distribution service, viewing history and interaction data of a specific user ID are collected, and the most suitable content is suggested to the user by analyzing emotions.

[0337] Prompt Sentence Examples

[0338] Collect viewing history and interaction data for user ID 12345, analyze the user's emotions with a sentiment analysis engine, and suggest appropriate content to the user based on the emotions and collect their feedback.

[0339] The above is an embodiment of the present invention. This system realizes flexible and personalized content provision based on the user's emotions, and can significantly improve the quality of the viewing experience.

[0340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0341] Step 1:

[0342] Data collection

[0343] The server accesses multiple data sources from the company and collects user viewing history and interaction data. Specifically, it uses the APIs of customer management systems and web analytics tools. As input, a user ID is provided. The server makes an API request to obtain viewing history and interaction data from these data sources. As output, it temporarily stores the collected data in memory.

[0344] Step 2:

[0345] Data storage

[0346] The server stores the data collected in step 1 in a data warehouse or data lake. As input, it uses the data temporarily held in memory. Specifically, it converts the data into a unified format and cleans incomplete and duplicate data. After this processing, the server stores the cleaned data in a data warehouse or data lake. As output, the cleaned data is stored in a data warehouse or data lake.

[0347] Step 3:

[0348] Data analysis

[0349] The server analyzes the stored data and extracts key indicators and trends. Data stored in a data warehouse or data lake is used as input. After cleaning the data, detecting and removing fraudulent data, and aggregating the data, the server extracts key indicators (KPIs) and trends from the data. The output is the analysis results.

[0350] Step 4:

[0351] Material and content generation

[0352] The server has the means to automatically generate presentation materials and financial statements based on the analysis results. The analysis results obtained in step 3 are used as input. The server uses templates to insert key indicators and trends into the materials in the appropriate format. The server obtains the generated presentation materials and financial statements as output. In addition, it suggests content and adjusts the display method based on the same analysis results.

[0353] Step 5:

[0354] Emotion recognition

[0355] The server uses the user's feedback and interaction data to use an emotion analysis engine to recognize the user's emotions. The feedback data and interaction data are provided as input. Specifically, the server sends this data to an emotion analysis API (e.g., Emotion Engine) and receives the analysis results. The output is the user's emotional state.

[0356] Step 6:

[0357] Adjustments to content and presentation

[0358] The server has the means to adjust the content and expression of the materials and content based on the user's emotions. The user's emotional state obtained in step 5 and the generated materials and content are used as input. The server adjusts the tone, wording, and layout according to the user's emotions. The adjusted materials and content are obtained as output.

[0359] The above are the specific processing steps of the system that realizes this application example. Each step realizes flexible and personalized content provision based on the user's emotions.

[0360] 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.

[0361] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0362] 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.

[0363] [Second embodiment]

[0364] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0365] 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.

[0366] 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).

[0367] 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.

[0368] 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.

[0369] 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).

[0370] 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.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0375] 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."

[0376] As an embodiment of the present invention, a system is configured as follows to collect data from multiple data sources of a company, store it in a data warehouse or data lake, and automatically compile the analysis results into documents.

[0377] Data collection

[0378] The server accesses each data source of the company (e.g., customer relationship management system, enterprise resource planning system, web analysis tool, etc.) and collects data. The collected data includes sales performance data, financial data, website traffic data, etc. The server obtains the necessary data using the API of each data source and temporarily stores it in memory.

[0379] Data storage

[0380] The server stores the collected data in a data warehouse or data lake. A data warehouse is a system for efficiently storing and quickly accessing structured data, while a data lake is a system for storing structured and unstructured data in its original form at high volume and low cost. The server converts the data into the appropriate format and stores it in these storage systems.

[0381] Data analysis

[0382] The server analyzes the collected and stored data. Using analytical tools (e.g., data visualization tools, BI tools), it performs processes such as cleaning the data, detecting and removing fraudulent data, and aggregating the data. For example, data cleaning involves detecting missing values ​​and outliers and correcting or removing them. Statistical methods and machine learning algorithms are used to detect fraudulent data. This results in reliable data.

[0383] Extracting indicators and trends

[0384] The server extracts key indicators (KPIs) and trends from the analysis results. For example, trends in sales or customer churn. This data is particularly important for business decisions. The server organizes this information and derives conclusions and insights.

[0385] Automatic generation of materials

[0386] The server automatically generates presentations and financial statements based on the extracted analysis results. For example, presentations include visually compiling key indicators into graphs and charts, while financial statements include creating reports containing detailed financial data such as revenue, expenses, and profits. This process involves inserting the results into appropriate formats using predefined templates.

[0387] Checking and correcting materials

[0388] Users can review the generated presentations and financial statements and make corrections as needed. They access the documents through the user interface, enter comments, and make corrections to data. This process ensures that the final documents are accurate and in the correct format.

[0389] Approval and Distribution of Materials

[0390] The user then approves the final revised and confirmed document, after which the device distributes the document to the relevant parties, which may include sending it via email, uploading it to cloud storage, or storing it in a database.

[0391] As a concrete example, consider the process by which a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. The data is then analyzed using a data visualization tool to extract important financial indicators and trends. Based on these results, the server automatically generates presentation materials and financial statements, which are then reviewed and revised by the user and finally distributed to the relevant parties.

[0392] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[0393] The processing flow will be explained below.

[0394] Step 1:

[0395] The server accesses each data source of the company and collects data. Specifically, it uses the APIs of different data sources (e.g., customer management systems, enterprise resource planning systems, web analytics tools) to obtain the required data. Each data source may require access authentication information and queries, so the server sets this information in advance.

[0396] Step 2:

[0397] The server temporarily holds the collected data in memory and stores it in a data warehouse or data lake. Here, the collected data is often provided in different formats, so the server converts the data into a unified format. This conversion process also includes cleaning the data, removing incomplete and duplicate data.

[0398] Step 3:

[0399] The server analyzes the stored data. First, it cleans the data, detecting missing values ​​and outliers and correcting or removing them. Next, it identifies and removes fraudulent data (e.g., abnormally high transaction amounts). After that, it aggregates the data and uses the aggregated results to calculate key performance indicators (KPIs). It also extracts trends based on past data and predicts customer behavior and market fluctuations.

[0400] Step 4:

[0401] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights based on these. During this process, data visualization tools are used to display the results in a visually understandable format.

[0402] Step 5:

[0403] The server automatically generates presentations and financial statements based on the extracted analysis results. The presentations visually display key indicators and trends as graphs and charts. The financial statements contain detailed financial data that allows management to make quick decisions. Templates are used to insert results in the appropriate format.

[0404] Step 6:

[0405] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary corrections. For example, the user can add explanations to graphs or correct annotations on data points. Once the corrections are complete, the user performs a final check of the documents.

[0406] Step 7:

[0407] The user approves the revised document. During the approval process, all revisions are checked to ensure they are properly reflected and officially accepted. The approved document is finally saved as an official document.

[0408] Step 8:

[0409] The device distributes the approved documents to the relevant parties via email, cloud storage sharing, or storing them in an internal company database, depending on the company's needs. This process ensures that all parties involved share the latest information and facilitates smooth decision-making.

[0410] These are the specific steps involved in the process, from data collection to analysis, document creation, and distribution. This system allows companies to obtain important management information efficiently and accurately.

[0411] Example 1

[0412] 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."

[0413] Modern companies need to efficiently manage and analyze large amounts of data collected from a wide variety of sources. However, organizing data provided in different formats and obtaining reliable analytical results is difficult. Furthermore, the process of quickly compiling the analytical results into reports and distributing them to relevant parties is time-consuming. There is a need to solve these issues and improve the efficiency of data processing and reporting.

[0414] 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.

[0415] In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a storage system, and a means for analyzing the stored data and extracting important indicators and trends, thereby enabling data collection from different data sources, data storage and analysis, and automatic generation of report materials.

[0416] "Multiple data sources of an enterprise" refers to multiple information sources that provide data in different formats, such as customer relationship management systems, enterprise resource planning systems, and web analytics tools used by an enterprise.

[0417] A "storage system" is a storage device such as a data warehouse or data lake for storing data efficiently and securely.

[0418] "Data cleaning" is the process of detecting, correcting, or removing missing or outlier values ​​from collected data.

[0419] "Incorrect data detection and removal" refers to the use of machine learning algorithms and statistical methods to identify inaccurate data and remove it from a dataset.

[0420] "Data aggregation" is the process of grouping scattered data points into specific metrics and conducting statistical analysis.

[0421] A "machine learning algorithm" is a mathematical model used to learn patterns in data analysis and perform predictions and clustering.

[0422] "Reliable data" is data whose accuracy and consistency are guaranteed after undergoing data cleaning and removal of inaccurate data.

[0423] "Report materials" are documents including presentation materials and financial statements generated based on the analysis results.

[0424] "End User" refers to the person or department responsible for reviewing, correcting, and ultimately approving the generated materials.

[0425] "Communication means" refers to an email system or cloud sharing service used to distribute the generated materials to relevant parties.

[0426] "Cloud storage" is an online storage service that stores data over the Internet and is accessible to multiple users.

[0427] As an embodiment of the present invention, a system is configured as follows, which collects data from a plurality of data sources of a company, stores the data in a storage system, and automatically compiles the analysis results into report materials.

[0428] Data collection

[0429] The server accesses each company's data source to collect data. It calls the API of each data source using pre-configured API keys and authentication information. During this process, sales performance data, financial data, web traffic data, etc. are collected from customer relationship management systems, enterprise resource planning systems, web analytics tools, etc. The server temporarily stores this data in memory.

[0430] Data storage

[0431] The server stores the collected data in a storage system, specifically a data warehouse such as Amazon Redshift to store structured data and a data lake such as Amazon S3 to store unstructured data. The server converts the data into an appropriate format (e.g., CSV or JSON) and uploads it to these storage systems.

[0432] Data analysis

[0433] The server then analyzes the collected and stored data. It uses data visualization tools such as Tableau and Power BI to perform the analysis. The server first cleans the data and uses statistical methods and machine learning algorithms to detect and correct missing values ​​and outliers. It then aggregates the data and creates graphs and charts to visualize key metrics.

[0434] Extracting indicators and trends

[0435] The server extracts important indicators (KPIs) and business trends from the analysis results. For example, trends in sales and customer attrition. This data is extremely important for making business decisions. The server stores the extracted indicators in a database and uses them to create reports.

[0436] Automatic generation of materials

[0437] The server automatically generates presentation materials and financial statements based on the extracted analysis results. Using templates such as Google Slides and Microsoft PowerPoint, important indicators are displayed visually in easy-to-understand graphs and charts. The generated materials can also be exported in PDF format and saved to cloud storage.

[0438] Checking and correcting materials

[0439] Users can review the generated presentations and financial statements and make corrections as needed. Users log in to a dedicated web interface to view the documents, add comments, and correct incorrect data.

[0440] Approval and Distribution of Materials

[0441] After the user has finalized and approved the document, the device distributes it to the relevant parties. Specifically, the document is sent and shared using an email system or cloud sharing service. In this way, the document that the end user has reviewed, corrected, and approved can be distributed to the relevant parties quickly and efficiently.

[0442] As a concrete example, consider the process when a company generates monthly financial statements. The server collects data from the customer management system and enterprise resource planning system and stores it in Amazon Redshift. It then analyzes the data using Tableau to extract monthly sales trends and customer churn trends. Based on this, the server automatically creates presentation materials and financial statements using Google Slides. The user reviews the materials, makes any necessary revisions, and distributes the final, approved materials to the relevant parties.

[0443] Example prompts for generative AI models

[0444] "Please automatically generate presentation materials and financial statements to analyze this month's sales trends and customer churn trends based on sales performance data and financial data collected from the company's customer relationship management system and enterprise resource planning system."

[0445] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1:

[0448] Data collection

[0449] The server accesses each company's data source and collects data. It uses pre-configured API keys and authentication information as input. Specifically, it performs the following operations:

[0450] The server makes an API call to retrieve sales performance data from the customer relationship management system.

[0451] Make another API call to retrieve financial data from an enterprise resource planning system.

[0452] Make yet another API call to get web traffic data from a web analytics tool.

[0453] As an output, the server temporarily stores the collected data in memory, thus completing the data collection from all data sources.

[0454] Step 2:

[0455] Data storage

[0456] The server stores the collected data in the storage system. As input, it uses the data collected in step 1. Specifically, it performs the following operations.

[0457] The server classifies the collected data into structured data and unstructured data.

[0458] Store structured data in Amazon Redshift (data warehouse) and unstructured data in Amazon S3 (data lake).

[0459] Convert the data into an appropriate format (e.g., CSV or JSON) and upload it to each storage system.

[0460] As an output, the server stores all data in a storage system.

[0461] Step 3:

[0462] Data analysis

[0463] The server analyzes the collected and stored data. It uses the data stored in step 2 as input. Specifically, it performs the following operations:

[0464] The server loads the data into a data visualization tool like Tableau or Power BI.

[0465] Perform data cleaning to detect, correct, or remove missing or outlier values, for example, by imputing missing values ​​with the mean using statistical methods or machine learning algorithms.

[0466] Apply machine learning algorithms to detect and filter out fraudulent data.

[0467] It performs the necessary aggregations and generates visuals such as bar graphs and line charts.

[0468] The output is a reliable analysis result.

[0469] Step 4:

[0470] Extracting indicators and trends

[0471] The server extracts key indicators and trends from the analysis results. It uses the analysis results obtained in step 3 as input. Specifically, it performs the following operations:

[0472] The server extracts important business trends such as sales trends and customer churn trends.

[0473] The extracted indicators are stored in a database for further processing.

[0474] The output is key metrics and business trends.

[0475] Step 5:

[0476] Automatic generation of materials

[0477] The server automatically generates presentation materials and financial statements based on the extracted analysis results. As input, it uses the indicators and trends obtained in step 4. Specifically, it performs the following operations:

[0478] The server loads Google Slides or Microsoft PowerPoint templates and prepares the slide structure.

[0479] Insert KPI graphs and charts into the template to make them visually easy to understand.

[0480] Export the generated documents in PDF format and temporarily save them in cloud storage.

[0481] As output, presentation materials and financial statements are generated.

[0482] Step 6:

[0483] Checking and correcting materials

[0484] The user checks the generated presentation materials and financial statements and makes any necessary corrections. The materials generated in step 5 are used as input. Specifically, the following operations are performed:

[0485] Users log in to a dedicated web interface to view the generated materials.

[0486] Users can add comments to documents and correct erroneous data if necessary.

[0487] When the user has completed the corrections, he or she presses the "Confirm" button.

[0488] The output is the corrected and verified material.

[0489] Step 7:

[0490] Approval and Distribution of Materials

[0491] The user finally approves the corrected and confirmed materials. The confirmed and corrected materials from step 6 are used as input. Specifically, the following operations are performed:

[0492] The user makes a final check of the materials and presses the "Approve" button.

[0493] The terminal sends the approved documents to the relevant parties by email.

