system

Abstract

Provide a system. 【Solution means】Means for receiving an electronic document including financial data and automatically extracting financial information from the electronic document; Means for receiving information including financial information and automatically extracting financial data from the information; Means for storing the extracted financial data in a storage area; Means for comparing the stored financial data with the financial data of other companies in the same industry and detecting abnormal events; Means for automatically generating a report based on the detected abnormal events; Means for driving an analysis algorithm using past financial data and predicting future financial indicators; Means for visualizing the predicted future financial indicators and supporting the re-evaluation of business strategies; Means for visualizing sales data and notifying of the detection of abnormal events; A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] The work of a company manually inputting and analyzing the data in the financial statements requires time and expertise, and there is a problem that the time allocated for management decisions and client responses is limited. In addition, since there is no mechanism to efficiently detect outliers and perform comparative analysis with other companies in the same industry, it is difficult to make quick decisions. Furthermore, there is a lack of methods for non-financial department personnel to easily understand the financial analysis results.

Means for Solving the Problems

[0005] This invention provides a system that uses generation AI to automatically extract financial information from electronic documents and store it in a database. It includes means for comparing the stored financial information with that of competitors and detecting anomalies. This allows for rapid identification of anomalies and the generation of alerts. Furthermore, it utilizes natural language generation technology to write generated reports in simple language. Finally, it enables data-driven strategic decision-making by driving machine learning algorithms based on historical data to predict future financial indicators.

[0006] "Financial data" refers to numerical information that shows a company's economic activities, and mainly includes sales, profits, assets, and liabilities.

[0007] An "electronic document" is an information document stored in digital format, such as PDF or Excel.

[0008] "Extraction" refers to the process of identifying and retrieving specific information from input data.

[0009] A "database" is a computer system that organizes, stores, and manages information in a structured format.

[0010] An "outlier" is a numerical value that deviates significantly from the general range or expected value.

[0011] A "machine learning algorithm" refers to a computational method that allows computers to automatically learn from data and perform predictions and classifications.

[0012] "Natural language generation technology" is a technology that uses human language to generate meaningful sentences.

[0013] A "report" refers to a document that summarizes analysis results and important points.

[0014] "Competitors" refers to other companies that compete in the same industry or market. [Brief explanation of the drawing]

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. This system utilizes generative AI technology to automatically extract financial information from electronic financial statements and store it in a database. The system consists of the following elements:

[0037] First, the user uploads the company's financial statements to the system from their terminal. The system receives the uploaded electronic document, and the server analyzes the document using natural language processing technology. This automatically extracts key financial indicators and records them in a structured data format in the database. This eliminates the need for manual data entry and significantly reduces the risk of input errors.

[0038] Next, the server uses the stored database to detect anomalies and perform comparative analysis with competitors. When anomalies are detected, the system automatically generates an alert. The insights gained at this stage allow companies to quickly develop strategies to gain a competitive advantage.

[0039] Furthermore, based on the generated data and analysis results, the server automatically creates reports. Natural language generation technology is used to explain financial indicators in simple language that is easy for non-experts to understand. These reports are presented on the terminal via a dashboard, allowing users to easily access and download them as needed.

[0040] Ultimately, a machine learning algorithm based on historical data allows the server to predict future financial conditions. This predictive model visualizes future sales growth and profitability, aiding in strategic decision-making. For example, if predicted sales growth exceeds the industry average, users can re-evaluate their growth strategy and review necessary investments.

[0041] These features make the present invention widely applicable as a system that significantly streamlines a company's financial management process and enables rapid management decisions.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] Users upload electronic financial statements from their devices to the system. This provides the system with PDF or Excel as the file format to be used.

[0045] Step 2:

[0046] The server receives the uploaded electronic document and selects the appropriate file parser. Next, it uses natural language processing technology to automatically extract financial information such as sales, profits, and assets from the financial statement and converts it into structured data.

[0047] Step 3:

[0048] The server stores the extracted financial data in a database. The stored data is used for subsequent analysis, anomaly detection, industry comparisons, and report generation.

[0049] Step 4:

[0050] The server uses stored data to apply an anomaly detection algorithm and evaluate how detected anomalies are impacting performance. If an anomaly is detected, the system automatically generates an alert and prepares to notify relevant parties.

[0051] Step 5:

[0052] The server drives the report generation engine based on the data it collects and analyzes. Utilizing natural language generation technology, the reports are written in simple language, minimizing technical jargon.

[0053] Step 6:

[0054] The generated reports are displayed on a dashboard on the device, allowing users to view, download, and print them. The information is also provided in a visually easy-to-understand format using graphs and charts.

[0055] Step 7:

[0056] The server trains a machine learning model based on historical data to predict future financial indicators. The prediction results are visualized on the terminal, clearly showing future growth potential and profitability.

[0057] Step 8:

[0058] The system makes strategic decisions based on the predictive data provided by the user and develops new action plans. Continuous improvement is achieved by feeding back the changed strategic information into the system as needed.

[0059] (Example 1)

[0060] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0061] Companies are required to efficiently manage vast amounts of financial data and make quick and accurate business decisions. However, conventional methods require a great deal of time and effort for manual data entry and analysis, and are prone to input errors and delays in information. Furthermore, there is a lack of practical means for quickly and accurately comparing financial performance with competitors and making future financial forecasts. This invention aims to solve these problems.

[0062] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0063] In this invention, the server includes means for receiving information provided in the form of an electronic document and automatically extracting financial indicators from said information; means for storing the extracted financial indicators in a data storage device; and means for comparing the stored financial indicators with the financial indicators of other entities and identifying outliers. This enables companies to efficiently analyze and store financial data, achieve rapid and accurate detection of outliers and future financial forecasts, and improve the quality of management decisions.

[0064] An "electronic document" is a document expressed in a digital format that can be read on a computer or digital device.

[0065] "Financial indicators" are statistical data used to quantify a company's financial condition and performance, and include sales revenue and profit margins.

[0066] A "data storage device" is a device or system for recording and retaining information for later use.

[0067] An "outlier" is a value that falls outside the normal range and exhibits specific or unexpected behavior within a dataset.

[0068] A "generative AI model" is a mathematical model that uses machine learning or artificial intelligence technology to generate new insights and predictions from data.

[0069] "Natural language generation technology" is a technology that enables computers to express analysis results and information in natural language that is easy for humans to understand.

[0070] "Natural language processing technology" refers to the techniques and methods used to enable computers to understand, interpret, and generate human language.

[0071] "Machine learning techniques" refer to a set of algorithms and methods for finding patterns in data and using them to learn and make predictions.

[0072] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. Its embodiments are described in detail below.

[0073] First, users upload their company's financial statements to the system as electronic documents using a device. Typically, a PC or tablet is used as the device, connecting to the server via the internet. This upload process is carried out through an upload form provided in a web browser.

[0074] The server operates natural language processing (NLP) technology in an independent computing environment to analyze received electronic documents. Open-source libraries such as spaCy and NLTK are utilized for this purpose, automatically extracting financial indicators from documents. Furthermore, libraries such as pdf-lib and SheetJS are used to convert the contents of electronic documents into text data.

[0075] The extracted information is converted into a structured data format and stored in a data storage device, such as a relational database like MySQL® or PostgreSQL. This makes data retrieval and analysis easier.

[0076] Using the stored data, the server drives generative AI models to perform analytical processing for financial comparisons with competitors and anomaly detection. This analysis utilizes libraries such as Scikit-learn, TENSORFLOW®, or PyTorch, enabling machine learning models to provide insights.

[0077] As a concrete example, a prompt message such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," can be generated and passed to the generation AI.

[0078] Finally, a report is created based on the generated analysis results and predictions, and natural language generation technology is applied to make this report understandable even to non-experts. This report is displayed on the device via a web dashboard, and users can view it in real time and download it as needed.

[0079] This invention is a powerful means for companies to manage their financial information more quickly and effectively and to enhance their business intelligence.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] Users upload their company's financial statements to the system using a terminal. Input is expected to be electronic documents in PDF or Excel format, which are sent to the server via a web browser. Output is an electronic document file temporarily stored on the server. This process begins with the user dragging and dropping the file into the upload form.

[0083] Step 2:

[0084] The server prepares to analyze the contents of the received electronic document. Specifically, it uses libraries such as pdf-lib for PDF analysis and SheetJS for Excel analysis. The uploaded electronic document is provided as input. The server converts its contents into text data and performs preprocessing for extracting financial indicators. The output is parseable text data. This step also verifies that the file is properly formatted.

[0085] Step 3:

[0086] The server extracts financial indicators from text data converted using natural language processing technology. Here, spaCy and NLTK are used to identify specific information such as amounts, dates, and department names within the document. The input is pre-processed text data, and the output is the extracted financial indicators. At this stage, processes such as tokenization and part-of-speech tagging are performed to ensure that the necessary information can be reliably extracted.

[0087] Step 4:

[0088] The server stores the extracted financial indicators in a structured data format in a data storage device. Specifically, it performs data insertion operations on SQL databases such as MySQL and PostgreSQL. A dataset of the extracted financial indicators is prepared as input. The structured data recorded in the database is obtained as output. This storage process also includes verification to prevent data duplication and inconsistencies.

[0089] Step 5:

[0090] The server uses stored financial indicators to perform comparisons with competitors and detect outliers. Here, machine learning models are operated using libraries such as Scikit-learn and TensorFlow. Financial indicators stored in the database are used as input, and the output generates a list of outliers and comparative analysis results with competitors. Regression analysis and clustering techniques are often applied to this analysis.

[0091] Step 6:

[0092] The server generates prompts using a generative AI model and creates a report based on the analysis results. Natural language generation technology is used to organize the information in a way that is easy for non-experts to understand. The input is the analysis results obtained in step 5. The output is a detailed report document. This report may include graphs and tables, along with explanatory text.

[0093] Step 7:

[0094] The terminal displays reports on a dashboard accessible to the user. Reports are provided in HTML or PDF format, and users can view and download them directly from their browser. Server-generated reports serve as input. A specific UI framework (e.g., React or Vue.js) is used to present information while maintaining a good user experience.