[0494] The device uploads the materials to cloud storage and generates a sharing link.

[0495] The device notifies the relevant parties of the generated shared link and provides them with access to the materials.

[0496] The output is the final approved and distributed material.

[0497] (Application example 1)

[0498] 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."

[0499] Traditional factory operations required the manual collection and analysis of information from many data sources, which hindered efforts to improve production efficiency and reduce failure rates. It was particularly difficult to collect large amounts of data, properly analyze it, extract key indicators, and then quickly take specific action based on them. As a result, it was difficult for management and on-site managers to make decisions, hindering the optimization of operations.

[0500] 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.

[0501] In this invention, the server includes: means for accessing multiple data sources within a company to collect data; means for storing the collected data in a data warehouse or data lake; means for analyzing the stored data and extracting important indicators and trends; and means for automatically generating reports based on the analysis results and analyzing production efficiency and failure rates based on data from equipment and sensors within the factory. This automates data collection and analysis from each data source, enabling the rapid extraction and reporting of important indicators and trends. Furthermore, the generated reports can be reviewed, revised, and approved by the user, supporting optimal decision-making and achieving more efficient factory operations and reduced failure rates.

[0502] "Data sources" refers to the multiple information sources that a company has, such as customer relationship management systems, enterprise resource planning systems, web analytics tools, and equipment and sensors in factories.

[0503] A "data warehouse" is a system for efficiently storing large amounts of structured data and enabling fast access.

[0504] A "data lake" is a system that stores structured and unstructured data in its original form at high volume and low cost.

[0505] "Analysis" refers to the process of cleaning, transforming, aggregating, detecting and removing fraudulent data from collected and stored data, and extracting important indicators and trends.

[0506] "Indicators" are important numerical values ​​or indicators extracted as a result of data analysis, and include, for example, production efficiency, failure rate, inventory turnover rate, etc.

[0507] "Trend" refers to patterns or trends in data that are revealed through data analysis, such as changes in sales or an increasing trend in breakdowns.

[0508] A "report" is a document automatically generated based on the analysis results, which includes detailed information on production efficiency and failure rates.

[0509] "User" refers to the person responsible for reviewing generated reports, making corrections and approvals, and ultimately distributing the materials.

[0510] "System" refers to an integrated set of equipment and software for carrying out a series of processes including data collection, data storage, data analysis, extraction of indicators and trends, report generation, and user review, correction, and approval.

[0511] As an embodiment of the present invention, a specific system configuration of a factory operations management assistant application will be described. This system collects information from multiple data sources within a company and stores it in a data warehouse or data lake. It also analyzes the collected data to extract important indicators and trends and automatically generates reports.

[0512] System Configuration

[0513] Data collection

[0514] The server collects data from each piece of equipment and sensor in the factory via API. This data collection is performed using a Python script, which obtains the necessary data from the IoT sensors via REST API and temporarily stores it in memory.

[0515] Data storage

[0516] The server stores the collected data in a data warehouse or data lake. Specifically, it uses Python scripts to store the data in AWS S3 and then in AWS Redshift (a data warehouse). This allows for efficient and low-cost management of large amounts of data.

[0517] Data analysis

[0518] The server analyzes the data using BI and data visualization tools, particularly Tableau, for data cleansing, analysis, and dashboard creation, and utilizes machine learning libraries such as scikit-learn to detect fraudulent data.

[0519] Extracting indicators and trends

[0520] Extract important KPIs from the analysis results, such as production efficiency, failure rate, and inventory turnover. By linking Python and Tableau, extract these indicators and clarify trends.

[0521] Automatic generation of materials

[0522] The server automatically generates reports based on the extracted KPIs and trends, and the reports are created according to predefined templates and presented in a visually easy-to-understand format.

[0523] User confirmation and correction

[0524] Users can view and edit the generated reports through a web interface, using a web framework such as Django to make it easier for users to add comments and edit the reports.

[0525] Approval and Distribution of Materials

[0526] After the user checks and modifies the report, they finally approve it. Approved documents are distributed to the relevant parties, sent via email, or uploaded to cloud storage.

[0527] Specific examples

[0528] For example, when managing a factory's production efficiency, this system works as follows: First, data from each production line is collected, stored in AWS S3, and managed using AWS Redshift. The data is then analyzed using Tableau to extract trends in production efficiency and failure rates. Based on this, reports are automatically generated, and managers can review, modify, and ultimately approve the reports through a Django-based web interface.

[0529] Prompt Sentence Examples

[0530] "Please develop an app that analyzes production efficiency and failure rate data within the factory and automatically generates monthly reports. The app will collect, save, analyze, extract KPIs, and automatically generate reports, and provide an interface that allows managers to easily check and modify the data."

[0531] In this way, the system of the present invention helps optimize factory operations, enabling efficient data management and analysis, and rapid report generation.

[0532] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0533] Step 1:

[0534] The server collects data from each piece of equipment and sensor in the factory. Specifically, it runs a Python script to obtain production data from each IoT sensor through a REST API. The input is the API endpoint and authentication information of each sensor. After collecting the data, this data is temporarily stored in memory. The output is a set of collected production data.

[0535] Step 2:

[0536] The server stores the collected data in a data warehouse or data lake. Specifically, a Python script is used to store the data in AWS S3 and then ingest it into AWS Redshift. The input is the production data collected in step 1, and the output is the data stored in AWS S3 and AWS Redshift. This process includes data format conversion and operations for storing it in appropriate storage.

[0537] Step 3:

[0538] The server analyzes the stored data. First, it cleanses the data using Tableau to detect and remove missing values ​​and outliers. Next, it applies a machine learning model using the scikit-learn library to detect fraudulent data. The input is the data stored in AWS Redshift, and the output is the analyzed data after cleansing and fraud detection.

[0539] Step 4:

[0540] The server extracts key metrics and trends. Python scripts and Tableau are used in conjunction with the server to calculate KPIs (e.g., production efficiency, failure rate, inventory turnover) and derive trends. The cleansed and fraud-detected data is used as input. The output is the extracted key metrics and their trend data.

[0541] Step 5:

[0542] The server automatically generates reports based on the analysis results. It uses Python and Tableau to create reports according to predefined templates. It uses extracted KPIs and trend data as input. The output is an automatically generated report. The report summarizes the data in a visually easy-to-understand format.

[0543] Step 6:

[0544] Users can view and modify the generated reports through a web interface. Using an interface based on the Django framework, users can check the report content and add data and comments as needed. The input is the automatically generated report, and the output is the reviewed and modified report.

[0545] Step 7:

[0546] The user approves the revised report, and the server distributes it to the relevant parties. The approved report is sent by email or uploaded to cloud storage. The input is the reviewed and revised report, and the output is the final, distributed report. Through this process, the relevant parties can quickly obtain the latest production information.

[0547] 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.

[0548] As an embodiment of the present invention, a system is configured as follows: it collects data from multiple corporate data sources, stores and analyzes it in a data warehouse or data lake, and automatically generates materials based on the analysis results. In addition, by combining it with an emotion engine that recognizes the user's emotions, the content and expression of the materials are adjusted according to the user's emotions.

[0549] Data collection

[0550] The server accesses each data source of the company and collects data. For example, it obtains the necessary data using APIs of customer management systems, enterprise resource planning systems, web analytics tools, etc. The data from each data source is temporarily stored in memory.

[0551] Data storage

[0552] The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, cleans incomplete and duplicate data, and stores it.

[0553] Data analysis

[0554] The server analyzes the data stored on it, cleaning it, detecting and removing fraudulent data, aggregating it, and extracting key performance indicators (KPIs) and trends.

[0555] Automatic generation of materials

[0556] The server automatically generates presentation materials and financial statements based on the analysis results. It creates presentation materials that visually display key indicators and trends, and financial statements that include detailed financial data. It uses templates to insert results in the appropriate format.

[0557] Checking and correcting materials

[0558] The user checks the generated presentation materials and financial statements. The user accesses the materials, reviews them, and makes corrections as necessary. Once corrections are complete, the user performs a final check of the materials.

[0559] Approval and Distribution of Materials

[0560] The user approves the revised document. The approval process checks whether all revisions are reflected and officially accepts the document. The approved document is saved as an official document. The terminal distributes the document to the relevant parties.

[0561] Incorporating an emotion engine

[0562] The server collects user feedback and uses an emotion engine to recognize the user's emotions. For example, if a user expresses dissatisfaction or concern about the content of a presentation, the emotion engine analyzes that emotion and instructs the system to adjust the content and expression of the presentation. Specifically, the system makes adjustments based on the user's emotions, such as changing the tone of the presentation or adding additional explanations.

[0563] Specific examples

[0564] Consider a case where a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. It then analyzes the data using a data visualization tool to extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the extracted results. The generated materials are reviewed by the user, and after recognizing the user's emotions through an emotion engine, the content of the materials is adjusted as necessary. Finally, the user approves the materials, and the terminal distributes them to the relevant parties.

[0565] In this way, by incorporating an emotion engine, it becomes possible to create more user-friendly documents, and a system can be provided that supports efficient and effective decision-making in companies.

[0566] The processing flow will be explained below.

[0567] Step 1:

[0568] The server accesses each data source of the company and collects the necessary data. For example, it retrieves sales performance data using the API of a customer management system, financial data from an enterprise resource planning system, and website traffic data from a web analytics tool. This data is temporarily stored in memory.

[0569] Step 2:

[0570] The server stores the collected data in a data warehouse or data lake. The data is often provided in different formats, and the server converts the data into a unified format. The conversion process also includes cleaning the data, removing incomplete and duplicate data.

[0571] Step 3:

[0572] The server analyzes the stored data. First, it cleans the data, then detects and removes any irregularities (e.g., abnormally high transaction amounts), then aggregates the data and calculates key performance indicators (KPIs). It also extracts trends based on past data.

[0573] Step 4:

[0574] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights. During this process, data visualization tools are used to display the results in a visually understandable format.

[0575] Step 5:

[0576] The server automatically generates presentations and financial statements based on the extracted analysis results. Presentations include visual displays of key indicators and trends as graphs and charts, while financial statements include detailed financial data. Templates are used to insert results in the appropriate format.

[0577] Step 6:

[0578] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary edits. For example, the user can add explanations to graphs or edit annotations for data points. Once edits are complete, the user performs a final review of the documents.

[0579] Step 7:

[0580] The emotion engine receives user feedback and recognizes the user's emotions. For example, if the user expresses dissatisfaction or concern, the emotion engine analyzes that emotion. Based on the user's emotions, the engine suggests modifications based on the user's emotions, such as changing the tone of the material or adding additional explanations.

[0581] Step 8:

[0582] The user reviews the revised document again and makes any necessary final adjustments. If the user is satisfied with the results of the revisions, they approve the document. This process ensures that the document is finally completed accurately and in the appropriate format.

[0583] Step 9:

[0584] The user reviews the final approved material and officially accepts it. The approved material is finally saved as an official document.

[0585] Step 10:

[0586] The terminal distributes approved documents to the relevant parties. Distribution methods include sending emails, uploading to cloud storage, and saving to the company's internal database. This allows all parties involved to share the latest information and facilitates smooth decision-making.

[0587] These are the specific steps in a company's data collection, analysis, document creation, and distribution. This system makes it possible to create documents that take user emotions into account, allowing companies to obtain important management information more efficiently and accurately.

[0588] Example 2

[0589] 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."

[0590] Modern companies possess large amounts of data, but it is difficult to efficiently collect, store, and analyze that data, and automatically generate materials to help with decision-making. Furthermore, because the content of the generated materials does not change based on the user's emotions, there is no guarantee that the materials will be easy for users to understand or presented in an appropriate tone.

[0591] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a data warehouse or data lake, a means for analyzing the stored data and extracting important indicators and trends, a means for automatically generating materials based on the analysis results, a means for acquiring user feedback and analyzing emotions, and a means for adjusting the content of the generated materials based on the emotion analysis results. This enables efficient use of data and flexible generation of materials according to user emotions.

[0592] A "data source" is a system or database that provides information held by a company.

[0593] A "data warehouse" is a structured database that integrates various data from inside and outside a company and is used for analysis and report generation.

[0594] A "data lake" is a data storage facility that stores large amounts of data in various formats in an unstructured state, allowing it to be analyzed and processed.

[0595] "Analytical tools" refer to techniques and methods for examining and processing data to extract important indicators and trends.

[0596] "Key indicators" are the key metrics used to evaluate a company's performance or achievements.

[0597] "Trends" describe changes or patterns in data, identifying long-term trends or short-term anomalies.

[0598] "Means for automatically generating materials" refers to technologies and methods for automatically creating presentation materials and reports based on analysis results.

[0599] "User feedback" refers to opinions and impressions provided by users regarding the generated materials.

[0600] "Means for analyzing emotions" refers to techniques and methods for detecting and analyzing the emotional state from user feedback.

[0601] "Emotion analysis result" refers to the result of analyzing the user's emotional state.

[0602] "Means for adjusting the content of materials" refers to techniques or methods that change the expression or tone of generated materials according to the user's emotions based on the results of emotion analysis.

[0603] The present invention relates to a system that collects, stores, and analyzes data from multiple corporate data sources and automatically generates materials based on the collected data. The purpose of the present invention is to provide effective materials by analyzing user feedback and adjusting the content of the materials according to the user's emotions.

[0604] Data collection

[0605] The server accesses data sources such as a company's customer relationship management system, enterprise resource planning system, and web analytics tool. It uses APIs to retrieve the required data from these systems. For example, it uses a REST API to retrieve customer information from the customer relationship management system and collect financial data from the enterprise resource planning system. This data is temporarily stored in memory.

[0606] Data formatting and storage

[0607] The server converts the collected data into a unified format (such as CSV or JSON). It then uses a data processing library such as Python's Pandas to clean the data and remove incomplete and duplicate data. The cleaned data is then stored in a data warehouse such as Amazon Redshift or a data lake such as Apache Hadoop.

[0608] Data analysis

[0609] The server performs data analysis. It uses data analysis libraries such as Python's NumPy and Scikit-learn to perform statistical processing of the data, calculate significant indicators, and detect and remove fraudulent data. It also extracts KPIs and trends. For example, it can extract monthly trends in sales or fluctuations in customer satisfaction.

[0610] Automatic generation of materials

[0611] The server automatically generates presentation materials and financial statements using Microsoft PowerPoint templates based on the analysis results. Graphs and tables are created and inserted into the templates using the Python-pptx library. For example, a graph showing sales over time or a pie chart showing customer satisfaction can be generated.

[0612] Checking and correcting materials

[0613] Users can check the generated data in a web browser and make any necessary corrections. The corrections are recorded using the comment function. For example, users can add feedback such as "Please update the values ​​in this section to the latest ones."

[0614] Approval and Distribution of Materials

[0615] The user then performs a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The distributed document is then saved as an official document.