[0095] Step 8:

[0096] The server drives a machine learning algorithm using historical data to predict future financial conditions. Historical financial data is used as input. The output reports forecasts for future sales growth and profitability. This allows users to gain visual insights for strategic decision-making. Specifically, a prompt such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," is used.

[0097] (Application Example 1)

[0098] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0099] Managing and analyzing financial data within companies often involves manual processes, which are time-consuming, labor-intensive, and prone to input errors. Furthermore, comparing financial performance with competitors and detecting anomalies can be inconsistent. There is a need for rapid and highly accurate financial data management and forecasting, along with the creation of easily understandable reports.

[0100] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0101] In this invention, the server includes means for automatically extracting information including financial information, means for storing the extracted financial data in a storage area, and means for comparing the stored financial data with the financial data of competitors. This enables efficient management of financial data, immediate detection of abnormal events, highly accurate prediction of future financial indicators, and support for re-evaluating business strategies based on the results.

[0102] "Financial information" refers to data that shows a company's financial condition and economic activities, and includes profits, expenses, assets, liabilities, etc.

[0103] "Information" refers to data that represents facts, events, concepts, etc., and is used for a specific purpose.

[0104] "Extraction" refers to the operation of taking specific data or information out of a large dataset.

[0105] "Storage area" refers to a physical or virtual space used to record and hold digital data.

[0106] An "abnormal event" refers to a value or situation that exceeds the normal range, indicating an unexpected fluctuation or anomaly.

[0107] A "report" is a document that summarizes specific information or analytical results and is used to support judgment and decision-making.

[0108] An "analysis algorithm" refers to a series of procedures or calculation methods used to extract useful patterns and information from large amounts of data.

[0109] "Future financial indicators" are indicators that show projected or predicted future financial conditions of a company, and include sales and profits.

[0110] "Visualization" is the process of representing data and information visually, and it is a technique used to improve ease of understanding.

[0111] "Business strategy" refers to the means and methods that a company plans to use to achieve its goals, and it is the framework that supports its management policies.

[0112] "Sales data" refers to data relating to the revenue generated from the sale of products and services provided by a company.

[0113] "Notification" is the act of informing a person or system of specific information, and is used to attract attention.

[0114] This invention is a system for efficiently managing and analyzing financial information. The server receives electronic documents containing financial information sent by users and automatically extracts specific information. This reduces manual data entry and improves data accuracy.

[0115] The primary software used is the Python pandas library, which is used for loading and manipulating data. Additionally, the scikit-learn library is used to detect anomalies using machine learning algorithms. Matplotlib and seaborn are used for data visualization, generating clean and clear visuals.

[0116] The server compares stored financial data with that of competitors and immediately detects anomalies. Information about detected anomalies is reported to the user through notifications. Furthermore, analytical algorithms predict future financial indicators and support the re-evaluation of business strategies based on this data. The visualized results are presented as a report on the user's terminal and used as a basis for decision-making.

[0117] For example, if a company inputs its quarterly sales data into this system, the system can quickly detect anomalies in sales and use that information to make informed business decisions. It can also forecast sales considering specific seasons and campaign effects, providing opportunities to improve marketing strategies.

[0118] By utilizing a generative AI model, it is possible to automate a portion of the program that performs the aforementioned series of processes. As an example of a prompt statement to be used for this, the following text could be used as input data: "Analyze the latest sales data, detect anomalies, and create a report. Compare it with competitors and include suggestions for adjusting business strategies if necessary."

[0119] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0120] Step 1:

[0121] The user uploads an electronic document containing financial information from their terminal. The terminal sends this electronic document to the server, which prepares to store the received document in a database for analysis. This input includes sales information, expense information, etc., and the server prepares this as data for analysis.

[0122] Step 2:

[0123] The server automatically analyzes the stored electronic documents. Specifically, it uses a generative AI model to select the necessary financial information and extracts it as structured data using the pandas library. This process yields a dataset of financial indicators as output.

[0124] Step 3:

[0125] The server stores the extracted financial data in a storage area according to the schema. This storage area is the database used for subsequent analytical processing. The input data is converted to an appropriate format and stored securely.

[0126] Step 4:

[0127] Based on the stored data, the server uses the scikit-learn library to detect anomalies. Specifically, it runs anomaly detection algorithms such as Isolation Forest to identify outliers in the financial data. The output of this step is the location and value of the data points identified as anomalies.

[0128] Step 5:

[0129] The server compares outliers with financial data from competitors as a baseline. When an anomaly is detected, it generates and sends alerts and notifications to the user. This process allows the user to immediately recognize significant performance fluctuations.

[0130] Step 6:

[0131] The user receives a report generated by the server. The server uses matplotlib and seaborn to visualize the data and formats it into a report using natural language generation technology. This allows the user to receive materials for future sales forecasts and strategic planning.

[0132] Step 7:

[0133] The server runs machine learning models based on historical financial data to visualize future financial indicators. This includes sales forecasts and expense trend graphs, presented to users in a visually easy-to-understand format. The analysis results are output as data to be incorporated into business strategies.

[0134] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0135] This invention efficiently analyzes a company's financial data and is implemented as an interactive system that takes user emotions into consideration. This system includes an emotion engine for managing, analyzing, and optimizing the user interface of financial information.

[0136] First, the user uploads electronic documents containing the company's financial data from their device. This data is received by a server, and the necessary financial information is automatically extracted using natural language processing technology. The extracted data is stored in a database and used for future anomaly detection and industry comparisons.

[0137] Next, the server uses the stored financial information to compare with competitors, and automatically generates an alert if anomalies are detected. Furthermore, it analyzes the user's emotions through an emotion engine and selects the most considerate report content and presentation style to provide a report that is as easy to understand as possible for the user.

[0138] When a report is generated, natural language generation technology is used to create a simple and easy-to-understand text, and then the report is refined based on sentiment analysis results. On the device, the dashboard design, colors, and font size are dynamically changed according to the user's emotional state to provide an optimal user experience.

[0139] Furthermore, based on past data, the server uses machine learning algorithms to predict future financial conditions. This predictive information is also refined by an emotion engine and displayed on the device in a visually easy-to-understand format.

[0140] For example, if the emotion engine determines that a user has negative feelings about a particular financial indicator, the system will highlight that indicator and automatically suggest detailed explanations and improvement measures. In this way, the present invention significantly advances conventional financial management systems by supporting rapid and accurate decision-making for companies and providing a flexible interface adapted to individual users.

[0141] The following describes the processing flow.

[0142] Step 1:

[0143] Users upload electronic documents containing company financial data from their devices. The system supports file formats such as PDF and Excel.

[0144] Step 2:

[0145] The server receives uploaded electronic documents, selects the appropriate file parser, and analyzes the documents. Using natural language processing technology, it automatically extracts necessary financial information such as sales and profits.

[0146] Step 3:

[0147] The server extracts financial data, structures it, and stores it in a database. This creates a data base that can be used for subsequent analysis and anomaly detection.

[0148] Step 4:

[0149] The server uses stored data to compare it with data from competitors and runs an algorithm to detect anomalies. Analysis is performed on the detected anomalies, and alerts are generated as needed.

[0150] Step 5:

[0151] The server uses an emotion engine to analyze the user's emotional state based on their past feedback and behavioral patterns. This emotional data is considered when generating reports.

[0152] Step 6:

[0153] The server generates a report based on financial data and anomaly analysis results. It uses natural language generation technology to create plain text and adjusts the expression based on sentiment engine analysis results.

[0154] Step 7:

[0155] The generated report is displayed on the device and can be viewed on the dashboard. The system dynamically changes the interface colors and layout according to the user's emotional state to provide an optimal display.

[0156] Step 8:

[0157] The server uses historical data to train machine learning models and predict future financial indicators. These predictions are then refined based on the analysis results of the emotion engine and presented to the device in a visually easy-to-understand format.

[0158] Step 9:

[0159] Users review detailed forecast data and reports, and restructure their corporate strategy as needed. The emotion engine continuously receives user feedback and incorporates it into future interface and content creation.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0162] In analyzing corporate financial data, a major challenge is the significant time and effort required for data extraction, anomaly detection, and future forecasting. Furthermore, the lack of information provision that considers user sentiment leads to a lack of understanding and acceptance of the information users receive.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes means for receiving and automatically extracting information including financial data, means for storing the extracted financial information in a storage device, means for analyzing the stored financial information to detect anomalies and further predict future indicators, and means for analyzing user sentiment information and optimizing the method of presenting information. This enables efficient analysis of financial data and the provision of information optimized for the user.

[0165] "Financial data" refers to numerical information related to the economic activities of a company or organization, and generally includes information such as sales, profits, costs, assets, and liabilities.

[0166] "Information" refers to knowledge or news about facts, events, or data, expressed in this context in an electronically stored or processed form.

[0167] "Storage device" refers to computer hardware capable of storing and retrieving information, and generally includes hard disks, SSDs, databases, and so on.

[0168] An "outlier" refers to a value that deviates significantly from the standard or expected value, and in data analysis, it is used to identify values ​​that exceed the normal range.

[0169] "Data analysis technology" refers to methods and techniques for extracting meaning and value from large amounts of information, and includes statistical analysis, machine learning, and artificial intelligence.

[0170] "User sentiment information" refers to the emotional reactions and states of information users, and is usually evaluated through natural language processing and sentiment analysis technologies.

[0171] "Natural language processing technology" refers to technology that enables computers to understand human language and interact with humans.

[0172] This invention provides an interactive system that efficiently analyzes a company's financial data and takes user emotions into consideration. The system includes a series of means for managing, analyzing, and optimizing the user interface of financial information.

[0173] The process begins with the user using a terminal to upload electronic documents containing company financial data. The terminal supports common data formats such as PDF and Excel files, which are sent to the server. The server processes and extracts the uploaded information using data analysis techniques. Here, the Python pandas library is used to analyze the data structure, and natural language processing software is used for natural language processing.

[0174] The server stores the extracted financial information in a storage device (database software). This information is later compared with information from other organizations and used for statistical analysis and anomaly detection. Anomaly detection is performed based on a statistical model utilizing the SciPy library, and if an anomaly is detected, the user is immediately notified.

[0175] Furthermore, the server uses sentiment analysis software to analyze the user's emotional information and adjust the tone and presentation of the information it provides. In this process, for example, a computer can analyze the user's responses and generate the most considerate information in an appropriate tone.

[0176] Furthermore, the user interface on the device dynamically changes according to the user's emotional state. This provides an optimal user experience, allowing users to understand important information without stress.

[0177] For example, when a user is interested in a particular financial metric, the system will focus on displaying information related to that metric and explain it in an easy-to-understand way. For instance, by entering a prompt such as, "What is the sales growth rate this year?", the system will generate and visually present detailed information about sales.

[0178] With this configuration, companies can efficiently obtain data to make quick and accurate decisions, and information tailored to the user can be provided.

[0179] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0180] Step 1:

[0181] Users upload electronic documents, including company financial data, via their terminals. Inputs include PDF and Excel files. The terminals send these files to the server. The server receives the uploaded data as output.

[0182] Step 2:

[0183] The server processes received electronic documents using advanced data analysis techniques. Specifically, it uses the Python pandas library to extract financial information in the required format. This process yields structured data that can be stored in a database. The input is electronic documents, and the output is structured financial information.

[0184] Step 3:

[0185] The server stores the extracted financial information in storage. The data stored in the database forms the basis for subsequent analysis and anomaly detection. The input here is the extracted structured data, and the output is that data stored in the database.

[0186] Step 4:

[0187] The server performs statistical analysis based on stored financial information and compares it with information from other organizations. During this process, it uses the SciPy library to detect outliers. When an outlier is detected, an automated process is initiated to notify the user. The input is stored financial information, and the output is notification information regarding the outlier.

[0188] Step 5:

[0189] The server drives a generative AI model and, as needed, uses natural language generation technology to generate records in plain language. Specifically, it automatically creates reports based on financial information. The input is analysis results, including outliers, and the output is a written report.

[0190] Step 6:

[0191] The server uses emotion analysis software to analyze the user's emotional information. Based on the analysis results, it adjusts the tone and visual presentation of the information provided. Specifically, the user interface on the terminal dynamically adapts according to the user's emotional state. The input is data related to the user's emotions, and the output is the adjusted user interface.

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] In today's economic environment, individuals and businesses need to accurately understand financial indicators and make future financial forecasts, but this is an extremely complex task. Furthermore, there is a problem where information is not fully utilized because it does not take into account user sentiment. Information overload and complexity make it difficult for users to make accurate decisions.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes means for receiving electronic documents containing financial data and automatically extracting economic information from said electronic documents; means for storing the extracted economic information in an information management system; means for comparing the stored economic information with economic information from other industries and detecting anomalies; means for automatically generating information displays based on the detected anomalies; means for driving a learning algorithm using past financial data and predicting future economic indicators; and means for analyzing the user's emotions using emotion analysis technology and adjusting the content and display method of the report. This makes it possible to provide financial information in a way that is easy for the user to understand and to present the information with an emotion-sensitive interface.

[0197] "Financial data" refers to information, including economic indicators and records, that companies and individuals use to manage their economic activities.

[0198] An "electronic document" is a document recorded in a format that can be read by an information processing device such as a computer.

[0199] "Economic information" refers to specific figures, categories, and indicators extracted from financial data, and is information used for analysis and comparison.

[0200] An "information management system" is a system for storing and managing various types of collected data, and for retrieving and utilizing it as needed.

[0201] An "outlier" refers to a value that falls outside the normal range and is considered a statistically unique data point.

[0202] "Information display" is a means of visually representing analysis results and data and communicating them to users.

[0203] A "learning algorithm" is a method for computers to automatically learn patterns and insights from data.

[0204] An "economic indicator" is a numerical value used as a standard to measure the state of the economy.

[0205] "Emotional analysis technology" is a technology that estimates and analyzes a user's emotional state from text, voice, and other sources.

[0206] An "interface" refers to the points of contact or means of exchanging information between a user and a system.

[0207] To implement this invention, the server first receives an electronic document containing financial data from a user. The server then uses natural language processing techniques to automatically extract the necessary economic information. Libraries such as Python and TensorFlow can be utilized for this process. The extracted economic information is stored in an information management system and used for detecting outliers and comparing it with economic information from other industries.

[0208] The server automatically detects anomalies based on this data and automatically generates information displays from the data analysis results. In this process, the user's emotional state is detected by sentiment analysis technology and influences the report display. For example, if a user feels anxious due to economic fluctuations, the interface visually displays information that promotes the user's sense of security. Machine learning libraries such as SciKit-Learn and Keras are often used for this process.

[0209] Furthermore, the device dynamically adjusts the interface design, colors, font sizes, and other elements based on the user's emotions. This adjustment is performed using JavaScript® and CSS technologies to provide the most comfortable user experience.

[0210] For example, if a user purchases a new, large home appliance and wants to know how it will affect their budget, this invention predicts in real time how the purchase will change the user's financial situation and provides reassuring information. An example of a prompt using the generative AI model would be: "If a user is feeling anxious about purchasing a large item, create a report on its economic impact and provide reassurance."

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The server receives electronic documents containing financial data submitted by users. This input includes data in CSV or Excel format. The server uses natural language processing technology to automatically extract economic information from these documents. This process tokenizes the documents and identifies necessary financial indicators using a pre-trained model. The extracted economic information is output as variable data.

[0214] Step 2:

[0215] The server stores the extracted economic information in an information management system. This information is stored using a database management system (DBMS). The database efficiently stores the economic information and generates indexes to allow for quick access in subsequent processing. This output is a dataset used in subsequent processing.

[0216] Step 3:

[0217] The server detects anomalies by comparing stored economic data with economic data from other industries. This involves using statistical analysis methods and rule-based algorithms to identify unusual patterns. The output includes data flagged as singularities.

[0218] Step 4:

[0219] The server automatically generates information displays based on detected anomalies. Using a generation AI model, it generates prompts indicating the causes of the anomalies and providing guidelines. This output is presented in the form of graphs and dashboards for visualization.

[0220] Step 5:

[0221] The terminal displays information received from the server according to the user's emotional state. In this step, emotion analysis technology analyzes the user's past behavior history and current interactions, dynamically changing the interface design, colors, and font size. The output is an interface adjusted to best suit the user's emotions.

[0222] Step 6:

[0223] Based on the displayed information, users review their own economic behavior. They refer to the provided improvement suggestions and information on ongoing budget adjustments to make decisions for the next steps. This output is a concrete action plan that will become part of the user's future financial plan.

[0224] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0225] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0226] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0227] [Second Embodiment]

[0228] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0229] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0230] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0231] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0232] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0233] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0234] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0235] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0236] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0237] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0238] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0239] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0240] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. This system utilizes generative AI technology to automatically extract financial information from electronic financial statements and store it in a database. The system consists of the following elements:

[0241] First, the user uploads the company's financial statements to the system from their terminal. The system receives the uploaded electronic document, and the server analyzes the document using natural language processing technology. This automatically extracts key financial indicators and records them in a structured data format in the database. This eliminates the need for manual data entry and significantly reduces the risk of input errors.

[0242] Next, the server uses the stored database to detect anomalies and perform comparative analysis with competitors. When anomalies are detected, the system automatically generates an alert. The insights gained at this stage allow companies to quickly develop strategies to gain a competitive advantage.

[0243] Furthermore, based on the generated data and analysis results, the server automatically creates reports. Natural language generation technology is used to explain financial indicators in simple language that is easy for non-experts to understand. These reports are presented on the terminal via a dashboard, allowing users to easily access and download them as needed.

[0244] Ultimately, a machine learning algorithm based on historical data allows the server to predict future financial conditions. This predictive model visualizes future sales growth and profitability, aiding in strategic decision-making. For example, if predicted sales growth exceeds the industry average, users can re-evaluate their growth strategy and review necessary investments.

[0245] These features make the present invention widely applicable as a system that significantly streamlines a company's financial management process and enables rapid management decisions.

[0246] The following describes the processing flow.

[0247] Step 1:

[0248] Users upload electronic financial statements from their devices to the system. This provides the system with PDF or Excel as the file format to be used.

[0249] Step 2:

[0250] The server receives the uploaded electronic document and selects the appropriate file parser. Next, it uses natural language processing technology to automatically extract financial information such as sales, profits, and assets from the financial statement and converts it into structured data.

[0251] Step 3:

[0252] The server stores the extracted financial data in a database. The stored data is used for subsequent analysis, anomaly detection, industry comparisons, and report generation.

[0253] Step 4:

[0254] The server uses stored data to apply an anomaly detection algorithm and evaluate how detected anomalies are impacting performance. If an anomaly is detected, the system automatically generates an alert and prepares to notify relevant parties.

[0255] Step 5:

[0256] The server drives the report generation engine based on the data it collects and analyzes. Utilizing natural language generation technology, the reports are written in simple language, minimizing technical jargon.

[0257] Step 6:

[0258] The generated reports are displayed on a dashboard on the device, allowing users to view, download, and print them. The information is also provided in a visually easy-to-understand format using graphs and charts.

[0259] Step 7:

[0260] The server trains a machine learning model based on historical data to predict future financial indicators. The prediction results are visualized on the terminal, clearly showing future growth potential and profitability.

[0261] Step 8:

[0262] The system makes strategic decisions based on the predictive data provided by the user and develops new action plans. Continuous improvement is achieved by feeding back the changed strategic information into the system as needed.

[0263] (Example 1)

[0264] Next, we will describe Example 1. 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."

[0265] Companies are required to efficiently manage vast amounts of financial data and make quick and accurate business decisions. However, conventional methods require a great deal of time and effort for manual data entry and analysis, and are prone to input errors and delays in information. Furthermore, there is a lack of practical means for quickly and accurately comparing financial performance with competitors and making future financial forecasts. This invention aims to solve these problems.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes means for receiving information provided in the form of an electronic document and automatically extracting financial indicators from said information; means for storing the extracted financial indicators in a data storage device; and means for comparing the stored financial indicators with the financial indicators of other entities and identifying outliers. This enables companies to efficiently analyze and store financial data, achieve rapid and accurate detection of outliers and future financial forecasts, and improve the quality of management decisions.