[0616] Incorporating an emotion engine

[0617] The server collects user feedback and analyzes the user's emotions using an emotion engine such as IBM Watson Tone Analyzer. The collected emotion data is used to adjust the tone and content of the material. For example, if the user gives feedback that "this content is too difficult," the material will be changed to simpler language.

[0618] Specific examples

[0619] When a company generates monthly financial statements, the server collects data from CRM, ERP, and web analytics tools and stores it in a data warehouse. It then uses a Python library to analyze the data and extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the analysis results. The generated materials are then reviewed by the user in a web browser, and feedback is collected through an emotion engine to adjust the tone of the materials. Finally, the user approves the materials, and the terminal distributes them to relevant parties.

[0620] Prompt Sentence Examples

[0621] "We want to automatically generate monthly financial statements. How can we gather data from our customer management system, enterprise resource planning system, and web analytics tools to create presentations and financial statements that include key metrics and trends?"

[0622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0623] Step 1: Data collection

[0624] The server runs a regularly scheduled job and sends API requests to each of the company's data sources (e.g., customer management system, enterprise resource planning system, web analytics tool). The API endpoint URL and authentication information are used as input. The data returned in JSON or CSV format is obtained as output. Specific operations include, for example, obtaining customer purchase history and inquiry information from the customer management system.

[0625] Step 2: Data Formatting and Storage

[0626] The server temporarily stores the acquired data in memory and converts data in different formats into a unified format (for example, CSV or JSON). It uses Python's Pandas library to clean the data and remove incomplete and duplicate data. The input is raw data acquired from each data source. The output is cleaned data in a unified format, which is stored in Amazon Redshift or Apache Hadoop. Specifically, it removes duplicate records and imputes missing values.

[0627] Step 3: Data analysis

[0628] The server reads the saved data and performs statistical processing using Python's NumPy and data analysis libraries such as Scikit-learn. It uses the cleaned data as input and extracts key indicators (KPIs) and trends as output. Specifically, it calculates monthly trends in sales and fluctuations in customer satisfaction, and aggregates important KPIs.

[0629] Step 4: Automatic generation of materials

[0630] The server uses Microsoft PowerPoint templates based on the analysis results to create presentation materials and financial statements. Graphs and tables are inserted into the templates using the Python-pptx library. The input is the indicators and trends obtained through data analysis, and the output is a visually easy-to-understand PowerPoint document. Specific operations include generating graphs showing sales over time and pie charts of customer satisfaction and inserting them into the templates.

[0631] Step 5: Check and correct the materials

[0632] The user checks the generated document on a web browser and makes corrections if necessary. The input is the generated document itself, and the output is a revised version that includes feedback from the user. Specifically, the comment function is used to add feedback such as "Please update the values ​​in this section to the latest ones."

[0633] Step 6: Approve and distribute materials

[0634] The user makes a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The input is the revised and approved document, and the output is the official document distributed to the relevant parties. The specific operation is to click the approval button and send the document by email.

[0635] Step 7: Incorporating the Emotion Engine

[0636] The server collects user feedback and reactions during the document review and analyzes the user's emotions using an emotion engine such as IBM Watson Tone Analyzer. The input is the user's feedback comments and reaction data, and the output is the analyzed emotion data. The server then adjusts the tone and content of the document based on this emotion data. Specifically, if the server receives feedback that "this content is too difficult," it changes the tone of the document to be simpler.

[0637] (Application example 2)

[0638] 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."

[0639] Conventional content delivery systems have a problem in that it is difficult to improve user satisfaction because they do not take user emotions into consideration when proposing content or adjusting display methods. In particular, they only provide simple recommendations based on the user's viewing history and interaction data, and are unable to respond to the user's instantaneous emotional state. As a result, the viewing experience is uniform, and flexible content delivery according to the user's preferences and emotions cannot be achieved.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing multiple data sources of a company to collect data, means for storing the collected data in a data warehouse or data lake, means for analyzing the stored data and extracting important indicators and trends, means for automatically generating presentation materials and financial statements based on the analysis results, and means for recognizing the user's emotions and adjusting the content and expression of the materials. This makes it possible to propose flexible and personalized content according to the user's emotions, significantly improving the quality of the viewing experience.

[0641] "Enterprise data sources" refers to sources that store and provide various information, such as an enterprise's internal customer management system, enterprise resource planning system, and web analytics tools.

[0642] A "data warehouse" is a centralized data management system that organizes large amounts of collected data in a unified format and efficiently stores and analyzes them.

[0643] A "data lake" is a data storage system that stores huge amounts of raw data and allows it to be analyzed and used as needed.

[0644] "Key metrics" are numbers or data points that are important to monitor in a business or operation, such as sales or profit margins.

[0645] "Trend" refers to a certain pattern, flow, or fluctuation found in analyzing data, including market trends and user behavior patterns.

[0646] "Data cleaning" is the process of removing incomplete, duplicate, and incorrect information from collected data to make it accurate and consistent.

[0647] "Detecting and removing invalid data" is the act of finding and removing intentionally or accidentally generated incorrect or anomalous data from a dataset.

[0648] "Data aggregation" refers to the classification and totalization of collected data and the compilation of statistical data.

[0649] "Presentation materials" refer to materials that visually organize and effectively communicate analysis results, important indicators, and trends.

[0650] "Financial statements" refer to official documents prepared to detail a company's financial position and performance.

[0651] "Recognizing the user's emotions" means analyzing the user's emotional state at that time from their specific feedback and interaction data.

[0652] "Adjusting the content and expression of the material" refers to the act of modifying the tone, language, and layout of the material based on user sentiment and feedback.

[0653] As an embodiment of the present invention, a system is configured to recognize a user's emotions in a content distribution service and provide personalized content. Specific embodiments are described below.

[0654] System configuration

[0655] The system mainly consists of the following means:

[0656] 1. Data collection methods: In content distribution services, servers access multiple data sources from companies to collect user viewing history, interaction data, etc. This is done using APIs for customer management systems and web analytics tools.

[0657] 2. Data storage: The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, and cleans incomplete and duplicate data before storing it.

[0658] 3. Data Analysis: The server analyzes the stored data and extracts important indicators and trends. This process involves data cleaning, detecting and removing invalid data, and aggregating the data.

[0659] 4. Material and content generation means: This system has a means for automatically generating presentation materials and financial statements based on the analysis results. Furthermore, this invention also includes a means for automatically adjusting content suggestions and display methods using the same analysis results.

[0660] 5. Emotion Recognition: The server uses an emotion analysis engine to recognize the user's emotions using user feedback and interaction data. For example, it uses an API such as Emotion Engine.

[0661] 6. Means for adjusting content and expression: Having means for adjusting the content and expression of materials and content based on the user's emotions.

[0662] Hardware and Software

[0663] Hardware: servers, storage systems to set up a data warehouse or data lake, and network infrastructure

[0664] Software: Data management tools, sentiment analysis engines (e.g., Emotion Engine), data visualization tools

[0665] Processing flow

[0666] The server first collects data such as user viewing history and interaction data and temporarily stores it in memory. It then converts this data into a unified format and stores it in a data warehouse or data lake. It then cleans the data and performs analysis to extract key indicators and trends. Based on the extracted results, it automatically generates and suggests materials and content.

[0667] Using user feedback and interaction data, a sentiment analysis engine can recognize user emotions and adjust the content and presentation of materials and content accordingly, using sentiment analysis tools such as Emotion Engine.

[0668] Specific examples

[0669] In a content distribution service, viewing history and interaction data of a specific user ID are collected, and the most suitable content is suggested to the user by analyzing emotions.

[0670] Prompt Sentence Examples

[0671] Collect viewing history and interaction data for user ID 12345, analyze the user's emotions with a sentiment analysis engine, and suggest appropriate content to the user based on the emotions and collect their feedback.

[0672] The above is an embodiment of the present invention. This system realizes flexible and personalized content provision based on the user's emotions, and can significantly improve the quality of the viewing experience.

[0673] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0674] Step 1:

[0675] Data collection

[0676] The server accesses multiple data sources from the company and collects user viewing history and interaction data. Specifically, it uses the APIs of customer management systems and web analytics tools. As input, a user ID is provided. The server makes an API request to obtain viewing history and interaction data from these data sources. As output, it temporarily stores the collected data in memory.

[0677] Step 2:

[0678] Data storage

[0679] The server stores the data collected in step 1 in a data warehouse or data lake. As input, it uses the data temporarily held in memory. Specifically, it converts the data into a unified format and cleans incomplete and duplicate data. After this processing, the server stores the cleaned data in a data warehouse or data lake. As output, the cleaned data is stored in a data warehouse or data lake.

[0680] Step 3:

[0681] Data analysis

[0682] The server analyzes the stored data and extracts key indicators and trends. Data stored in a data warehouse or data lake is used as input. After cleaning the data, detecting and removing fraudulent data, and aggregating the data, the server extracts key indicators (KPIs) and trends from the data. The output is the analysis results.

[0683] Step 4:

[0684] Material and content generation

[0685] The server has the means to automatically generate presentation materials and financial statements based on the analysis results. The analysis results obtained in step 3 are used as input. The server uses templates to insert key indicators and trends into the materials in the appropriate format. The server obtains the generated presentation materials and financial statements as output. In addition, it suggests content and adjusts the display method based on the same analysis results.

[0686] Step 5:

[0687] Emotion recognition

[0688] The server uses the user's feedback and interaction data to use an emotion analysis engine to recognize the user's emotions. The feedback data and interaction data are provided as input. Specifically, the server sends this data to an emotion analysis API (e.g., Emotion Engine) and receives the analysis results. The output is the user's emotional state.

[0689] Step 6:

[0690] Adjustments to content and presentation

[0691] The server has the means to adjust the content and expression of the materials and content based on the user's emotions. The user's emotional state obtained in step 5 and the generated materials and content are used as input. The server adjusts the tone, wording, and layout according to the user's emotions. The adjusted materials and content are obtained as output.

[0692] The above are the specific processing steps of the system that realizes this application example. Each step realizes flexible and personalized content provision based on the user's emotions.

[0693] 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.

[0694] 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.

[0695] 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.

[0696] [Third embodiment]

[0697] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0698] 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.

[0699] 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).

[0700] 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.

[0701] 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.

[0702] 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).

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] 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."

[0709] As an embodiment of the present invention, a system is configured as follows to collect data from multiple data sources of a company, store it in a data warehouse or data lake, and automatically compile the analysis results into documents.

[0710] Data collection

[0711] The server accesses each data source of the company (e.g., customer relationship management system, enterprise resource planning system, web analysis tool, etc.) and collects data. The collected data includes sales performance data, financial data, website traffic data, etc. The server obtains the necessary data using the API of each data source and temporarily stores it in memory.

[0712] Data storage

[0713] The server stores the collected data in a data warehouse or data lake. A data warehouse is a system for efficiently storing and quickly accessing structured data, while a data lake is a system for storing structured and unstructured data in its original form at high volume and low cost. The server converts the data into the appropriate format and stores it in these storage systems.

[0714] Data analysis

[0715] The server analyzes the collected and stored data. Using analytical tools (e.g., data visualization tools, BI tools), it performs processes such as cleaning the data, detecting and removing fraudulent data, and aggregating the data. For example, data cleaning involves detecting missing values ​​and outliers and correcting or removing them. Statistical methods and machine learning algorithms are used to detect fraudulent data. This results in reliable data.

[0716] Extracting indicators and trends

[0717] The server extracts key indicators (KPIs) and trends from the analysis results. For example, trends in sales or customer churn. This data is particularly important for business decisions. The server organizes this information and derives conclusions and insights.

[0718] Automatic generation of materials

[0719] The server automatically generates presentations and financial statements based on the extracted analysis results. For example, presentations include visually compiling key indicators into graphs and charts, while financial statements include creating reports containing detailed financial data such as revenue, expenses, and profits. This process involves inserting the results into appropriate formats using predefined templates.

[0720] Checking and correcting materials

[0721] Users can review the generated presentations and financial statements and make corrections as needed. They access the documents through the user interface, enter comments, and make corrections to data. This process ensures that the final documents are accurate and in the correct format.

[0722] Approval and Distribution of Materials

[0723] The user then approves the final revised and confirmed document, after which the device distributes the document to the relevant parties, which may include sending it via email, uploading it to cloud storage, or storing it in a database.

[0724] As a concrete example, consider the process by which a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. The data is then analyzed using a data visualization tool to extract important financial indicators and trends. Based on these results, the server automatically generates presentation materials and financial statements, which are then reviewed and revised by the user and finally distributed to the relevant parties.

[0725] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[0726] The processing flow will be explained below.

[0727] Step 1:

[0728] The server accesses each data source of the company and collects data. Specifically, it uses the APIs of different data sources (e.g., customer management systems, enterprise resource planning systems, web analytics tools) to obtain the required data. Each data source may require access authentication information and queries, so the server sets this information in advance.

[0729] Step 2:

[0730] The server temporarily holds the collected data in memory and stores it in a data warehouse or data lake. Here, the collected data is often provided in different formats, so the server converts the data into a unified format. This conversion process also includes cleaning the data, removing incomplete and duplicate data.

[0731] Step 3:

[0732] The server analyzes the stored data. First, it cleans the data, detecting missing values ​​and outliers and correcting or removing them. Next, it identifies and removes fraudulent data (e.g., abnormally high transaction amounts). After that, it aggregates the data and uses the aggregated results to calculate key performance indicators (KPIs). It also extracts trends based on past data and predicts customer behavior and market fluctuations.

[0733] Step 4:

[0734] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights based on these. During this process, data visualization tools are used to display the results in a visually understandable format.

[0735] Step 5:

[0736] The server automatically generates presentations and financial statements based on the extracted analysis results. The presentations visually display key indicators and trends as graphs and charts. The financial statements contain detailed financial data that allows management to make quick decisions. Templates are used to insert results in the appropriate format.

[0737] Step 6:

[0738] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary corrections. For example, the user can add explanations to graphs or correct annotations on data points. Once the corrections are complete, the user performs a final check of the documents.

[0739] Step 7:

[0740] The user approves the revised document. During the approval process, all revisions are checked to ensure they are properly reflected and officially accepted. The approved document is finally saved as an official document.

[0741] Step 8:

[0742] The device distributes the approved documents to the relevant parties via email, cloud storage sharing, or storing them in an internal company database, depending on the company's needs. This process ensures that all parties involved share the latest information and facilitates smooth decision-making.

[0743] These are the specific steps involved in the process, from data collection to analysis, document creation, and distribution. This system allows companies to obtain important management information efficiently and accurately.

[0744] Example 1

[0745] 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."

[0746] Modern companies need to efficiently manage and analyze large amounts of data collected from a wide variety of sources. However, organizing data provided in different formats and obtaining reliable analytical results is difficult. Furthermore, the process of quickly compiling the analytical results into reports and distributing them to relevant parties is time-consuming. There is a need to solve these issues and improve the efficiency of data processing and reporting.

[0747] 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.

[0748] In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a storage system, and a means for analyzing the stored data and extracting important indicators and trends, thereby enabling data collection from different data sources, data storage and analysis, and automatic generation of report materials.