[0268] An "electronic document" is a document expressed in a digital format that can be read on a computer or digital device.

[0269] "Financial indicators" are statistical data used to quantify a company's financial condition and performance, and include sales revenue and profit margins.

[0270] A "data storage device" is a device or system for recording and retaining information for later use.

[0271] An "outlier" is a value that falls outside the normal range and exhibits specific or unexpected behavior within a dataset.

[0272] A "generative AI model" is a mathematical model that uses machine learning or artificial intelligence technology to generate new insights and predictions from data.

[0273] "Natural language generation technology" is a technology that enables computers to express analysis results and information in natural language that is easy for humans to understand.

[0274] "Natural language processing technology" refers to the techniques and methods used to enable computers to understand, interpret, and generate human language.

[0275] "Machine learning techniques" refer to a set of algorithms and methods for finding patterns in data and using them to learn and make predictions.

[0276] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. Its embodiments are described in detail below.

[0277] First, users upload their company's financial statements to the system as electronic documents using a device. Typically, a PC or tablet is used as the device, connecting to the server via the internet. This upload process is carried out through an upload form provided in a web browser.

[0278] The server operates natural language processing (NLP) technology in an independent computing environment to analyze received electronic documents. Open-source libraries such as spaCy and NLTK are utilized for this purpose, automatically extracting financial indicators from documents. Furthermore, libraries such as pdf-lib and SheetJS are used to convert the contents of electronic documents into text data.

[0279] The extracted information is converted into a structured data format and stored in a data storage device, such as a relational database like MySQL or PostgreSQL. This makes it easier to search and analyze the data.

[0280] Using the stored data, the server drives generative AI models and performs analytical processing to perform financial comparisons with competitors and detect anomalies. This analysis utilizes libraries such as Scikit-learn, TensorFlow, or PyTorch, enabling machine learning models to provide insights.

[0281] As a concrete example, a prompt message such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," can be generated and passed to the generation AI.

[0282] Finally, a report is created based on the generated analysis results and predictions, and natural language generation technology is applied to make this report understandable even to non-experts. This report is displayed on the device via a web dashboard, and users can view it in real time and download it as needed.

[0283] This invention is a powerful means for companies to manage their financial information more quickly and effectively and to enhance their business intelligence.

[0284] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0285] Step 1:

[0286] The user uploads the company's financial statements to the system using a terminal. As input, an electronic document in PDF or Excel format is assumed, which is sent to the server via a web browser. As output, an electronic document file temporarily stored on the server is obtained. This process starts when the user drags and drops the file onto the upload form.

[0287] Step 2:

[0288] The server prepares to analyze the content of the received electronic document. Specifically, libraries such as pdf-lib for PDF analysis and SheetJS for Excel analysis are used. As input, the uploaded electronic document is provided. The server converts its content into text data and performs preprocessing for financial indicator extraction. As output, analyzable text data is obtained. In this step, it is also checked simultaneously whether the file is properly formatted.

[0289] Step 3:

[0290] The server extracts financial indicators from the text data converted using natural language processing techniques. Here, spaCy or NLTK is utilized to identify specific information such as amounts, dates, and department names in the document. The text data obtained from the preprocessing is used as input, and the extracted financial indicators are generated as output. At this stage, through processes such as tokenization and part-of-speech tagging, the necessary information can be reliably retrieved.

[0291] Step 4:

[0292] The server stores the extracted financial indicators in a structured data format in a data storage device. Specifically, it performs data insertion operations on SQL databases such as MySQL and PostgreSQL. A dataset of the extracted financial indicators is prepared as input. The structured data recorded in the database is obtained as output. This storage process also includes verification to prevent data duplication and inconsistencies.

[0293] Step 5:

[0294] The server uses stored financial indicators to perform comparisons with competitors and detect outliers. Here, machine learning models are operated using libraries such as Scikit-learn and TensorFlow. Financial indicators stored in the database are used as input, and the output generates a list of outliers and comparative analysis results with competitors. Regression analysis and clustering techniques are often applied to this analysis.

[0295] Step 6:

[0296] The server generates prompts using a generative AI model and creates a report based on the analysis results. Natural language generation technology is used to organize the information in a way that is easy for non-experts to understand. The input is the analysis results obtained in step 5. The output is a detailed report document. This report may include graphs and tables, along with explanatory text.

[0297] Step 7:

[0298] The terminal displays reports on a dashboard accessible to the user. Reports are provided in HTML or PDF format, and users can view and download them directly from their browser. Server-generated reports serve as input. A specific UI framework (e.g., React or Vue.js) is used to present information while maintaining a good user experience.

[0299] Step 8:

[0300] The server drives a machine learning algorithm using historical data to predict future financial conditions. Historical financial data is used as input. The output reports forecasts for future sales growth and profitability. This allows users to gain visual insights for strategic decision-making. Specifically, a prompt such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," is used.

[0301] (Application Example 1)

[0302] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0303] Managing and analyzing financial data within companies often involves manual processes, which are time-consuming, labor-intensive, and prone to input errors. Furthermore, comparing financial performance with competitors and detecting anomalies can be inconsistent. There is a need for rapid and highly accurate financial data management and forecasting, along with the creation of easily understandable reports.

[0304] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0305] In this invention, the server includes means for automatically extracting information including financial information, means for storing the extracted financial data in a storage area, and means for comparing the stored financial data with the financial data of competitors. This enables efficient management of financial data, immediate detection of abnormal events, highly accurate prediction of future financial indicators, and support for re-evaluating business strategies based on the results.

[0306] "Financial information" refers to data that shows a company's financial condition and economic activities, and includes profits, expenses, assets, liabilities, etc.

[0307] "Information" refers to data that represents facts, events, concepts, etc., and is used for specific purposes.

[0308] "Extraction" refers to the operation of extracting specific data or information from a large dataset.

[0309] "Storage area" refers to a physical or virtual space for recording and holding digital data.

[0310] "Abnormal event" refers to values or situations that exceed the normal range, indicating unexpected fluctuations or abnormalities.

[0311] "Report" is a document that summarizes and reports specific information or analysis results, and is used to support decision-making.

[0312] "Analysis algorithm" refers to a series of procedures or calculation methods for extracting useful patterns and information from a large amount of data.

[0313] "Future financial indicator" refers to an indicator that shows the estimated or predicted values of a company's future financial situation, including sales and profits.

[0314] "Visualization" means visually representing data or information, and is a technique to enhance understandability.

[0315] "Business strategy" refers to the means and methods planned by a company to achieve its goals, and is a framework to support business policies.

[0316] "Sales data" refers to data related to the revenue obtained from the sales of products or services provided by a company.

[0317] "Notification" is an act of informing a person or a system of specific information, and is used to draw attention.

[0318] This invention is a system for efficiently managing and analyzing financial information. The server receives electronic documents containing financial information sent by users and automatically extracts specific information. This reduces manual data entry and improves data accuracy.

[0319] The primary software used is the Python pandas library, which is used for loading and manipulating data. Additionally, the scikit-learn library is used to detect anomalies using machine learning algorithms. Matplotlib and seaborn are used for data visualization, generating clean and clear visuals.

[0320] The server compares stored financial data with that of competitors and immediately detects anomalies. Information about detected anomalies is reported to the user through notifications. Furthermore, analytical algorithms predict future financial indicators and support the re-evaluation of business strategies based on this data. The visualized results are presented as a report on the user's terminal and used as a basis for decision-making.

[0321] For example, if a company inputs its quarterly sales data into this system, the system can quickly detect anomalies in sales and use that information to make informed business decisions. It can also forecast sales considering specific seasons and campaign effects, providing opportunities to improve marketing strategies.

[0322] By utilizing a generative AI model, it is possible to automate a portion of the program that performs the aforementioned series of processes. As an example of a prompt statement to be used for this, the following text could be used as input data: "Analyze the latest sales data, detect anomalies, and create a report. Compare it with competitors and include suggestions for adjusting business strategies if necessary."

[0323] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0324] Step 1:

[0325] The user uploads an electronic document containing financial information from their terminal. The terminal sends this electronic document to the server, which prepares to store the received document in a database for analysis. This input includes sales information, expense information, etc., and the server prepares this as data for analysis.

[0326] Step 2:

[0327] The server automatically analyzes the stored electronic documents. Specifically, it uses a generative AI model to select the necessary financial information and extracts it as structured data using the pandas library. This process yields a dataset of financial indicators as output.

[0328] Step 3:

[0329] The server stores the extracted financial data in a storage area according to the schema. This storage area is the database used for subsequent analytical processing. The input data is converted to an appropriate format and stored securely.

[0330] Step 4:

[0331] Based on the stored data, the server uses the scikit-learn library to detect anomalies. Specifically, it runs anomaly detection algorithms such as Isolation Forest to identify outliers in the financial data. The output of this step is the location and value of the data points identified as anomalies.

[0332] Step 5:

[0333] The server compares outliers with financial data from competitors as a baseline. When an anomaly is detected, it generates and sends alerts and notifications to the user. This process allows the user to immediately recognize significant performance fluctuations.

[0334] Step 6:

[0335] The user receives a report generated by the server. The server uses matplotlib and seaborn to visualize the data and formats it into a report using natural language generation technology. This allows the user to receive materials for future sales forecasts and strategic planning.

[0336] Step 7:

[0337] The server runs machine learning models based on historical financial data to visualize future financial indicators. This includes sales forecasts and expense trend graphs, presented to users in a visually easy-to-understand format. The analysis results are output as data to be incorporated into business strategies.

[0338] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0339] This invention efficiently analyzes a company's financial data and is implemented as an interactive system that takes user emotions into consideration. This system includes an emotion engine for managing, analyzing, and optimizing the user interface of financial information.

[0340] First, the user uploads electronic documents containing the company's financial data from their device. This data is received by a server, and the necessary financial information is automatically extracted using natural language processing technology. The extracted data is stored in a database and used for future anomaly detection and industry comparisons.

[0341] Next, the server uses the stored financial information to compare with competitors, and automatically generates an alert if anomalies are detected. Furthermore, it analyzes the user's emotions through an emotion engine and selects the most considerate report content and presentation style to provide a report that is as easy to understand as possible for the user.

[0342] When a report is generated, natural language generation technology is used to create a simple and easy-to-understand text, and then the report is refined based on sentiment analysis results. On the device, the dashboard design, colors, and font size are dynamically changed according to the user's emotional state to provide an optimal user experience.

[0343] Furthermore, based on past data, the server uses machine learning algorithms to predict future financial conditions. This predictive information is also refined by an emotion engine and displayed on the device in a visually easy-to-understand format.

[0344] For example, if the emotion engine determines that a user has negative feelings about a particular financial indicator, the system will highlight that indicator and automatically suggest detailed explanations and improvement measures. In this way, the present invention significantly advances conventional financial management systems by supporting rapid and accurate decision-making for companies and providing a flexible interface adapted to individual users.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] Users upload electronic documents containing company financial data from their devices. The system supports file formats such as PDF and Excel.

[0348] Step 2:

[0349] The server receives uploaded electronic documents, selects the appropriate file parser, and analyzes the documents. Using natural language processing technology, it automatically extracts necessary financial information such as sales and profits.

[0350] Step 3:

[0351] The server extracts financial data, structures it, and stores it in a database. This creates a data base that can be used for subsequent analysis and anomaly detection.

[0352] Step 4:

[0353] The server uses stored data to compare it with data from competitors and runs an algorithm to detect anomalies. Analysis is performed on the detected anomalies, and alerts are generated as needed.

[0354] Step 5:

[0355] The server uses an emotion engine to analyze the user's emotional state based on their past feedback and behavioral patterns. This emotional data is considered when generating reports.

[0356] Step 6:

[0357] The server generates a report based on financial data and anomaly analysis results. It uses natural language generation technology to create plain text and adjusts the expression based on sentiment engine analysis results.

[0358] Step 7:

[0359] The generated report is displayed on the device and can be viewed on the dashboard. The system dynamically changes the interface colors and layout according to the user's emotional state to provide an optimal display.

[0360] Step 8:

[0361] The server uses historical data to train machine learning models and predict future financial indicators. These predictions are then refined based on the analysis results of the emotion engine and presented to the device in a visually easy-to-understand format.

[0362] Step 9:

[0363] Users review detailed forecast data and reports, and restructure their corporate strategy as needed. The emotion engine continuously receives user feedback and incorporates it into future interface and content creation.

[0364] (Example 2)

[0365] Next, we will describe Example 2. 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".

[0366] In analyzing corporate financial data, a major challenge is the significant time and effort required for data extraction, anomaly detection, and future forecasting. Furthermore, the lack of information provision that considers user sentiment leads to a lack of understanding and acceptance of the information users receive.

[0367] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0368] In this invention, the server includes means for receiving and automatically extracting information including financial data, means for storing the extracted financial information in a storage device, means for analyzing the stored financial information to detect anomalies and further predict future indicators, and means for analyzing user sentiment information and optimizing the method of presenting information. This enables efficient analysis of financial data and the provision of information optimized for the user.

[0369] "Financial data" refers to numerical information related to the economic activities of a company or organization, and generally includes information such as sales, profits, costs, assets, and liabilities.

[0370] "Information" refers to knowledge or news about facts, events, or data, expressed in this context in an electronically stored or processed form.

[0371] "Storage device" refers to computer hardware capable of storing and retrieving information, and generally includes hard disks, SSDs, databases, and so on.

[0372] An "outlier" refers to a value that deviates significantly from the standard or expected value, and in data analysis, it is used to identify values ​​that exceed the normal range.

[0373] "Data analysis technology" refers to methods and techniques for extracting meaning and value from large amounts of information, and includes statistical analysis, machine learning, and artificial intelligence.

[0374] "User sentiment information" refers to the emotional reactions and states of information users, and is usually evaluated through natural language processing and sentiment analysis technologies.

[0375] "Natural language processing technology" refers to technology that enables computers to understand human language and interact with humans.

[0376] This invention provides an interactive system that efficiently analyzes a company's financial data and takes user emotions into consideration. The system includes a series of means for managing, analyzing, and optimizing the user interface of financial information.

[0377] The process begins with the user using a terminal to upload electronic documents containing company financial data. The terminal supports common data formats such as PDF and Excel files, which are sent to the server. The server processes and extracts the uploaded information using data analysis techniques. Here, the Python pandas library is used to analyze the data structure, and natural language processing software is used for natural language processing.

[0378] The server stores the extracted financial information in a storage device (database software). This information is later compared with information from other organizations and used for statistical analysis and anomaly detection. Anomaly detection is performed based on a statistical model utilizing the SciPy library, and if an anomaly is detected, the user is immediately notified.

[0379] Furthermore, the server uses sentiment analysis software to analyze the user's emotional information and adjust the tone and presentation of the information it provides. In this process, for example, a computer can analyze the user's responses and generate the most considerate information in an appropriate tone.

[0380] Furthermore, the user interface on the device dynamically changes according to the user's emotional state. This provides an optimal user experience, allowing users to understand important information without stress.

[0381] For example, when a user is interested in a particular financial metric, the system will focus on displaying information related to that metric and explain it in an easy-to-understand way. For instance, by entering a prompt such as, "What is the sales growth rate this year?", the system will generate and visually present detailed information about sales.

[0382] With this configuration, companies can efficiently obtain data to make quick and accurate decisions, and information tailored to the user can be provided.

[0383] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0384] Step 1:

[0385] Users upload electronic documents, including company financial data, via their terminals. Inputs include PDF and Excel files. The terminals send these files to the server. The server receives the uploaded data as output.

[0386] Step 2:

[0387] The server processes received electronic documents using advanced data analysis techniques. Specifically, it uses the Python pandas library to extract financial information in the required format. This process yields structured data that can be stored in a database. The input is electronic documents, and the output is structured financial information.

[0388] Step 3:

[0389] The server stores the extracted financial information in storage. The data stored in the database forms the basis for subsequent analysis and anomaly detection. The input here is the extracted structured data, and the output is that data stored in the database.

[0390] Step 4:

[0391] The server performs statistical analysis based on stored financial information and compares it with information from other organizations. During this process, it uses the SciPy library to detect outliers. When an outlier is detected, an automated process is initiated to notify the user. The input is stored financial information, and the output is notification information regarding the outlier.

[0392] Step 5:

[0393] The server drives a generative AI model and, as needed, uses natural language generation technology to generate records in plain language. Specifically, it automatically creates reports based on financial information. The input is analysis results, including outliers, and the output is a written report.

[0394] Step 6:

[0395] The server uses emotion analysis software to analyze the user's emotional information. Based on the analysis results, it adjusts the tone and visual presentation of the information provided. Specifically, the user interface on the terminal dynamically adapts according to the user's emotional state. The input is data related to the user's emotions, and the output is the adjusted user interface.

[0396] (Application Example 2)

[0397] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0398] In today's economic environment, individuals and businesses need to accurately understand financial indicators and make future financial forecasts, but this is an extremely complex task. Furthermore, there is a problem where information is not fully utilized because it does not take into account user sentiment. Information overload and complexity make it difficult for users to make accurate decisions.

[0399] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0400] In this invention, the server includes means for receiving electronic documents containing financial data and automatically extracting economic information from said electronic documents; means for storing the extracted economic information in an information management system; means for comparing the stored economic information with economic information from other industries and detecting anomalies; means for automatically generating information displays based on the detected anomalies; means for driving a learning algorithm using past financial data and predicting future economic indicators; and means for analyzing the user's emotions using emotion analysis technology and adjusting the content and display method of the report. This makes it possible to provide financial information in a way that is easy for the user to understand and to present the information with an emotion-sensitive interface.

[0401] "Financial data" refers to information, including economic indicators and records, that companies and individuals use to manage their economic activities.

[0402] An "electronic document" is a document recorded in a format that can be read by an information processing device such as a computer.

[0403] "Economic information" refers to specific figures, categories, and indicators extracted from financial data, and is information used for analysis and comparison.

[0404] An "information management system" is a system for storing and managing various types of collected data, and for retrieving and utilizing it as needed.

[0405] An "outlier" refers to a value that falls outside the normal range and is considered a statistically unique data point.

[0406] "Information display" is a means of visually representing analysis results and data and communicating them to users.

[0407] A "learning algorithm" is a method for computers to automatically learn patterns and insights from data.

[0408] An "economic indicator" is a numerical value used as a standard to measure the state of the economy.

[0409] "Emotional analysis technology" is a technology that estimates and analyzes a user's emotional state from text, voice, and other sources.

[0410] An "interface" refers to the points of contact or means of exchanging information between a user and a system.

[0411] To implement this invention, the server first receives an electronic document containing financial data from a user. The server then uses natural language processing techniques to automatically extract the necessary economic information. Libraries such as Python and TensorFlow can be utilized for this process. The extracted economic information is stored in an information management system and used for detecting outliers and comparing it with economic information from other industries.

[0412] The server automatically detects anomalies based on this data and automatically generates information displays from the data analysis results. In this process, the user's emotional state is detected by sentiment analysis technology and influences the report display. For example, if a user feels anxious due to economic fluctuations, the interface visually displays information that promotes the user's sense of security. Machine learning libraries such as SciKit-Learn and Keras are often used for this process.

[0413] Furthermore, the device dynamically adjusts the interface design, colors, font sizes, and other elements based on the user's emotions. This adjustment is performed using JavaScript and CSS techniques to provide the most comfortable user experience.

[0414] For example, if a user purchases a new, large home appliance and wants to know how it will affect their budget, this invention predicts in real time how the purchase will change the user's financial situation and provides reassuring information. An example of a prompt using the generative AI model would be: "If a user is feeling anxious about purchasing a large item, create a report on its economic impact and provide reassurance."