[0749] "Multiple data sources of an enterprise" refers to multiple information sources that provide data in different formats, such as customer relationship management systems, enterprise resource planning systems, and web analytics tools used by an enterprise.

[0750] A "storage system" is a storage device such as a data warehouse or data lake for storing data efficiently and securely.

[0751] "Data cleaning" is the process of detecting, correcting, or removing missing or outlier values ​​from collected data.

[0752] "Incorrect data detection and removal" refers to the use of machine learning algorithms and statistical methods to identify inaccurate data and remove it from a dataset.

[0753] "Data aggregation" is the process of grouping scattered data points into specific metrics and conducting statistical analysis.

[0754] A "machine learning algorithm" is a mathematical model used to learn patterns in data analysis and perform predictions and clustering.

[0755] "Reliable data" is data whose accuracy and consistency are guaranteed after undergoing data cleaning and removal of inaccurate data.

[0756] "Report materials" are documents including presentation materials and financial statements generated based on the analysis results.

[0757] "End User" refers to the person or department responsible for reviewing, correcting, and ultimately approving the generated materials.

[0758] "Communication means" refers to an email system or cloud sharing service used to distribute the generated materials to relevant parties.

[0759] "Cloud storage" is an online storage service that stores data over the Internet and is accessible to multiple users.

[0760] As an embodiment of the present invention, a system is configured as follows, which collects data from a plurality of data sources of a company, stores the data in a storage system, and automatically compiles the analysis results into report materials.

[0761] Data collection

[0762] The server accesses each company's data source to collect data. It calls the API of each data source using pre-configured API keys and authentication information. During this process, sales performance data, financial data, web traffic data, etc. are collected from customer relationship management systems, enterprise resource planning systems, web analytics tools, etc. The server temporarily stores this data in memory.

[0763] Data storage

[0764] The server stores the collected data in a storage system, specifically a data warehouse such as Amazon Redshift to store structured data and a data lake such as Amazon S3 to store unstructured data. The server converts the data into an appropriate format (e.g., CSV or JSON) and uploads it to these storage systems.

[0765] Data analysis

[0766] The server then analyzes the collected and stored data. It uses data visualization tools such as Tableau and Power BI to perform the analysis. The server first cleans the data and uses statistical methods and machine learning algorithms to detect and correct missing values ​​and outliers. It then aggregates the data and creates graphs and charts to visualize key metrics.

[0767] Extracting indicators and trends

[0768] The server extracts important indicators (KPIs) and business trends from the analysis results. For example, trends in sales and customer attrition. This data is extremely important for making business decisions. The server stores the extracted indicators in a database and uses them to create reports.

[0769] Automatic generation of materials

[0770] The server automatically generates presentation materials and financial statements based on the extracted analysis results. Using templates such as Google Slides and Microsoft PowerPoint, important indicators are displayed visually in easy-to-understand graphs and charts. The generated materials can also be exported in PDF format and saved to cloud storage.

[0771] Checking and correcting materials

[0772] Users can review the generated presentations and financial statements and make corrections as needed. Users log in to a dedicated web interface to view the documents, add comments, and correct incorrect data.

[0773] Approval and Distribution of Materials

[0774] After the user has finalized and approved the document, the device distributes it to the relevant parties. Specifically, the document is sent and shared using an email system or cloud sharing service. In this way, the document that the end user has reviewed, corrected, and approved can be distributed to the relevant parties quickly and efficiently.

[0775] As a concrete example, consider the process when a company generates monthly financial statements. The server collects data from the customer management system and enterprise resource planning system and stores it in Amazon Redshift. It then analyzes the data using Tableau to extract monthly sales trends and customer churn trends. Based on this, the server automatically creates presentation materials and financial statements using Google Slides. The user reviews the materials, makes any necessary revisions, and distributes the final, approved materials to the relevant parties.

[0776] Example prompts for generative AI models

[0777] "Please automatically generate presentation materials and financial statements to analyze this month's sales trends and customer churn trends based on sales performance data and financial data collected from the company's customer relationship management system and enterprise resource planning system."

[0778] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[0779] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0780] Step 1:

[0781] Data collection

[0782] The server accesses each company's data source and collects data. It uses pre-configured API keys and authentication information as input. Specifically, it performs the following operations:

[0783] The server makes an API call to retrieve sales performance data from the customer relationship management system.

[0784] Make another API call to retrieve financial data from an enterprise resource planning system.

[0785] Make yet another API call to get web traffic data from a web analytics tool.

[0786] As an output, the server temporarily stores the collected data in memory, thus completing the data collection from all data sources.

[0787] Step 2:

[0788] Data storage

[0789] The server stores the collected data in the storage system. As input, it uses the data collected in step 1. Specifically, it performs the following operations.

[0790] The server classifies the collected data into structured data and unstructured data.

[0791] Store structured data in Amazon Redshift (data warehouse) and unstructured data in Amazon S3 (data lake).

[0792] Convert the data into an appropriate format (e.g., CSV or JSON) and upload it to each storage system.

[0793] As an output, the server stores all data in a storage system.

[0794] Step 3:

[0795] Data analysis

[0796] The server analyzes the collected and stored data. It uses the data stored in step 2 as input. Specifically, it performs the following operations:

[0797] The server loads the data into a data visualization tool like Tableau or Power BI.

[0798] Perform data cleaning to detect, correct, or remove missing or outlier values, for example, by imputing missing values ​​with the mean using statistical methods or machine learning algorithms.

[0799] Apply machine learning algorithms to detect and filter out fraudulent data.

[0800] It performs the necessary aggregations and generates visuals such as bar graphs and line charts.

[0801] The output is a reliable analysis result.

[0802] Step 4:

[0803] Extracting indicators and trends

[0804] The server extracts key indicators and trends from the analysis results, using the analysis results obtained in step 3 as input. Specifically, it performs the following operations:

[0805] The server extracts important business trends such as sales trends and customer churn trends.

[0806] The extracted indicators are stored in a database for further processing.

[0807] The output is key metrics and business trends.

[0808] Step 5:

[0809] Automatic generation of materials

[0810] The server automatically generates presentation materials and financial statements based on the extracted analysis results. As input, it uses the indicators and trends obtained in step 4. Specifically, it performs the following operations:

[0811] The server loads Google Slides or Microsoft PowerPoint templates and prepares the slide structure.

[0812] Insert KPI graphs and charts into the template to make them visually easy to understand.

[0813] Export the generated documents in PDF format and temporarily save them in cloud storage.

[0814] As output, presentation materials and financial statements are generated.

[0815] Step 6:

[0816] Checking and correcting materials

[0817] The user checks the generated presentation materials and financial statements and makes any necessary corrections. The materials generated in step 5 are used as input. Specifically, the following operations are performed:

[0818] Users log in to a dedicated web interface to view the generated materials.

[0819] Users can add comments to documents and correct erroneous data if necessary.

[0820] When the user has completed the corrections, he or she presses the "Confirm" button.

[0821] The output is the corrected and verified material.

[0822] Step 7:

[0823] Approval and Distribution of Materials

[0824] The user finally approves the corrected and confirmed materials. The confirmed and corrected materials from step 6 are used as input. Specifically, the following operations are performed:

[0825] The user makes a final check of the materials and presses the "Approve" button.

[0826] The terminal sends the approved documents to the relevant parties by email.

[0827] The device uploads the materials to cloud storage and generates a sharing link.

[0828] The device notifies the relevant parties of the generated shared link and provides them with access to the materials.

[0829] The output is the final approved and distributed material.

[0830] (Application example 1)

[0831] 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."

[0832] Traditional factory operations required the manual collection and analysis of information from many data sources, which hindered efforts to improve production efficiency and reduce failure rates. It was particularly difficult to collect large amounts of data, properly analyze it, extract key indicators, and then quickly take specific action based on them. As a result, it was difficult for management and on-site managers to make decisions, hindering the optimization of operations.

[0833] 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.

[0834] In this invention, the server includes: means for accessing multiple data sources within a company to collect data; means for storing the collected data in a data warehouse or data lake; means for analyzing the stored data and extracting important indicators and trends; and means for automatically generating reports based on the analysis results and analyzing production efficiency and failure rates based on data from equipment and sensors within the factory. This automates data collection and analysis from each data source, enabling the rapid extraction and reporting of important indicators and trends. Furthermore, the generated reports can be reviewed, revised, and approved by the user, supporting optimal decision-making and achieving more efficient factory operations and reduced failure rates.

[0835] "Data sources" refers to the multiple information sources that a company has, such as customer relationship management systems, enterprise resource planning systems, web analytics tools, and equipment and sensors in factories.

[0836] A "data warehouse" is a system for efficiently storing large amounts of structured data and enabling fast access.

[0837] A "data lake" is a system that stores structured and unstructured data in its original form at high volume and low cost.

[0838] "Analysis" refers to the process of cleaning, transforming, aggregating, detecting and removing fraudulent data from collected and stored data, and extracting important indicators and trends.

[0839] "Indicators" are important numerical values ​​or indicators extracted as a result of data analysis, and include, for example, production efficiency, failure rate, inventory turnover rate, etc.

[0840] "Trend" refers to patterns or trends in data that are revealed through data analysis, such as changes in sales or an increasing trend in breakdowns.

[0841] A "report" is a document automatically generated based on the analysis results, which includes detailed information on production efficiency and failure rates.

[0842] "User" refers to the person responsible for reviewing generated reports, making corrections and approvals, and ultimately distributing the materials.

[0843] "System" refers to an integrated set of equipment and software for carrying out a series of processes including data collection, data storage, data analysis, extraction of indicators and trends, report generation, and user review, correction, and approval.

[0844] As an embodiment of the present invention, a specific system configuration of a factory operations management assistant application will be described. This system collects information from multiple data sources within a company and stores it in a data warehouse or data lake. It also analyzes the collected data to extract important indicators and trends and automatically generates reports.

[0845] System Configuration

[0846] Data collection

[0847] The server collects data from each piece of equipment and sensor in the factory via API. This data collection is performed using a Python script, which obtains the necessary data from the IoT sensors via REST API and temporarily stores it in memory.

[0848] Data storage

[0849] The server stores the collected data in a data warehouse or data lake. Specifically, it uses Python scripts to store the data in AWS S3 and then in AWS Redshift (a data warehouse). This allows for efficient and low-cost management of large amounts of data.

[0850] Data analysis

[0851] The server analyzes the data using BI and data visualization tools, particularly Tableau, for data cleansing, analysis, and dashboard creation, and utilizes machine learning libraries such as scikit-learn to detect fraudulent data.

[0852] Extracting indicators and trends

[0853] Extract important KPIs from the analysis results, such as production efficiency, failure rate, and inventory turnover. By linking Python and Tableau, extract these indicators and clarify trends.

[0854] Automatic generation of materials

[0855] The server automatically generates reports based on the extracted KPIs and trends, and the reports are created according to predefined templates and presented in a visually easy-to-understand format.

[0856] User confirmation and correction

[0857] Users can view and edit the generated reports through a web interface, using a web framework such as Django to make it easier for users to add comments and edit the reports.

[0858] Approval and Distribution of Materials

[0859] After the user checks and modifies the report, they finally approve it. Approved documents are distributed to the relevant parties, sent via email, or uploaded to cloud storage.

[0860] Specific examples

[0861] For example, when managing a factory's production efficiency, this system works as follows: First, data from each production line is collected, stored in AWS S3, and managed using AWS Redshift. The data is then analyzed using Tableau to extract trends in production efficiency and failure rates. Based on this, reports are automatically generated, and managers can review, modify, and ultimately approve the reports through a Django-based web interface.

[0862] Prompt Sentence Examples

[0863] "Please develop an app that analyzes production efficiency and failure rate data within the factory and automatically generates monthly reports. The app will collect, save, analyze, extract KPIs, and automatically generate reports, and provide an interface that allows managers to easily check and modify the data."

[0864] In this way, the system of the present invention helps optimize factory operations, enabling efficient data management and analysis, and rapid report generation.

[0865] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0866] Step 1:

[0867] The server collects data from each piece of equipment and sensor in the factory. Specifically, it runs a Python script to obtain production data from each IoT sensor through a REST API. The input is the API endpoint and authentication information of each sensor. After collecting the data, this data is temporarily stored in memory. The output is a set of collected production data.

[0868] Step 2:

[0869] The server stores the collected data in a data warehouse or data lake. Specifically, a Python script is used to store the data in AWS S3 and then ingest it into AWS Redshift. The input is the production data collected in step 1, and the output is the data stored in AWS S3 and AWS Redshift. This process includes data format conversion and operations for storing it in appropriate storage.

[0870] Step 3:

[0871] The server analyzes the stored data. First, it cleanses the data using Tableau to detect and remove missing values ​​and outliers. Next, it applies a machine learning model using the scikit-learn library to detect fraudulent data. The input is the data stored in AWS Redshift, and the output is the analyzed data after cleansing and fraud detection.

[0872] Step 4:

[0873] The server extracts key metrics and trends. Python scripts and Tableau are used in conjunction with the server to calculate KPIs (e.g., production efficiency, failure rate, inventory turnover) and derive trends. The cleansed and fraud-detected data is used as input. The output is the extracted key metrics and their trend data.

[0874] Step 5:

[0875] The server automatically generates reports based on the analysis results. It uses Python and Tableau to create reports according to predefined templates. It uses extracted KPIs and trend data as input. The output is an automatically generated report. The report summarizes the data in a visually easy-to-understand format.

[0876] Step 6:

[0877] Users can view and modify the generated reports through a web interface. Using an interface based on the Django framework, users can check the report content and add data and comments as needed. The input is the automatically generated report, and the output is the reviewed and modified report.

[0878] Step 7:

[0879] The user approves the revised report, and the server distributes it to the relevant parties. The approved report is sent by email or uploaded to cloud storage. The input is the reviewed and revised report, and the output is the final, distributed report. Through this process, the relevant parties can quickly obtain the latest production information.

[0880] 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.

[0881] As an embodiment of the present invention, a system is configured as follows: it collects data from multiple corporate data sources, stores and analyzes it in a data warehouse or data lake, and automatically generates materials based on the analysis results. In addition, by combining it with an emotion engine that recognizes the user's emotions, the content and expression of the materials are adjusted according to the user's emotions.

[0882] Data collection

[0883] The server accesses each data source of the company and collects data. For example, it obtains the necessary data using APIs of customer management systems, enterprise resource planning systems, web analytics tools, etc. The data from each data source is temporarily stored in memory.

[0884] Data storage

[0885] The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, cleans incomplete and duplicate data, and stores it.

[0886] Data analysis

[0887] The server analyzes the data stored on it, cleaning it, detecting and removing fraudulent data, aggregating it, and extracting key performance indicators (KPIs) and trends.

[0888] Automatic generation of materials

[0889] The server automatically generates presentation materials and financial statements based on the analysis results. It creates presentation materials that visually display key indicators and trends, and financial statements that include detailed financial data. It uses templates to insert results in the appropriate format.

[0890] Checking and correcting materials

[0891] The user checks the generated presentation materials and financial statements. The user accesses the materials, reviews them, and makes corrections as necessary. Once corrections are complete, the user performs a final check of the materials.

[0892] Approval and Distribution of Materials

[0893] The user approves the revised document. The approval process checks whether all revisions are reflected and officially accepts the document. The approved document is saved as an official document. The terminal distributes the document to the relevant parties.

[0894] Incorporating an emotion engine

[0895] The server collects user feedback and uses an emotion engine to recognize the user's emotions. For example, if a user expresses dissatisfaction or concern about the content of a presentation, the emotion engine analyzes that emotion and instructs the system to adjust the content and expression of the presentation. Specifically, the system makes adjustments based on the user's emotions, such as changing the tone of the presentation or adding additional explanations.

[0896] Specific examples

[0897] Consider a case where a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. It then analyzes the data using a data visualization tool to extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the extracted results. The generated materials are reviewed by the user, and after recognizing the user's emotions through an emotion engine, the content of the materials is adjusted as necessary. Finally, the user approves the materials, and the terminal distributes them to the relevant parties.

[0898] In this way, by incorporating an emotion engine, it becomes possible to create more user-friendly documents, and a system can be provided that supports efficient and effective decision-making in companies.

[0899] The processing flow will be explained below.

[0900] Step 1:

[0901] The server accesses each data source of the company and collects the necessary data. For example, it retrieves sales performance data using the API of a customer management system, financial data from an enterprise resource planning system, and website traffic data from a web analytics tool. This data is temporarily stored in memory.

[0902] Step 2:

[0903] The server stores the collected data in a data warehouse or data lake. The data is often provided in different formats, and the server converts the data into a unified format. The conversion process also includes cleaning the data, removing incomplete and duplicate data.

[0904] Step 3:

[0905] The server analyzes the stored data. First, it cleans the data, then detects and removes any irregularities (e.g., abnormally high transaction amounts), then aggregates the data and calculates key performance indicators (KPIs). It also extracts trends based on past data.

[0906] Step 4:

[0907] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights. During this process, data visualization tools are used to display the results in a visually understandable format.

[0908] Step 5:

[0909] The server automatically generates presentations and financial statements based on the extracted analysis results. Presentations include visual displays of key indicators and trends as graphs and charts, while financial statements include detailed financial data. Templates are used to insert results in the appropriate format.

[0910] Step 6:

[0911] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary edits. For example, the user can add explanations to graphs or edit annotations for data points. Once edits are complete, the user performs a final review of the documents.

[0912] Step 7:

[0913] The emotion engine receives user feedback and recognizes the user's emotions. For example, if the user expresses dissatisfaction or concern, the emotion engine analyzes that emotion. Based on the user's emotions, the engine suggests modifications based on the user's emotions, such as changing the tone of the material or adding additional explanations.

[0914] Step 8:

[0915] The user reviews the revised document again and makes any necessary final adjustments. If the user is satisfied with the results of the revisions, they approve the document. This process ensures that the document is finally completed accurately and in the appropriate format.

[0916] Step 9:

[0917] The user reviews the final approved material and officially accepts it. The approved material is finally saved as an official document.

[0918] Step 10:

[0919] The terminal distributes approved documents to the relevant parties. Distribution methods include sending emails, uploading to cloud storage, and saving to the company's internal database. This allows all parties involved to share the latest information and facilitates smooth decision-making.

[0920] These are the specific steps in a company's data collection, analysis, document creation, and distribution. This system makes it possible to create documents that take user emotions into account, allowing companies to obtain important management information more efficiently and accurately.

[0921] Example 2

[0922] 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."

[0923] Modern companies possess large amounts of data, but it is difficult to efficiently collect, store, and analyze that data, and automatically generate materials to help with decision-making. Furthermore, because the content of the generated materials does not change based on the user's emotions, there is no guarantee that the materials will be easy for users to understand or presented in an appropriate tone.

[0924] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a data warehouse or data lake, a means for analyzing the stored data and extracting important indicators and trends, a means for automatically generating materials based on the analysis results, a means for acquiring user feedback and analyzing emotions, and a means for adjusting the content of the generated materials based on the emotion analysis results. This enables efficient use of data and flexible generation of materials according to user emotions.

[0925] A "data source" is a system or database that provides information held by a company.

[0926] A "data warehouse" is a structured database that integrates various data from inside and outside a company and is used for analysis and report generation.

[0927] A "data lake" is a data storage facility that stores large amounts of data in various formats in an unstructured state, allowing it to be analyzed and processed.

[0928] "Analytical tools" refer to techniques and methods for examining and processing data to extract important indicators and trends.

[0929] "Key indicators" are the key metrics used to evaluate a company's performance or achievements.

[0930] "Trends" describe changes or patterns in data, identifying long-term trends or short-term anomalies.

[0931] "Means for automatically generating materials" refers to technologies and methods for automatically creating presentation materials and reports based on analysis results.

[0932] "User feedback" refers to opinions and impressions provided by users regarding the generated materials.

[0933] "Means for analyzing emotions" refers to techniques and methods for detecting and analyzing the emotional state from user feedback.

[0934] "Emotion analysis result" refers to the result of analyzing the user's emotional state.

[0935] "Means for adjusting the content of materials" refers to techniques or methods that change the expression or tone of generated materials according to the user's emotions based on the results of emotion analysis.

[0936] The present invention relates to a system that collects, stores, and analyzes data from multiple corporate data sources and automatically generates materials based on the collected data. The purpose of the present invention is to provide effective materials by analyzing user feedback and adjusting the content of the materials according to the user's emotions.

[0937] Data collection

[0938] The server accesses data sources such as a company's customer relationship management system, enterprise resource planning system, and web analytics tool. It uses APIs to retrieve the required data from these systems. For example, it uses a REST API to retrieve customer information from the customer relationship management system and collect financial data from the enterprise resource planning system. This data is temporarily stored in memory.

[0939] Data formatting and storage

[0940] The server converts the collected data into a unified format (such as CSV or JSON). It then uses a data processing library such as Python's Pandas to clean the data and remove incomplete and duplicate data. The cleaned data is then stored in a data warehouse such as Amazon Redshift or a data lake such as Apache Hadoop.

[0941] Data analysis

[0942] The server performs data analysis. It uses data analysis libraries such as Python's NumPy and Scikit-learn to perform statistical processing of the data, calculate significant indicators, and detect and remove fraudulent data. It also extracts KPIs and trends. For example, it can extract monthly trends in sales or fluctuations in customer satisfaction.

[0943] Automatic generation of materials

[0944] The server automatically generates presentation materials and financial statements using Microsoft PowerPoint templates based on the analysis results. Graphs and tables are created and inserted into the templates using the Python-pptx library. For example, a graph showing sales over time or a pie chart showing customer satisfaction can be generated.

[0945] Checking and correcting materials

[0946] Users can check the generated data in a web browser and make any necessary corrections. The corrections are recorded using the comment function. For example, users can add feedback such as "Please update the values ​​in this section to the latest ones."

[0947] Approval and Distribution of Materials

[0948] The user then performs a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The distributed document is then saved as an official document.

[0949] Incorporating an emotion engine

[0950] The server collects user feedback and analyzes the user's emotions using an emotion engine such as IBM Watson Tone Analyzer. The collected emotion data is used to adjust the tone and content of the material. For example, if the user gives feedback that "this content is too difficult," the material will be changed to simpler language.

[0951] Specific examples

[0952] When a company generates monthly financial statements, the server collects data from CRM, ERP, and web analytics tools and stores it in a data warehouse. It then uses a Python library to analyze the data and extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the analysis results. The generated materials are then reviewed by the user in a web browser, and feedback is collected through an emotion engine to adjust the tone of the materials. Finally, the user approves the materials, and the terminal distributes them to relevant parties.

[0953] Prompt Sentence Examples

[0954] "We want to automatically generate monthly financial statements. How can we gather data from our customer management system, enterprise resource planning system, and web analytics tools to create presentations and financial statements that include key metrics and trends?"

[0955] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0956] Step 1: Data collection

[0957] The server runs a regularly scheduled job and sends API requests to each of the company's data sources (e.g., customer management system, enterprise resource planning system, web analytics tool). The API endpoint URL and authentication information are used as input. The data returned in JSON or CSV format is obtained as output. Specific operations include, for example, obtaining customer purchase history and inquiry information from the customer management system.

[0958] Step 2: Data Formatting and Storage

[0959] The server temporarily stores the acquired data in memory and converts data in different formats into a unified format (for example, CSV or JSON). It uses Python's Pandas library to clean the data and remove incomplete and duplicate data. The input is raw data acquired from each data source. The output is cleaned data in a unified format, which is stored in Amazon Redshift or Apache Hadoop. Specifically, it removes duplicate records and imputes missing values.

[0960] Step 3: Data analysis

[0961] The server reads the saved data and performs statistical processing using Python's NumPy and data analysis libraries such as Scikit-learn. It uses the cleaned data as input and extracts key indicators (KPIs) and trends as output. Specifically, it calculates monthly trends in sales and fluctuations in customer satisfaction, and aggregates important KPIs.

[0962] Step 4: Automatic generation of materials

[0963] The server uses Microsoft PowerPoint templates based on the analysis results to create presentation materials and financial statements. Graphs and tables are inserted into the templates using the Python-pptx library. The input is the indicators and trends obtained through data analysis, and the output is a visually easy-to-understand PowerPoint document. Specific operations include generating graphs showing sales over time and pie charts of customer satisfaction and inserting them into the templates.

[0964] Step 5: Check and correct the materials

[0965] The user checks the generated document on a web browser and makes corrections if necessary. The input is the generated document itself, and the output is a revised version that includes feedback from the user. Specifically, the comment function is used to add feedback such as "Please update the values ​​in this section to the latest ones."

[0966] Step 6: Approve and distribute materials

[0967] The user makes a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The input is the revised and approved document, and the output is the official document distributed to the relevant parties. The specific operation is to click the approval button and send the document by email.

[0968] Step 7: Incorporating the Emotion Engine

[0969] The server collects user feedback and reactions during the document review and analyzes the user's emotions using an emotion engine such as IBM Watson Tone Analyzer. The input is the user's feedback comments and reaction data, and the output is the analyzed emotion data. The server then adjusts the tone and content of the document based on this emotion data. Specifically, if the server receives feedback that "this content is too difficult," it changes the tone of the document to be simpler.

[0970] (Application example 2)

[0971] 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."

[0972] Conventional content delivery systems have a problem in that it is difficult to improve user satisfaction because they do not take user emotions into consideration when proposing content or adjusting display methods. In particular, they only provide simple recommendations based on the user's viewing history and interaction data, and are unable to respond to the user's instantaneous emotional state. As a result, the viewing experience is uniform, and flexible content delivery according to the user's preferences and emotions cannot be achieved.

[0973] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing multiple data sources of a company to collect data, means for storing the collected data in a data warehouse or data lake, means for analyzing the stored data and extracting important indicators and trends, means for automatically generating presentation materials and financial statements based on the analysis results, and means for recognizing the user's emotions and adjusting the content and expression of the materials. This makes it possible to propose flexible and personalized content according to the user's emotions, significantly improving the quality of the viewing experience.

[0974] "Enterprise data sources" refers to sources that store and provide various information, such as an enterprise's internal customer management system, enterprise resource planning system, and web analytics tools.

[0975] A "data warehouse" is a centralized data management system that organizes large amounts of collected data in a unified format and efficiently stores and analyzes them.

[0976] A "data lake" is a data storage system that stores huge amounts of raw data and allows it to be analyzed and used as needed.

[0977] "Key metrics" are numbers or data points that are important to monitor in a business or operation, such as sales or profit margins.

[0978] "Trend" refers to a certain pattern, flow, or fluctuation found in analyzing data, including market trends and user behavior patterns.

[0979] "Data cleaning" is the process of removing incomplete, duplicate, and incorrect information from collected data to make it accurate and consistent.

[0980] "Detecting and removing invalid data" is the act of finding and removing intentionally or accidentally generated incorrect or anomalous data from a dataset.

[0981] "Data aggregation" refers to the classification and totalization of collected data and the compilation of statistical data.

[0982] "Presentation materials" refer to materials that visually organize and effectively communicate analysis results, important indicators, and trends.

[0983] "Financial statements" refer to official documents prepared to detail a company's financial position and performance.

[0984] "Recognizing the user's emotions" means analyzing the user's emotional state at that time from their specific feedback and interaction data.

[0985] "Adjusting the content and expression of the material" refers to the act of modifying the tone, language, and layout of the material based on user sentiment and feedback.

[0986] As an embodiment of the present invention, a system is configured to recognize a user's emotions in a content distribution service and provide personalized content. Specific embodiments are described below.

[0987] System configuration

[0988] The system mainly consists of the following means:

[0989] 1. Data collection methods: In content distribution services, servers access multiple data sources from companies to collect user viewing history, interaction data, etc. This is done using APIs for customer management systems and web analytics tools.

[0990] 2. Data storage: The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, and cleans incomplete and duplicate data before storing it.

[0991] 3. Data Analysis: The server analyzes the stored data and extracts important indicators and trends. This process involves data cleaning, detecting and removing invalid data, and aggregating the data.

[0992] 4. Material and content generation means: This system has a means for automatically generating presentation materials and financial statements based on the analysis results. Furthermore, this invention also includes a means for automatically adjusting content suggestions and display methods using the same analysis results.

[0993] 5. Emotion Recognition: The server uses an emotion analysis engine to recognize the user's emotions using user feedback and interaction data. For example, it uses an API such as Emotion Engine.

[0994] 6. Means for adjusting content and expression: Having means for adjusting the content and expression of materials and content based on the user's emotions.

[0995] Hardware and Software

[0996] Hardware: servers, storage systems to set up a data warehouse or data lake, and network infrastructure

[0997] Software: Data management tools, sentiment analysis engines (e.g., Emotion Engine), data visualization tools

[0998] Processing flow

[0999] The server first collects data such as user viewing history and interaction data and temporarily stores it in memory. It then converts this data into a unified format and stores it in a data warehouse or data lake. It then cleans the data and performs analysis to extract key indicators and trends. Based on the extracted results, it automatically generates and suggests materials and content.

[1000] Using user feedback and interaction data, a sentiment analysis engine can recognize user emotions and adjust the content and presentation of materials and content accordingly, using sentiment analysis tools such as Emotion Engine.

[1001] Specific examples

[1002] In a content distribution service, viewing history and interaction data of a specific user ID are collected, and the most suitable content is suggested to the user by analyzing emotions.

[1003] Prompt Sentence Examples

[1004] Collect viewing history and interaction data for user ID 12345, analyze the user's emotions with a sentiment analysis engine, and suggest appropriate content to the user based on the emotions and collect their feedback.

[1005] The above is an embodiment of the present invention. This system realizes flexible and personalized content provision based on the user's emotions, and can significantly improve the quality of the viewing experience.