[0415] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0416] Step 1:

[0417] The server receives electronic documents containing financial data submitted by users. This input includes data in CSV or Excel format. The server uses natural language processing technology to automatically extract economic information from these documents. This process tokenizes the documents and identifies necessary financial indicators using a pre-trained model. The extracted economic information is output as variable data.

[0418] Step 2:

[0419] The server stores the extracted economic information in an information management system. This information is stored using a database management system (DBMS). The database efficiently stores the economic information and generates indexes to allow for quick access in subsequent processing. This output is a dataset used in subsequent processing.

[0420] Step 3:

[0421] The server detects anomalies by comparing stored economic data with economic data from other industries. This involves using statistical analysis methods and rule-based algorithms to identify unusual patterns. The output includes data flagged as singularities.

[0422] Step 4:

[0423] The server automatically generates information displays based on detected anomalies. Using a generation AI model, it generates prompts indicating the causes of the anomalies and providing guidelines. This output is presented in the form of graphs and dashboards for visualization.

[0424] Step 5:

[0425] The terminal displays information received from the server according to the user's emotional state. In this step, emotion analysis technology analyzes the user's past behavior history and current interactions, dynamically changing the interface design, colors, and font size. The output is an interface adjusted to best suit the user's emotions.

[0426] Step 6:

[0427] Based on the displayed information, users review their own economic behavior. They refer to the provided improvement suggestions and information on ongoing budget adjustments to make decisions for the next steps. This output is a concrete action plan that will become part of the user's future financial plan.

[0428] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0429] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0430] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0431] [Third Embodiment]

[0432] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0433] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0434] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0435] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0436] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0437] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0438] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0439] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0440] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0441] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0442] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0443] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0444] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. This system utilizes generative AI technology to automatically extract financial information from electronic financial statements and store it in a database. The system consists of the following elements:

[0445] First, the user uploads the company's financial statements to the system from their terminal. The system receives the uploaded electronic document, and the server analyzes the document using natural language processing technology. This automatically extracts key financial indicators and records them in a structured data format in the database. This eliminates the need for manual data entry and significantly reduces the risk of input errors.

[0446] Next, the server uses the stored database to detect anomalies and perform comparative analysis with competitors. When anomalies are detected, the system automatically generates an alert. The insights gained at this stage allow companies to quickly develop strategies to gain a competitive advantage.

[0447] Furthermore, based on the generated data and analysis results, the server automatically creates reports. Natural language generation technology is used to explain financial indicators in simple language that is easy for non-experts to understand. These reports are presented on the terminal via a dashboard, allowing users to easily access and download them as needed.

[0448] Ultimately, a machine learning algorithm based on historical data allows the server to predict future financial conditions. This predictive model visualizes future sales growth and profitability, aiding in strategic decision-making. For example, if predicted sales growth exceeds the industry average, users can re-evaluate their growth strategy and review necessary investments.

[0449] These features make the present invention widely applicable as a system that significantly streamlines a company's financial management process and enables rapid management decisions.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] Users upload electronic financial statements from their devices to the system. This provides the system with PDF or Excel as the file format to be used.

[0453] Step 2:

[0454] The server receives the uploaded electronic document and selects the appropriate file parser. Next, it uses natural language processing technology to automatically extract financial information such as sales, profits, and assets from the financial statement and converts it into structured data.

[0455] Step 3:

[0456] The server stores the extracted financial data in a database. The stored data is used for subsequent analysis, anomaly detection, industry comparisons, and report generation.

[0457] Step 4:

[0458] The server uses stored data to apply an anomaly detection algorithm and evaluate how detected anomalies are impacting performance. If an anomaly is detected, the system automatically generates an alert and prepares to notify relevant parties.

[0459] Step 5:

[0460] The server drives the report generation engine based on the data it collects and analyzes. Utilizing natural language generation technology, the reports are written in simple language, minimizing technical jargon.

[0461] Step 6:

[0462] The generated reports are displayed on a dashboard on the device, allowing users to view, download, and print them. The information is also provided in a visually easy-to-understand format using graphs and charts.

[0463] Step 7:

[0464] The server trains a machine learning model based on historical data to predict future financial indicators. The prediction results are visualized on the terminal, clearly showing future growth potential and profitability.

[0465] Step 8:

[0466] The system makes strategic decisions based on the predictive data provided by the user and develops new action plans. Continuous improvement is achieved by feeding back the changed strategic information into the system as needed.

[0467] (Example 1)

[0468] Next, we will describe Example 1. 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."

[0469] Companies are required to efficiently manage vast amounts of financial data and make quick and accurate business decisions. However, conventional methods require a great deal of time and effort for manual data entry and analysis, and are prone to input errors and delays in information. Furthermore, there is a lack of practical means for quickly and accurately comparing financial performance with competitors and making future financial forecasts. This invention aims to solve these problems.

[0470] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0471] In this invention, the server includes means for receiving information provided in the form of an electronic document and automatically extracting financial indicators from said information; means for storing the extracted financial indicators in a data storage device; and means for comparing the stored financial indicators with the financial indicators of other entities and identifying outliers. This enables companies to efficiently analyze and store financial data, achieve rapid and accurate detection of outliers and future financial forecasts, and improve the quality of management decisions.

[0472] An "electronic document" is a document expressed in a digital format that can be read on a computer or digital device.

[0473] "Financial indicators" are statistical data used to quantify a company's financial condition and performance, and include sales revenue and profit margins.

[0474] A "data storage device" is a device or system for recording and retaining information for later use.

[0475] An "outlier" is a value that falls outside the normal range and exhibits specific or unexpected behavior within a dataset.

[0476] A "generative AI model" is a mathematical model that uses machine learning or artificial intelligence technology to generate new insights and predictions from data.

[0477] "Natural language generation technology" is a technology that enables computers to express analysis results and information in natural language that is easy for humans to understand.

[0478] "Natural language processing technology" refers to the techniques and methods used to enable computers to understand, interpret, and generate human language.

[0479] "Machine learning techniques" refer to a set of algorithms and methods for finding patterns in data and using them to learn and make predictions.

[0480] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. Its embodiments are described in detail below.

[0481] First, users upload their company's financial statements to the system as electronic documents using a device. Typically, a PC or tablet is used as the device, connecting to the server via the internet. This upload process is carried out through an upload form provided in a web browser.

[0482] The server operates natural language processing (NLP) technology in an independent computing environment to analyze received electronic documents. Open-source libraries such as spaCy and NLTK are utilized for this purpose, automatically extracting financial indicators from documents. Furthermore, libraries such as pdf-lib and SheetJS are used to convert the contents of electronic documents into text data.

[0483] The extracted information is converted into a structured data format and stored in a data storage device, such as a relational database like MySQL or PostgreSQL. This makes it easier to search and analyze the data.

[0484] Using the stored data, the server drives generative AI models and performs analytical processing to perform financial comparisons with competitors and detect anomalies. This analysis utilizes libraries such as Scikit-learn, TensorFlow, or PyTorch, enabling machine learning models to provide insights.

[0485] As a concrete example, a prompt message such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," can be generated and passed to the generation AI.

[0486] Finally, a report is created based on the generated analysis results and predictions, and natural language generation technology is applied to make this report understandable even to non-experts. This report is displayed on the device via a web dashboard, and users can view it in real time and download it as needed.

[0487] This invention is a powerful means for companies to manage their financial information more quickly and effectively and to enhance their business intelligence.

[0488] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0489] Step 1:

[0490] Users upload their company's financial statements to the system using a terminal. Input is expected to be electronic documents in PDF or Excel format, which are sent to the server via a web browser. Output is an electronic document file temporarily stored on the server. This process begins with the user dragging and dropping the file into the upload form.

[0491] Step 2:

[0492] The server prepares to analyze the contents of the received electronic document. Specifically, it uses libraries such as pdf-lib for PDF analysis and SheetJS for Excel analysis. The uploaded electronic document is provided as input. The server converts its contents into text data and performs preprocessing for extracting financial indicators. The output is parseable text data. This step also verifies that the file is properly formatted.

[0493] Step 3:

[0494] The server extracts financial indicators from text data converted using natural language processing technology. Here, spaCy and NLTK are used to identify specific information such as amounts, dates, and department names within the document. The input is pre-processed text data, and the output is the extracted financial indicators. At this stage, processes such as tokenization and part-of-speech tagging are performed to ensure that the necessary information can be reliably extracted.

[0495] Step 4:

[0496] The server stores the extracted financial indicators in a structured data format in a data storage device. Specifically, it performs data insertion operations on SQL databases such as MySQL and PostgreSQL. A dataset of the extracted financial indicators is prepared as input. The structured data recorded in the database is obtained as output. This storage process also includes verification to prevent data duplication and inconsistencies.

[0497] Step 5:

[0498] The server uses stored financial indicators to perform comparisons with competitors and detect outliers. Here, machine learning models are operated using libraries such as Scikit-learn and TensorFlow. Financial indicators stored in the database are used as input, and the output generates a list of outliers and comparative analysis results with competitors. Regression analysis and clustering techniques are often applied to this analysis.

[0499] Step 6:

[0500] The server generates prompts using a generative AI model and creates a report based on the analysis results. Natural language generation technology is used to organize the information in a way that is easy for non-experts to understand. The input is the analysis results obtained in step 5. The output is a detailed report document. This report may include graphs and tables, along with explanatory text.

[0501] Step 7:

[0502] The terminal displays reports on a dashboard accessible to the user. Reports are provided in HTML or PDF format, and users can view and download them directly from their browser. Server-generated reports serve as input. A specific UI framework (e.g., React or Vue.js) is used to present information while maintaining a good user experience.

[0503] Step 8:

[0504] The server drives a machine learning algorithm using historical data to predict future financial conditions. Historical financial data is used as input. The output reports forecasts for future sales growth and profitability. This allows users to gain visual insights for strategic decision-making. Specifically, a prompt such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," is used.

[0505] (Application Example 1)

[0506] Next, we will explain Application Example 1. In the following explanation, 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."

[0507] Managing and analyzing financial data within companies often involves manual processes, which are time-consuming, labor-intensive, and prone to input errors. Furthermore, comparing financial performance with competitors and detecting anomalies can be inconsistent. There is a need for rapid and highly accurate financial data management and forecasting, along with the creation of easily understandable reports.