[1006] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1007] Step 1:

[1008] Data collection

[1009] The server accesses multiple data sources from the company and collects user viewing history and interaction data. Specifically, it uses the APIs of customer management systems and web analytics tools. As input, a user ID is provided. The server makes an API request to obtain viewing history and interaction data from these data sources. As output, it temporarily stores the collected data in memory.

[1010] Step 2:

[1011] Data storage

[1012] The server stores the data collected in step 1 in a data warehouse or data lake. As input, it uses the data temporarily held in memory. Specifically, it converts the data into a unified format and cleans incomplete and duplicate data. After this processing, the server stores the cleaned data in a data warehouse or data lake. As output, the cleaned data is stored in a data warehouse or data lake.

[1013] Step 3:

[1014] Data analysis

[1015] The server analyzes the stored data and extracts key indicators and trends. Data stored in a data warehouse or data lake is used as input. After cleaning the data, detecting and removing fraudulent data, and aggregating the data, the server extracts key indicators (KPIs) and trends from the data. The output is the analysis results.

[1016] Step 4:

[1017] Material and content generation

[1018] The server has the means to automatically generate presentation materials and financial statements based on the analysis results. The analysis results obtained in step 3 are used as input. The server uses templates to insert key indicators and trends into the materials in the appropriate format. The server obtains the generated presentation materials and financial statements as output. In addition, it suggests content and adjusts the display method based on the same analysis results.

[1019] Step 5:

[1020] Emotion recognition

[1021] The server uses the user's feedback and interaction data to use an emotion analysis engine to recognize the user's emotions. The feedback data and interaction data are provided as input. Specifically, the server sends this data to an emotion analysis API (e.g., Emotion Engine) and receives the analysis results. The output is the user's emotional state.

[1022] Step 6:

[1023] Adjustments to content and presentation

[1024] The server has the means to adjust the content and expression of the materials and content based on the user's emotions. The user's emotional state obtained in step 5 and the generated materials and content are used as input. The server adjusts the tone, wording, and layout according to the user's emotions. The adjusted materials and content are obtained as output.

[1025] The above are the specific processing steps of the system that realizes this application example. Each step realizes flexible and personalized content provision based on the user's emotions.

[1026] 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.

[1027] 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.

[1028] 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.

[1029] [Fourth embodiment]

[1030] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1031] 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.

[1032] 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).

[1033] 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.

[1034] 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.

[1035] 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).

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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.

[1041] 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.

[1042] 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."

[1043] As an embodiment of the present invention, a system is configured as follows to collect data from multiple data sources of a company, store it in a data warehouse or data lake, and automatically compile the analysis results into documents.

[1044] Data collection

[1045] The server accesses each data source of the company (e.g., customer relationship management system, enterprise resource planning system, web analysis tool, etc.) and collects data. The collected data includes sales performance data, financial data, website traffic data, etc. The server obtains the necessary data using the API of each data source and temporarily stores it in memory.

[1046] Data storage

[1047] The server stores the collected data in a data warehouse or data lake. A data warehouse is a system for efficiently storing and quickly accessing structured data, while a data lake is a system for storing structured and unstructured data in its original form at high volume and low cost. The server converts the data into the appropriate format and stores it in these storage systems.

[1048] Data analysis

[1049] The server analyzes the collected and stored data. Using analytical tools (e.g., data visualization tools, BI tools), it performs processes such as cleaning the data, detecting and removing fraudulent data, and aggregating the data. For example, data cleaning involves detecting missing values ​​and outliers and correcting or removing them. Statistical methods and machine learning algorithms are used to detect fraudulent data. This results in reliable data.

[1050] Extracting indicators and trends

[1051] The server extracts key indicators (KPIs) and trends from the analysis results. For example, trends in sales or customer churn. This data is particularly important for business decisions. The server organizes this information and derives conclusions and insights.

[1052] Automatic generation of materials

[1053] The server automatically generates presentations and financial statements based on the extracted analysis results. For example, presentations include visually compiling key indicators into graphs and charts, while financial statements include creating reports containing detailed financial data such as revenue, expenses, and profits. This process involves inserting the results into appropriate formats using predefined templates.

[1054] Checking and correcting materials

[1055] Users can review the generated presentations and financial statements and make corrections as needed. They access the documents through the user interface, enter comments, and make corrections to data. This process ensures that the final documents are accurate and in the correct format.

[1056] Approval and Distribution of Materials

[1057] The user then approves the final revised and confirmed document, after which the device distributes the document to the relevant parties, which may include sending it via email, uploading it to cloud storage, or storing it in a database.

[1058] As a concrete example, consider the process by which a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. The data is then analyzed using a data visualization tool to extract important financial indicators and trends. Based on these results, the server automatically generates presentation materials and financial statements, which are then reviewed and revised by the user and finally distributed to the relevant parties.

[1059] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[1060] The processing flow will be explained below.

[1061] Step 1:

[1062] The server accesses each data source of the company and collects data. Specifically, it uses the APIs of different data sources (e.g., customer management systems, enterprise resource planning systems, web analytics tools) to obtain the required data. Each data source may require access authentication information and queries, so the server sets this information in advance.

[1063] Step 2:

[1064] The server temporarily holds the collected data in memory and stores it in a data warehouse or data lake. Here, the collected data is often provided in different formats, so the server converts the data into a unified format. This conversion process also includes cleaning the data, removing incomplete and duplicate data.

[1065] Step 3:

[1066] The server analyzes the stored data. First, it cleans the data, detecting missing values ​​and outliers and correcting or removing them. Next, it identifies and removes fraudulent data (e.g., abnormally high transaction amounts). After that, it aggregates the data and uses the aggregated results to calculate key performance indicators (KPIs). It also extracts trends based on past data and predicts customer behavior and market fluctuations.

[1067] Step 4:

[1068] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights based on these. During this process, data visualization tools are used to display the results in a visually understandable format.

[1069] Step 5:

[1070] The server automatically generates presentations and financial statements based on the extracted analysis results. The presentations visually display key indicators and trends as graphs and charts. The financial statements contain detailed financial data that allows management to make quick decisions. Templates are used to insert results in the appropriate format.

[1071] Step 6:

[1072] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary corrections. For example, the user can add explanations to graphs or correct annotations on data points. Once the corrections are complete, the user performs a final check of the documents.

[1073] Step 7:

[1074] The user approves the revised document. During the approval process, all revisions are checked to ensure they are properly reflected and officially accepted. The approved document is finally saved as an official document.

[1075] Step 8:

[1076] The device distributes the approved documents to the relevant parties via email, cloud storage sharing, or storing them in an internal company database, depending on the company's needs. This process ensures that all parties involved share the latest information and facilitates smooth decision-making.

[1077] These are the specific steps involved in the process, from data collection to analysis, document creation, and distribution. This system allows companies to obtain important management information efficiently and accurately.

[1078] Example 1

[1079] 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."

[1080] Modern companies need to efficiently manage and analyze large amounts of data collected from a wide variety of sources. However, organizing data provided in different formats and obtaining reliable analytical results is difficult. Furthermore, the process of quickly compiling the analytical results into reports and distributing them to relevant parties is time-consuming. There is a need to solve these issues and improve the efficiency of data processing and reporting.

[1081] 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.

[1082] In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a storage system, and a means for analyzing the stored data and extracting important indicators and trends, thereby enabling data collection from different data sources, data storage and analysis, and automatic generation of report materials.

[1083] "Multiple data sources of an enterprise" refers to multiple information sources that provide data in different formats, such as customer relationship management systems, enterprise resource planning systems, and web analytics tools used by an enterprise.

[1084] A "storage system" is a storage device such as a data warehouse or data lake for storing data efficiently and securely.

[1085] "Data cleaning" is the process of detecting, correcting, or removing missing or outlier values ​​from collected data.

[1086] "Incorrect data detection and removal" refers to the use of machine learning algorithms and statistical methods to identify inaccurate data and remove it from a dataset.

[1087] "Data aggregation" is the process of grouping scattered data points into specific metrics and conducting statistical analysis.

[1088] A "machine learning algorithm" is a mathematical model used to learn patterns in data analysis and perform predictions and clustering.

[1089] "Reliable data" is data whose accuracy and consistency are guaranteed after undergoing data cleaning and removal of inaccurate data.

[1090] "Report materials" are documents including presentation materials and financial statements generated based on the analysis results.

[1091] "End User" refers to the person or department responsible for reviewing, correcting, and ultimately approving the generated materials.

[1092] "Communication means" refers to an email system or cloud sharing service used to distribute the generated materials to relevant parties.

[1093] "Cloud storage" is an online storage service that stores data over the Internet and is accessible to multiple users.

[1094] As an embodiment of the present invention, a system is configured as follows, which collects data from a plurality of data sources of a company, stores the data in a storage system, and automatically compiles the analysis results into report materials.

[1095] Data collection

[1096] The server accesses each company's data source to collect data. It calls the API of each data source using pre-configured API keys and authentication information. During this process, sales performance data, financial data, web traffic data, etc. are collected from customer relationship management systems, enterprise resource planning systems, web analytics tools, etc. The server temporarily stores this data in memory.

[1097] Data storage

[1098] The server stores the collected data in a storage system, specifically a data warehouse such as Amazon Redshift to store structured data and a data lake such as Amazon S3 to store unstructured data. The server converts the data into an appropriate format (e.g., CSV or JSON) and uploads it to these storage systems.

[1099] Data analysis

[1100] The server then analyzes the collected and stored data. It uses data visualization tools such as Tableau and Power BI to perform the analysis. The server first cleans the data and uses statistical methods and machine learning algorithms to detect and correct missing values ​​and outliers. It then aggregates the data and creates graphs and charts to visualize key metrics.

[1101] Extracting indicators and trends

[1102] The server extracts important indicators (KPIs) and business trends from the analysis results. For example, trends in sales and customer attrition. This data is extremely important for making business decisions. The server stores the extracted indicators in a database and uses them to create reports.

[1103] Automatic generation of materials

[1104] The server automatically generates presentation materials and financial statements based on the extracted analysis results. Using templates such as Google Slides and Microsoft PowerPoint, important indicators are displayed visually in easy-to-understand graphs and charts. The generated materials can also be exported in PDF format and saved to cloud storage.

[1105] Checking and correcting materials

[1106] Users can review the generated presentations and financial statements and make corrections as needed. Users log in to a dedicated web interface to view the documents, add comments, and correct incorrect data.

[1107] Approval and Distribution of Materials

[1108] After the user has finalized and approved the document, the device distributes it to the relevant parties. Specifically, the document is sent and shared using an email system or cloud sharing service. In this way, the document that the end user has reviewed, corrected, and approved can be distributed to the relevant parties quickly and efficiently.

[1109] As a concrete example, consider the process when a company generates monthly financial statements. The server collects data from the customer management system and enterprise resource planning system and stores it in Amazon Redshift. It then analyzes the data using Tableau to extract monthly sales trends and customer churn trends. Based on this, the server automatically creates presentation materials and financial statements using Google Slides. The user reviews the materials, makes any necessary revisions, and distributes the final, approved materials to the relevant parties.

[1110] Example prompts for generative AI models

[1111] "Please automatically generate presentation materials and financial statements to analyze this month's sales trends and customer churn trends based on sales performance data and financial data collected from the company's customer relationship management system and enterprise resource planning system."

[1112] In this way, the system of the present invention can process data efficiently and accurately, and quickly create and distribute necessary materials.

[1113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1114] Step 1:

[1115] Data collection

[1116] The server accesses each company's data source and collects data. It uses pre-configured API keys and authentication information as input. Specifically, it performs the following operations:

[1117] The server makes an API call to retrieve sales performance data from the customer relationship management system.

[1118] Make another API call to retrieve financial data from an enterprise resource planning system.

[1119] Make yet another API call to get web traffic data from a web analytics tool.

[1120] As an output, the server temporarily stores the collected data in memory, thus completing the data collection from all data sources.

[1121] Step 2:

[1122] Data storage

[1123] The server stores the collected data in the storage system. As input, it uses the data collected in step 1. Specifically, it performs the following operations.

[1124] The server classifies the collected data into structured data and unstructured data.

[1125] Store structured data in Amazon Redshift (data warehouse) and unstructured data in Amazon S3 (data lake).

[1126] Convert the data into an appropriate format (e.g., CSV or JSON) and upload it to each storage system.

[1127] As an output, the server stores all data in a storage system.

[1128] Step 3:

[1129] Data analysis

[1130] The server analyzes the collected and stored data. It uses the data stored in step 2 as input. Specifically, it performs the following operations:

[1131] The server loads the data into a data visualization tool like Tableau or Power BI.

[1132] Perform data cleaning to detect, correct, or remove missing or outlier values, for example, by imputing missing values ​​with the mean using statistical methods or machine learning algorithms.

[1133] Apply machine learning algorithms to detect and filter out fraudulent data.

[1134] It performs the necessary aggregations and generates visuals such as bar graphs and line charts.

[1135] The output is a reliable analysis result.

[1136] Step 4:

[1137] Extracting indicators and trends

[1138] The server extracts key indicators and trends from the analysis results, using the analysis results obtained in step 3 as input. Specifically, it performs the following operations:

[1139] The server extracts important business trends such as sales trends and customer churn trends.

[1140] The extracted indicators are stored in a database for further processing.

[1141] The output is key metrics and business trends.

[1142] Step 5:

[1143] Automatic generation of materials

[1144] The server automatically generates presentation materials and financial statements based on the extracted analysis results. As input, it uses the indicators and trends obtained in step 4. Specifically, it performs the following operations:

[1145] The server loads Google Slides or Microsoft PowerPoint templates and prepares the slide structure.

[1146] Insert KPI graphs and charts into the template to make them visually easy to understand.

[1147] Export the generated documents in PDF format and temporarily save them in cloud storage.

[1148] As output, presentation materials and financial statements are generated.

[1149] Step 6:

[1150] Checking and correcting materials

[1151] The user checks the generated presentation materials and financial statements and makes any necessary corrections. The materials generated in step 5 are used as input. Specifically, the following operations are performed:

[1152] Users log in to a dedicated web interface to view the generated materials.

[1153] Users can add comments to documents and correct erroneous data if necessary.

[1154] When the user has completed the corrections, he or she presses the "Confirm" button.

[1155] The output is the corrected and verified material.

[1156] Step 7:

[1157] Approval and Distribution of Materials

[1158] The user finally approves the corrected and confirmed materials. The confirmed and corrected materials from step 6 are used as input. Specifically, the following operations are performed:

[1159] The user makes a final check of the materials and presses the "Approve" button.

[1160] The terminal sends the approved documents to the relevant parties by email.

[1161] The device uploads the materials to cloud storage and generates a sharing link.

[1162] The device notifies the relevant parties of the generated shared link and provides them with access to the materials.

[1163] The output is the final approved and distributed material.

[1164] (Application example 1)

[1165] 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."