[0508] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0509] In this invention, the server includes means for automatically extracting information including financial information, means for storing the extracted financial data in a storage area, and means for comparing the stored financial data with the financial data of competitors. This enables efficient management of financial data, immediate detection of abnormal events, highly accurate prediction of future financial indicators, and support for re-evaluating business strategies based on the results.

[0510] "Financial information" refers to data that shows a company's financial condition and economic activities, and includes profits, expenses, assets, liabilities, etc.

[0511] "Information" refers to data that represents facts, events, concepts, etc., and is used for a specific purpose.

[0512] "Extraction" refers to the operation of taking specific data or information out of a large dataset.

[0513] "Storage area" refers to a physical or virtual space used to record and hold digital data.

[0514] An "abnormal event" refers to a value or situation that exceeds the normal range, indicating an unexpected fluctuation or anomaly.

[0515] A "report" is a document that summarizes specific information or analytical results and is used to support judgment and decision-making.

[0516] An "analysis algorithm" refers to a series of procedures or calculation methods used to extract useful patterns and information from large amounts of data.

[0517] "Future financial indicators" are indicators that show projected or predicted future financial conditions of a company, and include sales and profits.

[0518] "Visualization" is the process of representing data and information visually, and it is a technique used to improve ease of understanding.

[0519] "Business strategy" refers to the means and methods that a company plans to use to achieve its goals, and it is the framework that supports its management policies.

[0520] "Sales data" refers to data relating to the revenue generated from the sale of products and services provided by a company.

[0521] "Notification" is the act of informing a person or system of specific information, and is used to attract attention.

[0522] This invention is a system for efficiently managing and analyzing financial information. The server receives electronic documents containing financial information sent by users and automatically extracts specific information. This reduces manual data entry and improves data accuracy.

[0523] The primary software used is the Python pandas library, which is used for loading and manipulating data. Additionally, the scikit-learn library is used to detect anomalies using machine learning algorithms. Matplotlib and seaborn are used for data visualization, generating clean and clear visuals.

[0524] The server compares stored financial data with that of competitors and immediately detects anomalies. Information about detected anomalies is reported to the user through notifications. Furthermore, analytical algorithms predict future financial indicators and support the re-evaluation of business strategies based on this data. The visualized results are presented as a report on the user's terminal and used as a basis for decision-making.

[0525] For example, if a company inputs its quarterly sales data into this system, the system can quickly detect anomalies in sales and use that information to make informed business decisions. It can also forecast sales considering specific seasons and campaign effects, providing opportunities to improve marketing strategies.

[0526] By utilizing a generative AI model, it is possible to automate a portion of the program that performs the aforementioned series of processes. As an example of a prompt statement to be used for this, the following text could be used as input data: "Analyze the latest sales data, detect anomalies, and create a report. Compare it with competitors and include suggestions for adjusting business strategies if necessary."

[0527] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0528] Step 1:

[0529] The user uploads an electronic document containing financial information from their terminal. The terminal sends this electronic document to the server, which prepares to store the received document in a database for analysis. This input includes sales information, expense information, etc., and the server prepares this as data for analysis.

[0530] Step 2:

[0531] The server automatically analyzes the stored electronic documents. Specifically, it uses a generative AI model to select the necessary financial information and extracts it as structured data using the pandas library. This process yields a dataset of financial indicators as output.

[0532] Step 3:

[0533] The server stores the extracted financial data in a storage area according to the schema. This storage area is the database used for subsequent analytical processing. The input data is converted to an appropriate format and stored securely.

[0534] Step 4:

[0535] Based on the stored data, the server uses the scikit-learn library to detect anomalies. Specifically, it runs anomaly detection algorithms such as Isolation Forest to identify outliers in the financial data. The output of this step is the location and value of the data points identified as anomalies.

[0536] Step 5:

[0537] The server compares outliers with financial data from competitors as a baseline. When an anomaly is detected, it generates and sends alerts and notifications to the user. This process allows the user to immediately recognize significant performance fluctuations.

[0538] Step 6:

[0539] The user receives a report generated by the server. The server uses matplotlib and seaborn to visualize the data and formats it into a report using natural language generation technology. This allows the user to receive materials for future sales forecasts and strategic planning.

[0540] Step 7:

[0541] The server runs machine learning models based on historical financial data to visualize future financial indicators. This includes sales forecasts and expense trend graphs, presented to users in a visually easy-to-understand format. The analysis results are output as data to be incorporated into business strategies.

[0542] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0543] This invention efficiently analyzes a company's financial data and is implemented as an interactive system that takes user emotions into consideration. This system includes an emotion engine for managing, analyzing, and optimizing the user interface of financial information.

[0544] First, the user uploads electronic documents containing the company's financial data from their device. This data is received by a server, and the necessary financial information is automatically extracted using natural language processing technology. The extracted data is stored in a database and used for future anomaly detection and industry comparisons.

[0545] Next, the server uses the stored financial information to compare with competitors, and automatically generates an alert if anomalies are detected. Furthermore, it analyzes the user's emotions through an emotion engine and selects the most considerate report content and presentation style to provide a report that is as easy to understand as possible for the user.

[0546] When a report is generated, natural language generation technology is used to create a simple and easy-to-understand text, and then the report is refined based on sentiment analysis results. On the device, the dashboard design, colors, and font size are dynamically changed according to the user's emotional state to provide an optimal user experience.

[0547] Furthermore, based on past data, the server uses machine learning algorithms to predict future financial conditions. This predictive information is also refined by an emotion engine and displayed on the device in a visually easy-to-understand format.

[0548] For example, if the emotion engine determines that a user has negative feelings about a particular financial indicator, the system will highlight that indicator and automatically suggest detailed explanations and improvement measures. In this way, the present invention significantly advances conventional financial management systems by supporting rapid and accurate decision-making for companies and providing a flexible interface adapted to individual users.

[0549] The following describes the processing flow.

[0550] Step 1:

[0551] Users upload electronic documents containing company financial data from their devices. The system supports file formats such as PDF and Excel.

[0552] Step 2:

[0553] The server receives uploaded electronic documents, selects the appropriate file parser, and analyzes the documents. Using natural language processing technology, it automatically extracts necessary financial information such as sales and profits.

[0554] Step 3:

[0555] The server extracts financial data, structures it, and stores it in a database. This creates a data base that can be used for subsequent analysis and anomaly detection.

[0556] Step 4:

[0557] The server uses stored data to compare it with data from competitors and runs an algorithm to detect anomalies. Analysis is performed on the detected anomalies, and alerts are generated as needed.

[0558] Step 5:

[0559] The server uses an emotion engine to analyze the user's emotional state based on their past feedback and behavioral patterns. This emotional data is considered when generating reports.

[0560] Step 6:

[0561] The server generates a report based on financial data and anomaly analysis results. It uses natural language generation technology to create plain text and adjusts the expression based on sentiment engine analysis results.

[0562] Step 7:

[0563] The generated report is displayed on the device and can be viewed on the dashboard. The system dynamically changes the interface colors and layout according to the user's emotional state to provide an optimal display.

[0564] Step 8:

[0565] The server uses historical data to train machine learning models and predict future financial indicators. These predictions are then refined based on the analysis results of the emotion engine and presented to the device in a visually easy-to-understand format.

[0566] Step 9:

[0567] Users review detailed forecast data and reports, and restructure their corporate strategy as needed. The emotion engine continuously receives user feedback and incorporates it into future interface and content creation.

[0568] (Example 2)

[0569] Next, we will describe Example 2. 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."

[0570] In analyzing corporate financial data, a major challenge is the significant time and effort required for data extraction, anomaly detection, and future forecasting. Furthermore, the lack of information provision that considers user sentiment leads to a lack of understanding and acceptance of the information users receive.

[0571] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0572] In this invention, the server includes means for receiving and automatically extracting information including financial data, means for storing the extracted financial information in a storage device, means for analyzing the stored financial information to detect anomalies and further predict future indicators, and means for analyzing user sentiment information and optimizing the method of presenting information. This enables efficient analysis of financial data and the provision of information optimized for the user.

[0573] "Financial data" refers to numerical information related to the economic activities of a company or organization, and generally includes information such as sales, profits, costs, assets, and liabilities.

[0574] "Information" refers to knowledge or news about facts, events, or data, expressed in this context in an electronically stored or processed form.

[0575] "Storage device" refers to computer hardware capable of storing and retrieving information, and generally includes hard disks, SSDs, databases, and so on.

[0576] An "outlier" refers to a value that deviates significantly from the standard or expected value, and in data analysis, it is used to identify values ​​that exceed the normal range.

[0577] "Data analysis technology" refers to methods and techniques for extracting meaning and value from large amounts of information, and includes statistical analysis, machine learning, and artificial intelligence.

[0578] "User sentiment information" refers to the emotional reactions and states of information users, and is usually evaluated through natural language processing and sentiment analysis technologies.

[0579] "Natural language processing technology" refers to technology that enables computers to understand human language and interact with humans.

[0580] This invention provides an interactive system that efficiently analyzes a company's financial data and takes user emotions into consideration. The system includes a series of means for managing, analyzing, and optimizing the user interface of financial information.

[0581] The process begins with the user using a terminal to upload electronic documents containing company financial data. The terminal supports common data formats such as PDF and Excel files, which are sent to the server. The server processes and extracts the uploaded information using data analysis techniques. Here, the Python pandas library is used to analyze the data structure, and natural language processing software is used for natural language processing.

[0582] The server stores the extracted financial information in a storage device (database software). This information is later compared with information from other organizations and used for statistical analysis and anomaly detection. Anomaly detection is performed based on a statistical model utilizing the SciPy library, and if an anomaly is detected, the user is immediately notified.

[0583] Furthermore, the server uses sentiment analysis software to analyze the user's emotional information and adjust the tone and presentation of the information it provides. In this process, for example, a computer can analyze the user's responses and generate the most considerate information in an appropriate tone.

[0584] Furthermore, the user interface on the device dynamically changes according to the user's emotional state. This provides an optimal user experience, allowing users to understand important information without stress.