[1166] Traditional factory operations required the manual collection and analysis of information from many data sources, which hindered efforts to improve production efficiency and reduce failure rates. It was particularly difficult to collect large amounts of data, properly analyze it, extract key indicators, and then quickly take specific action based on them. As a result, it was difficult for management and on-site managers to make decisions, hindering the optimization of operations.

[1167] 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.

[1168] In this invention, the server includes: means for accessing multiple data sources within a company to collect data; means for storing the collected data in a data warehouse or data lake; means for analyzing the stored data and extracting important indicators and trends; and means for automatically generating reports based on the analysis results and analyzing production efficiency and failure rates based on data from equipment and sensors within the factory. This automates data collection and analysis from each data source, enabling the rapid extraction and reporting of important indicators and trends. Furthermore, the generated reports can be reviewed, revised, and approved by the user, supporting optimal decision-making and achieving more efficient factory operations and reduced failure rates.

[1169] "Data sources" refers to the multiple information sources that a company has, such as customer relationship management systems, enterprise resource planning systems, web analytics tools, and equipment and sensors in factories.

[1170] A "data warehouse" is a system for efficiently storing large amounts of structured data and enabling fast access.

[1171] A "data lake" is a system that stores structured and unstructured data in its original form at high volume and low cost.

[1172] "Analysis" refers to the process of cleaning, transforming, aggregating, detecting and removing fraudulent data from collected and stored data, and extracting important indicators and trends.

[1173] "Indicators" are important numerical values ​​or indicators extracted as a result of data analysis, and include, for example, production efficiency, failure rate, inventory turnover rate, etc.

[1174] "Trend" refers to patterns or trends in data that are revealed through data analysis, such as changes in sales or an increasing trend in breakdowns.

[1175] A "report" is a document automatically generated based on the analysis results, which includes detailed information on production efficiency and failure rates.

[1176] "User" refers to the person responsible for reviewing generated reports, making corrections and approvals, and ultimately distributing the materials.

[1177] "System" refers to an integrated set of equipment and software for carrying out a series of processes including data collection, data storage, data analysis, extraction of indicators and trends, report generation, and user review, correction, and approval.

[1178] As an embodiment of the present invention, a specific system configuration of a factory operations management assistant application will be described. This system collects information from multiple data sources within a company and stores it in a data warehouse or data lake. It also analyzes the collected data to extract important indicators and trends and automatically generates reports.

[1179] System Configuration

[1180] Data collection

[1181] The server collects data from each piece of equipment and sensor in the factory via API. This data collection is performed using a Python script, which obtains the necessary data from the IoT sensors via REST API and temporarily stores it in memory.

[1182] Data storage

[1183] The server stores the collected data in a data warehouse or data lake. Specifically, it uses Python scripts to store the data in AWS S3 and then in AWS Redshift (a data warehouse). This allows for efficient and low-cost management of large amounts of data.

[1184] Data analysis

[1185] The server analyzes the data using BI and data visualization tools, particularly Tableau, for data cleansing, analysis, and dashboard creation, and utilizes machine learning libraries such as scikit-learn to detect fraudulent data.

[1186] Extracting indicators and trends

[1187] Extract important KPIs from the analysis results, such as production efficiency, failure rate, and inventory turnover. By linking Python and Tableau, extract these indicators and clarify trends.

[1188] Automatic generation of materials

[1189] The server automatically generates reports based on the extracted KPIs and trends, and the reports are created according to predefined templates and presented in a visually easy-to-understand format.

[1190] User confirmation and correction

[1191] Users can view and edit the generated reports through a web interface, using a web framework such as Django to make it easier for users to add comments and edit the reports.

[1192] Approval and Distribution of Materials

[1193] After the user checks and modifies the report, they finally approve it. Approved documents are distributed to the relevant parties and sent via email or uploaded to cloud storage.

[1194] Specific examples

[1195] For example, when managing a factory's production efficiency, the system works as follows: First, data from each production line is collected, stored in AWS S3, and managed using AWS Redshift. The data is then analyzed using Tableau to extract trends in production efficiency and failure rates. Based on this, reports are automatically generated, and managers can review, modify, and ultimately approve the reports through a Django-based web interface.

[1196] Prompt Sentence Examples

[1197] "Please develop an app that analyzes production efficiency and failure rate data within the factory and automatically generates monthly reports. The app will collect, store, analyze, extract KPIs, and automatically generate reports, and provide an interface that allows managers to easily check and modify the data."

[1198] In this way, the system of the present invention helps optimize factory operations, enabling efficient data management and analysis, and rapid report generation.

[1199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1200] Step 1:

[1201] The server collects data from each piece of equipment and sensor in the factory. Specifically, it runs a Python script to obtain production data from each IoT sensor through a REST API. The input is the API endpoint and authentication information of each sensor. After collecting the data, this data is temporarily stored in memory. The output is a set of collected production data.

[1202] Step 2:

[1203] The server stores the collected data in a data warehouse or data lake. Specifically, a Python script is used to store the data in AWS S3 and then ingest it into AWS Redshift. The input is the production data collected in step 1, and the output is the data stored in AWS S3 and AWS Redshift. This process includes data format conversion and operations for storing it in appropriate storage.

[1204] Step 3:

[1205] The server analyzes the stored data. First, it cleanses the data using Tableau to detect and remove missing values ​​and outliers. Next, it applies a machine learning model using the scikit-learn library to detect fraudulent data. The input is the data stored in AWS Redshift, and the output is the analyzed data after cleansing and fraud detection.

[1206] Step 4:

[1207] The server extracts key metrics and trends. Python scripts and Tableau are used in conjunction with the server to calculate KPIs (e.g., production efficiency, failure rate, inventory turnover) and derive trends. The cleansed and fraud-detected data is used as input. The output is the extracted key metrics and their trend data.

[1208] Step 5:

[1209] The server automatically generates reports based on the analysis results. It uses Python and Tableau to create reports according to predefined templates. It uses extracted KPIs and trend data as input. The output is an automatically generated report. The report summarizes the data in a visually easy-to-understand format.

[1210] Step 6:

[1211] Users can view and modify the generated reports through a web interface. Using an interface based on the Django framework, users can check the report content and add data and comments as needed. The input is the automatically generated report, and the output is the reviewed and modified report.

[1212] Step 7:

[1213] The user approves the revised report, and the server distributes it to the relevant parties. The approved report is sent by email or uploaded to cloud storage. The input is the reviewed and revised report, and the output is the final, distributed report. Through this process, the relevant parties can quickly obtain the latest production information.

[1214] 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.

[1215] As an embodiment of the present invention, a system is configured as follows: it collects data from multiple corporate data sources, stores and analyzes it in a data warehouse or data lake, and automatically generates materials based on the analysis results. In addition, by combining it with an emotion engine that recognizes the user's emotions, the content and expression of the materials are adjusted according to the user's emotions.

[1216] Data collection

[1217] The server accesses each data source of the company and collects data. For example, it obtains the necessary data using APIs of customer management systems, enterprise resource planning systems, web analytics tools, etc. The data from each data source is temporarily stored in memory.

[1218] Data storage

[1219] The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, cleans incomplete and duplicate data, and stores it.

[1220] Data analysis

[1221] The server analyzes the data stored on it, cleaning it, detecting and removing fraudulent data, aggregating it, and extracting key performance indicators (KPIs) and trends.

[1222] Automatic generation of materials

[1223] The server automatically generates presentation materials and financial statements based on the analysis results. It creates presentation materials that visually display key indicators and trends, and financial statements that include detailed financial data. It uses templates to insert results in the appropriate format.

[1224] Checking and correcting materials

[1225] The user checks the generated presentation materials and financial statements. The user accesses the materials, reviews them, and makes corrections as necessary. Once corrections are complete, the user performs a final check of the materials.

[1226] Approval and Distribution of Materials

[1227] The user approves the revised document. The approval process checks whether all revisions are reflected and officially accepts the document. The approved document is saved as an official document. The terminal distributes the document to the relevant parties.

[1228] Incorporating an emotion engine

[1229] The server collects user feedback and uses an emotion engine to recognize the user's emotions. For example, if a user expresses dissatisfaction or concern about the content of a presentation, the emotion engine analyzes that emotion and instructs the system to adjust the content and expression of the presentation. Specifically, the system makes adjustments based on the user's emotions, such as changing the tone of the presentation or adding additional explanations.

[1230] Specific examples

[1231] Consider a case where a company generates monthly financial statements. The server collects data from customer management systems, enterprise resource planning systems, and web analytics tools and stores it in a data warehouse. It then analyzes the data using a data visualization tool to extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the extracted results. The generated materials are reviewed by the user, and after recognizing the user's emotions through an emotion engine, the content of the materials is adjusted as necessary. Finally, the user approves the materials, and the terminal distributes them to the relevant parties.

[1232] In this way, by incorporating an emotion engine, it becomes possible to create more user-friendly documents, and a system can be provided that supports efficient and effective decision-making in companies.

[1233] The processing flow will be explained below.

[1234] Step 1:

[1235] The server accesses each data source of the company and collects the necessary data. For example, it retrieves sales performance data using the API of a customer management system, financial data from an enterprise resource planning system, and website traffic data from a web analytics tool. This data is temporarily stored in memory.

[1236] Step 2:

[1237] The server stores the collected data in a data warehouse or data lake. The data is often provided in different formats, and the server converts the data into a unified format. The conversion process also includes cleaning the data, removing incomplete and duplicate data.

[1238] Step 3:

[1239] The server analyzes the stored data. First, it cleans the data, then detects and removes any irregularities (e.g., abnormally high transaction amounts), then aggregates the data and calculates key performance indicators (KPIs). It also extracts trends based on past data.

[1240] Step 4:

[1241] The server extracts key indicators and trends from the analysis results, such as sales, customer acquisition costs, and customer retention rates, and derives management insights. During this process, data visualization tools are used to display the results in a visually understandable format.

[1242] Step 5:

[1243] The server automatically generates presentations and financial statements based on the extracted analysis results. Presentations include visual displays of key indicators and trends as graphs and charts, while financial statements include detailed financial data. Templates are used to insert results in the appropriate format.

[1244] Step 6:

[1245] The user checks the generated presentation and financial statements. The user accesses the documents, reviews the content, and makes any necessary edits. For example, the user can add explanations to graphs or edit annotations for data points. Once edits are complete, the user performs a final review of the documents.

[1246] Step 7:

[1247] The emotion engine receives user feedback and recognizes the user's emotions. For example, if the user expresses dissatisfaction or concern, the emotion engine analyzes that emotion. Based on the user's emotions, the engine suggests modifications based on the user's emotions, such as changing the tone of the material or adding additional explanations.

[1248] Step 8:

[1249] The user reviews the revised document again and makes any necessary final adjustments. If the user is satisfied with the results of the revisions, they approve the document. This process ensures that the document is finally completed accurately and in the appropriate format.

[1250] Step 9:

[1251] The user reviews the final approved material and officially accepts it. The approved material is finally saved as an official document.

[1252] Step 10:

[1253] The terminal distributes approved documents to the relevant parties. Distribution methods include sending emails, uploading to cloud storage, and saving to the company's internal database. This allows all parties involved to share the latest information and facilitates smooth decision-making.

[1254] These are the specific steps in a company's data collection, analysis, document creation, and distribution. This system makes it possible to create documents that take user emotions into account, allowing companies to obtain important management information more efficiently and accurately.

[1255] Example 2

[1256] 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."

[1257] Modern companies possess large amounts of data, but it is difficult to efficiently collect, store, and analyze that data, and automatically generate materials to help with decision-making. Furthermore, because the content of the generated materials does not change based on the user's emotions, there is no guarantee that the materials will be easy for users to understand or presented in an appropriate tone.

[1258] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for accessing multiple data sources of a company to collect data, a means for storing the collected data in a data warehouse or data lake, a means for analyzing the stored data and extracting important indicators and trends, a means for automatically generating materials based on the analysis results, a means for acquiring user feedback and analyzing emotions, and a means for adjusting the content of the generated materials based on the emotion analysis results. This enables efficient use of data and flexible generation of materials according to user emotions.

[1259] A "data source" is a system or database that provides information held by a company.

[1260] A "data warehouse" is a structured database that integrates various data from inside and outside a company and is used for analysis and report generation.

[1261] A "data lake" is a data storage facility that stores large amounts of data in various formats in an unstructured state, allowing it to be analyzed and processed.

[1262] "Analytical tools" refer to techniques and methods for examining and processing data to extract important indicators and trends.

[1263] "Key indicators" are the key metrics used to evaluate a company's performance or achievements.

[1264] "Trends" describe changes or patterns in data, identifying long-term trends or short-term anomalies.

[1265] "Means for automatically generating materials" refers to technologies and methods for automatically creating presentation materials and reports based on analysis results.

[1266] "User feedback" refers to opinions and impressions provided by users regarding the generated materials.

[1267] "Means for analyzing emotions" refers to techniques and methods for detecting and analyzing the emotional state from user feedback.

[1268] "Emotion analysis result" refers to the result of analyzing the user's emotional state.

[1269] "Means for adjusting the content of materials" refers to techniques or methods that change the expression or tone of generated materials according to the user's emotions based on the results of emotion analysis.

[1270] The present invention relates to a system that collects, stores, and analyzes data from multiple corporate data sources and automatically generates materials based on the collected data. The purpose of the present invention is to provide effective materials by analyzing user feedback and adjusting the content of the materials according to the user's emotions.

[1271] Data collection

[1272] The server accesses data sources such as a company's customer relationship management system, enterprise resource planning system, and web analytics tool. It uses APIs to retrieve the required data from these systems. For example, it uses a REST API to retrieve customer information from the customer relationship management system and collect financial data from the enterprise resource planning system. This data is temporarily stored in memory.

[1273] Data formatting and storage

[1274] The server converts the collected data into a unified format (such as CSV or JSON). It then uses a data processing library such as Python's Pandas to clean the data and remove incomplete and duplicate data. The cleaned data is then stored in a data warehouse such as Amazon Redshift or a data lake such as Apache Hadoop.

[1275] Data analysis

[1276] The server performs data analysis. It uses data analysis libraries such as Python's NumPy and Scikit-learn to perform statistical processing of the data, calculate significant indicators, and detect and remove fraudulent data. It also extracts KPIs and trends. For example, it can extract monthly trends in sales or fluctuations in customer satisfaction.

[1277] Automatic generation of materials

[1278] The server automatically generates presentation materials and financial statements using Microsoft PowerPoint templates based on the analysis results. Graphs and tables are created and inserted into the templates using the Python-pptx library. For example, a graph showing sales over time or a pie chart showing customer satisfaction can be generated.

[1279] Checking and correcting materials

[1280] Users can check the generated data in a web browser and make any necessary corrections. The corrections are recorded using the comment function. For example, users can add feedback such as "Please update the values ​​in this section to the latest ones."

[1281] Approval and Distribution of Materials

[1282] The user then performs a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The distributed document is then saved as an official document.

[1283] Incorporating an emotion engine

[1284] The server collects user feedback and analyzes the user's emotions using an emotion engine such as IBM Watson Tone Analyzer. The collected emotion data is used to adjust the tone and content of the material. For example, if the user gives feedback that "this content is too difficult," the material will be changed to simpler language.

[1285] Specific examples

[1286] When a company generates monthly financial statements, the server collects data from CRM, ERP, and web analytics tools and stores it in a data warehouse. It then uses a Python library to analyze the data and extract key financial indicators and trends. The server automatically generates presentation materials and financial statements based on the analysis results. The generated materials are then reviewed by the user in a web browser, and feedback is collected through an emotion engine to adjust the tone of the materials. Finally, the user approves the materials, and the terminal distributes them to relevant parties.

[1287] Prompt Sentence Examples

[1288] "We want to automatically generate monthly financial statements. How can we gather data from our customer management system, enterprise resource planning system, and web analytics tools to create presentations and financial statements that include key metrics and trends?"

[1289] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1290] Step 1: Data collection

[1291] The server runs a regularly scheduled job and sends API requests to each of the company's data sources (e.g., customer management system, enterprise resource planning system, web analytics tool). The API endpoint URL and authentication information are used as input. The data returned in JSON or CSV format is obtained as output. Specific operations include, for example, obtaining customer purchase history and inquiry information from the customer management system.

[1292] Step 2: Data Formatting and Storage

[1293] The server temporarily stores the acquired data in memory and converts data in different formats into a unified format (for example, CSV or JSON). It uses Python's Pandas library to clean the data and remove incomplete and duplicate data. The input is raw data acquired from each data source. The output is cleaned data in a unified format, which is stored in Amazon Redshift or Apache Hadoop. Specifically, it removes duplicate records and imputes missing values.

[1294] Step 3: Data analysis

[1295] The server reads the saved data and performs statistical processing using Python's NumPy and data analysis libraries such as Scikit-learn. It uses the cleaned data as input and extracts key indicators (KPIs) and trends as output. Specifically, it calculates monthly trends in sales and fluctuations in customer satisfaction, and aggregates important KPIs.

[1296] Step 4: Automatic generation of materials

[1297] The server uses Microsoft PowerPoint templates based on the analysis results to create presentation materials and financial statements. Graphs and tables are inserted into the templates using the Python-pptx library. The input is the indicators and trends obtained through data analysis, and the output is a visually easy-to-understand PowerPoint document. Specific operations include generating graphs showing sales over time and pie charts of customer satisfaction and inserting them into the templates.

[1298] Step 5: Check and correct the materials

[1299] The user checks the generated document on a web browser and makes corrections if necessary. The input is the generated document itself, and the output is a revised version that includes feedback from the user. Specifically, the comment function is used to add feedback such as "Please update the values ​​in this section to the latest ones."

[1300] Step 6: Approve and distribute materials

[1301] The user makes a final check of the revised document and approves it. Once the document is approved, the terminal distributes it to the relevant parties as an email attachment. The input is the revised and approved document, and the output is the official document distributed to the relevant parties. The specific operation is to click the approval button and send the document by email.

[1302] Step 7: Incorporating the Emotion Engine

[1303] The server collects user feedback and reactions during the document review and analyzes the user's emotions using an emotion engine such as IBM Watson Tone Analyzer. The input is the user's feedback comments and reaction data, and the output is the analyzed emotion data. The server then adjusts the tone and content of the document based on this emotion data. Specifically, if the server receives feedback that "this content is too difficult," it changes the tone of the document to be simpler.

[1304] (Application example 2)

[1305] 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."

[1306] Conventional content delivery systems have a problem in that it is difficult to improve user satisfaction because they do not take user emotions into consideration when proposing content or adjusting display methods. In particular, they only provide simple recommendations based on the user's viewing history and interaction data, and are unable to respond to the user's instantaneous emotional state. As a result, the viewing experience is uniform, and flexible content delivery according to the user's preferences and emotions cannot be achieved.

[1307] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing multiple data sources of a company to collect data, means for storing the collected data in a data warehouse or data lake, means for analyzing the stored data and extracting important indicators and trends, means for automatically generating presentation materials and financial statements based on the analysis results, and means for recognizing the user's emotions and adjusting the content and expression of the materials. This makes it possible to propose flexible and personalized content according to the user's emotions, significantly improving the quality of the viewing experience.

[1308] "Enterprise data sources" refers to sources that store and provide various information, such as an enterprise's internal customer management system, enterprise resource planning system, and web analytics tools.

[1309] A "data warehouse" is a centralized data management system that organizes large amounts of collected data in a unified format and efficiently stores and analyzes them.

[1310] A "data lake" is a data storage system that stores huge amounts of raw data and allows it to be analyzed and used as needed.

[1311] "Key metrics" are numbers or data points that are important to monitor in a business or operation, such as sales or profit margins.

[1312] "Trend" refers to a certain pattern, flow, or fluctuation found in analyzing data, including market trends and user behavior patterns.

[1313] "Data cleaning" is the process of removing incomplete, duplicate, and incorrect information from collected data to make it accurate and consistent.

[1314] "Detecting and removing invalid data" is the act of finding and removing intentionally or accidentally generated incorrect or anomalous data from a dataset.

[1315] "Data aggregation" refers to the classification and totalization of collected data and the compilation of statistical data.

[1316] "Presentation materials" refer to materials that visually organize and effectively communicate analysis results, important indicators, and trends.

[1317] "Financial statements" refer to official documents prepared to detail a company's financial position and performance.

[1318] "Recognizing the user's emotions" means analyzing the user's emotional state at that time from their specific feedback and interaction data.

[1319] "Adjusting the content and expression of the material" refers to the act of modifying the tone, language, and layout of the material based on user sentiment and feedback.

[1320] As an embodiment of the present invention, a system is configured to recognize a user's emotions in a content distribution service and provide personalized content. Specific embodiments are described below.

[1321] System configuration

[1322] The system mainly consists of the following means:

[1323] 1. Data collection methods: In content distribution services, servers access multiple data sources from companies to collect user viewing history, interaction data, etc. This is done using APIs for customer management systems and web analytics tools.

[1324] 2. Data storage: The server stores the collected data in a data warehouse or data lake, converts the collected data into a unified format, and cleans incomplete and duplicate data before storing it.

[1325] 3. Data Analysis: The server analyzes the stored data and extracts important indicators and trends. This process involves data cleaning, detecting and removing invalid data, and aggregating the data.

[1326] 4. Material and content generation means: This system has a means for automatically generating presentation materials and financial statements based on the analysis results. Furthermore, this invention also includes a means for automatically adjusting content suggestions and display methods using the same analysis results.

[1327] 5. Emotion Recognition: The server uses an emotion analysis engine to recognize the user's emotions using user feedback and interaction data. For example, it uses an API such as Emotion Engine.

[1328] 6. Means for adjusting content and expression: Having means for adjusting the content and expression of materials and content based on the user's emotions.

[1329] Hardware and Software

[1330] Hardware: servers, storage systems to set up a data warehouse or data lake, and network infrastructure

[1331] Software: Data management tools, sentiment analysis engines (e.g., Emotion Engine), data visualization tools

[1332] Processing flow

[1333] The server first collects data such as user viewing history and interaction data and temporarily stores it in memory. It then converts this data into a unified format and stores it in a data warehouse or data lake. It then cleans the data and performs analysis to extract key indicators and trends. Based on the extracted results, it automatically generates and suggests materials and content.

[1334] Using user feedback and interaction data, a sentiment analysis engine can recognize user emotions and adjust the content and presentation of materials and content accordingly, using sentiment analysis tools such as Emotion Engine.

[1335] Specific examples

[1336] In a content distribution service, viewing history and interaction data of a specific user ID are collected, and the most suitable content is suggested to the user by analyzing emotions.

[1337] Prompt Sentence Examples

[1338] Collect viewing history and interaction data for user ID 12345, analyze the user's emotions with a sentiment analysis engine, and suggest appropriate content to the user based on the emotions and collect their feedback.

[1339] The above is an embodiment of the present invention. This system realizes flexible and personalized content provision based on the user's emotions, and can significantly improve the quality of the viewing experience.

[1340] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1341] Step 1:

[1342] Data collection

[1343] The server accesses multiple data sources from the company and collects user viewing history and interaction data. Specifically, it uses the APIs of customer management systems and web analytics tools. As input, a user ID is provided. The server makes an API request to obtain viewing history and interaction data from these data sources. As output, it temporarily stores the collected data in memory.

[1344] Step 2:

[1345] Data storage

[1346] The server stores the data collected in step 1 in a data warehouse or data lake. As input, it uses the data temporarily held in memory. Specifically, it converts the data into a unified format and cleans incomplete and duplicate data. After this processing, the server stores the cleaned data in a data warehouse or data lake. As output, the cleaned data is stored in a data warehouse or data lake.

[1347] Step 3:

[1348] Data analysis

[1349] The server analyzes the stored data and extracts key indicators and trends. Data stored in a data warehouse or data lake is used as input. After cleaning the data, detecting and removing fraudulent data, and aggregating the data, the server extracts key indicators (KPIs) and trends from the data. The output is the analysis results.

[1350] Step 4:

[1351] Material and content generation

[1352] The server has the means to automatically generate presentation materials and financial statements based on the analysis results. The analysis results obtained in step 3 are used as input. The server uses templates to insert key indicators and trends into the materials in the appropriate format. The server obtains the generated presentation materials and financial statements as output. In addition, it suggests content and adjusts the display method based on the same analysis results.

[1353] Step 5:

[1354] Emotion recognition

[1355] The server uses the user's feedback and interaction data to use an emotion analysis engine to recognize the user's emotions. The feedback data and interaction data are provided as input. Specifically, the server sends this data to an emotion analysis API (e.g., Emotion Engine) and receives the analysis results. The output is the user's emotional state.

[1356] Step 6:

[1357] Adjustments to content and presentation

[1358] The server has the means to adjust the content and expression of the materials and content based on the user's emotions. The user's emotional state obtained in step 5 and the generated materials and content are used as input. The server adjusts the tone, wording, and layout according to the user's emotions. The adjusted materials and content are obtained as output.

[1359] The above are the specific processing steps of the system that realizes this application example. Each step realizes flexible and personalized content provision based on the user's emotions.

[1360] 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.

[1361] 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.

[1362] 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 robot 414.

[1363] 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.

[1364] FIG. 9 illustrates 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 behaviors 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.

[1365] 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.

[1366] 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).

[1367] 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.

[1368] 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."

[1369] 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.

[1370] 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).

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] 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.

[1381] The following is further disclosed regarding the above embodiment.

[1382] (Claim 1)

[1383] A means of accessing and collecting data from multiple enterprise data sources;

[1384] a means for storing the collected data in a data warehouse or data lake;

[1385] means for analyzing the stored data and extracting key metrics and trends;

[1386] A means for automatically generating presentation materials and financial statements based on the analysis results;

[1387] A system including:

[1388] (Claim 2)

[1389] 2. The system of claim 1, wherein the analysis means performs data cleaning, detection and removal of fraudulent data, and data aggregation.

[1390] (Claim 3)

[1391] 2. The system of claim 1, further comprising means for enabling a user to review, correct and approve the generated materials.

[1392] "Example 1"

[1393] (Claim 1)

[1394] A means of accessing and collecting data from multiple enterprise data sources;

[1395] means for storing the collected data in a storage system;

[1396] means for analyzing the stored data and extracting key metrics and trends;

[1397] means for automatically generating a report based on the analysis results;

[1398] A system including:

[1399] (Claim 2)

[1400] 2. The system of claim 1, wherein the analysis means performs data cleaning, detects and removes fraudulent data, aggregates data, and generates reliable data using machine learning algorithms.

[1401] (Claim 3)

[1402] 10. The system of claim 1, further comprising means for enabling an end user to review, modify and approve the generated materials.

[1403] (Claim 4)

[1404] 4. The system of claim 3, further comprising a communication means for distributing the materials to interested parties after end-user approval.

[1405] (Claim 5)

[1406] The system of claim 1, further comprising means for storing the analysis results and generated materials in cloud storage.

[1407] "Application Example 1"

[1408] (Claim 1)

[1409] A means of accessing and collecting data from multiple enterprise data sources;

[1410] a means for storing the collected data in a data warehouse or data lake;

[1411] means for analyzing the stored data and extracting key metrics and trends;

[1412] A means to automatically generate reports based on the analysis results and analyze production efficiency and failure rates based on data from equipment and sensors in the factory.

[1413] A system including:

[1414] (Claim 2)

[1415] 2. The system according to claim 1, wherein the analysis means performs data cleaning, detects and removes incorrect data, aggregates data, and further extracts trends in production efficiency and failure rates.

[1416] (Claim 3)

[1417] 10. The system of claim 1, further comprising means for enabling a user to review, modify and approve the generated report.

[1418] "Example 2: Combining Emotion Engines"

[1419] (Claim 1)

[1420] A means of accessing and collecting data from multiple enterprise data sources;

[1421] a means for storing the collected data in a data warehouse or data lake;

[1422] means for analyzing the stored data and extracting key metrics and trends;

[1423] A means for automatically generating materials based on the analysis results;

[1424] a means for obtaining user feedback and analyzing emotions;

[1425] A means for adjusting the content of the generated material based on the sentiment analysis results;

[1426] A system including:

[1427] (Claim 2)

[1428] 2. The system of claim 1, wherein the analysis means performs data cleaning, detection and removal of fraudulent data, and data aggregation.

[1429] (Claim 3)

[1430] 2. The system of claim 1, further comprising means for enabling a user to review, correct and approve the generated materials.

[1431] "Application example 2 when combining emotion engines"

[1432] (Claim 1)

[1433] A means of accessing and collecting data from multiple enterprise data sources;

[1434] a means for storing the collected data in a data warehouse or data lake;

[1435] means for analyzing the stored data and extracting key metrics and trends;

[1436] A means for automatically generating presentation materials and financial statements based on the analysis results;

[1437] A means for recognizing the user's emotions and adjusting the content and expression of the material;

[1438] A system including:

[1439] (Claim 2)

[1440] 2. The system of claim 1, wherein the analysis means performs data cleaning, detection and removal of fraudulent data, data aggregation, and automatic generation of presentation materials and financial statements.

[1441] (Claim 3)

[1442] 10. The system of claim 1, further comprising means for allowing a user to review, modify and approve the generated materials, and further adjusting the content of the materials based on user feedback. [Explanation of symbols]

[1443] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of accessing and collecting data from multiple enterprise data sources; a means for storing the collected data in a data warehouse or data lake; means for analyzing the stored data and extracting key metrics and trends; A means for automatically generating presentation materials and financial statements based on the analysis results; A system including:

2. 2. The system according to claim 1, wherein the analysis means performs data cleaning, detection and removal of incorrect data, and data aggregation.

3. 2. The system of claim 1, further comprising means for enabling a user to review, correct and approve the generated materials.

Images