[0585] For example, when a user is interested in a particular financial metric, the system will focus on displaying information related to that metric and explain it in an easy-to-understand way. For instance, by entering a prompt such as, "What is the sales growth rate this year?", the system will generate and visually present detailed information about sales.

[0586] With this configuration, companies can efficiently obtain data to make quick and accurate decisions, and information tailored to the user can be provided.

[0587] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0588] Step 1:

[0589] Users upload electronic documents, including company financial data, via their terminals. Inputs include PDF and Excel files. The terminals send these files to the server. The server receives the uploaded data as output.

[0590] Step 2:

[0591] The server processes received electronic documents using advanced data analysis techniques. Specifically, it uses the Python pandas library to extract financial information in the required format. This process yields structured data that can be stored in a database. The input is electronic documents, and the output is structured financial information.

[0592] Step 3:

[0593] The server stores the extracted financial information in storage. The data stored in the database forms the basis for subsequent analysis and anomaly detection. The input here is the extracted structured data, and the output is that data stored in the database.

[0594] Step 4:

[0595] The server performs statistical analysis based on stored financial information and compares it with information from other organizations. During this process, it uses the SciPy library to detect outliers. When an outlier is detected, an automated process is initiated to notify the user. The input is stored financial information, and the output is notification information regarding the outlier.

[0596] Step 5:

[0597] The server drives a generative AI model and, as needed, uses natural language generation technology to generate records in plain language. Specifically, it automatically creates reports based on financial information. The input is analysis results, including outliers, and the output is a written report.

[0598] Step 6:

[0599] The server uses emotion analysis software to analyze the user's emotional information. Based on the analysis results, it adjusts the tone and visual presentation of the information provided. Specifically, the user interface on the terminal dynamically adapts according to the user's emotional state. The input is data related to the user's emotions, and the output is the adjusted user interface.

[0600] (Application Example 2)

[0601] Next, we will explain application example 2. In the following explanation, 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."

[0602] In today's economic environment, individuals and businesses need to accurately understand financial indicators and make future financial forecasts, but this is an extremely complex task. Furthermore, there is a problem where information is not fully utilized because it does not take into account user sentiment. Information overload and complexity make it difficult for users to make accurate decisions.

[0603] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0604] In this invention, the server includes means for receiving electronic documents containing financial data and automatically extracting economic information from said electronic documents; means for storing the extracted economic information in an information management system; means for comparing the stored economic information with economic information from other industries and detecting anomalies; means for automatically generating information displays based on the detected anomalies; means for driving a learning algorithm using past financial data and predicting future economic indicators; and means for analyzing the user's emotions using emotion analysis technology and adjusting the content and display method of the report. This makes it possible to provide financial information in a way that is easy for the user to understand and to present the information with an emotion-sensitive interface.

[0605] "Financial data" refers to information, including economic indicators and records, that companies and individuals use to manage their economic activities.

[0606] An "electronic document" is a document recorded in a format that can be read by an information processing device such as a computer.

[0607] "Economic information" refers to specific figures, categories, and indicators extracted from financial data, and is information used for analysis and comparison.

[0608] An "information management system" is a system for storing and managing various types of collected data, and for retrieving and utilizing it as needed.

[0609] An "outlier" refers to a value that falls outside the normal range and is considered a statistically unique data point.

[0610] "Information display" is a means of visually representing analysis results and data and communicating them to users.

[0611] A "learning algorithm" is a method for computers to automatically learn patterns and insights from data.

[0612] An "economic indicator" is a numerical value used as a standard to measure the state of the economy.

[0613] "Emotional analysis technology" is a technology that estimates and analyzes a user's emotional state from text, voice, and other sources.

[0614] An "interface" refers to the points of contact or means of exchanging information between a user and a system.

[0615] To implement this invention, the server first receives an electronic document containing financial data from a user. The server then uses natural language processing techniques to automatically extract the necessary economic information. Libraries such as Python and TensorFlow can be utilized for this process. The extracted economic information is stored in an information management system and used for detecting outliers and comparing it with economic information from other industries.

[0616] The server automatically detects anomalies based on this data and automatically generates information displays from the data analysis results. In this process, the user's emotional state is detected by sentiment analysis technology and influences the report display. For example, if a user feels anxious due to economic fluctuations, the interface visually displays information that promotes the user's sense of security. Machine learning libraries such as SciKit-Learn and Keras are often used for this process.

[0617] Furthermore, the device dynamically adjusts the interface design, colors, font sizes, and other elements based on the user's emotions. This adjustment is performed using JavaScript and CSS techniques to provide the most comfortable user experience.

[0618] For example, if a user purchases a new, large home appliance and wants to know how it will affect their budget, this invention predicts in real time how the purchase will change the user's financial situation and provides reassuring information. An example of a prompt using the generative AI model would be: "If a user is feeling anxious about purchasing a large item, create a report on its economic impact and provide reassurance."

[0619] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0620] Step 1:

[0621] The server receives electronic documents containing financial data submitted by users. This input includes data in CSV or Excel format. The server uses natural language processing technology to automatically extract economic information from these documents. This process tokenizes the documents and identifies necessary financial indicators using a pre-trained model. The extracted economic information is output as variable data.

[0622] Step 2:

[0623] The server stores the extracted economic information in an information management system. This information is stored using a database management system (DBMS). The database efficiently stores the economic information and generates indexes to allow for quick access in subsequent processing. This output is a dataset used in subsequent processing.

[0624] Step 3:

[0625] The server detects anomalies by comparing stored economic data with economic data from other industries. This involves using statistical analysis methods and rule-based algorithms to identify unusual patterns. The output includes data flagged as singularities.

[0626] Step 4:

[0627] The server automatically generates information displays based on detected anomalies. Using a generation AI model, it generates prompts indicating the causes of the anomalies and providing guidelines. This output is presented in the form of graphs and dashboards for visualization.

[0628] Step 5:

[0629] The terminal displays information received from the server according to the user's emotional state. In this step, emotion analysis technology analyzes the user's past behavior history and current interactions, dynamically changing the interface design, colors, and font size. The output is an interface adjusted to best suit the user's emotions.

[0630] Step 6:

[0631] Based on the displayed information, users review their own economic behavior. They refer to the provided improvement suggestions and information on ongoing budget adjustments to make decisions for the next steps. This output is a concrete action plan that will become part of the user's future financial plan.

[0632] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0633] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0634] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0635] [Fourth Embodiment]

[0636] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0637] As shown in Figure 7, the 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.

[0638] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0639] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0640] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0641] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0642] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0643] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0644] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0645] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0646] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0647] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0648] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0649] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. This system utilizes generative AI technology to automatically extract financial information from electronic financial statements and store it in a database. The system consists of the following elements:

[0650] First, the user uploads the company's financial statements to the system from their terminal. The system receives the uploaded electronic document, and the server analyzes the document using natural language processing technology. This automatically extracts key financial indicators and records them in a structured data format in the database. This eliminates the need for manual data entry and significantly reduces the risk of input errors.

[0651] Next, the server uses the stored database to detect anomalies and perform comparative analysis with competitors. When anomalies are detected, the system automatically generates an alert. The insights gained at this stage allow companies to quickly develop strategies to gain a competitive advantage.

[0652] Furthermore, based on the generated data and analysis results, the server automatically creates reports. Natural language generation technology is used to explain financial indicators in simple language that is easy for non-experts to understand. These reports are presented on the terminal via a dashboard, allowing users to easily access and download them as needed.

[0653] Ultimately, a machine learning algorithm based on historical data allows the server to predict future financial conditions. This predictive model visualizes future sales growth and profitability, aiding in strategic decision-making. For example, if predicted sales growth exceeds the industry average, users can re-evaluate their growth strategy and review necessary investments.

[0654] These features make the present invention widely applicable as a system that significantly streamlines a company's financial management process and enables rapid management decisions.

[0655] The following describes the processing flow.

[0656] Step 1:

[0657] Users upload electronic financial statements from their devices to the system. This provides the system with PDF or Excel as the file format to be used.

[0658] Step 2:

[0659] The server receives the uploaded electronic document and selects the appropriate file parser. Next, it uses natural language processing technology to automatically extract financial information such as sales, profits, and assets from the financial statement and converts it into structured data.

[0660] Step 3:

[0661] The server stores the extracted financial data in a database. The stored data is used for subsequent analysis, anomaly detection, industry comparisons, and report generation.

[0662] Step 4:

[0663] The server uses stored data to apply an anomaly detection algorithm and evaluate how detected anomalies are impacting performance. If an anomaly is detected, the system automatically generates an alert and prepares to notify relevant parties.

[0664] Step 5:

[0665] The server drives the report generation engine based on the data it collects and analyzes. Utilizing natural language generation technology, the reports are written in simple language, minimizing technical jargon.

[0666] Step 6:

[0667] The generated reports are displayed on a dashboard on the device, allowing users to view, download, and print them. The information is also provided in a visually easy-to-understand format using graphs and charts.

[0668] Step 7:

[0669] The server trains a machine learning model based on historical data to predict future financial indicators. The prediction results are visualized on the terminal, clearly showing future growth potential and profitability.

[0670] Step 8:

[0671] The system makes strategic decisions based on the predictive data provided by the user and develops new action plans. Continuous improvement is achieved by feeding back the changed strategic information into the system as needed.

[0672] (Example 1)

[0673] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] Companies are required to efficiently manage vast amounts of financial data and make quick and accurate business decisions. However, conventional methods require a great deal of time and effort for manual data entry and analysis, and are prone to input errors and delays in information. Furthermore, there is a lack of practical means for quickly and accurately comparing financial performance with competitors and making future financial forecasts. This invention aims to solve these problems.

[0675] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0676] In this invention, the server includes means for receiving information provided in the form of an electronic document and automatically extracting financial indicators from said information; means for storing the extracted financial indicators in a data storage device; and means for comparing the stored financial indicators with the financial indicators of other entities and identifying outliers. This enables companies to efficiently analyze and store financial data, achieve rapid and accurate detection of outliers and future financial forecasts, and improve the quality of management decisions.

[0677] An "electronic document" is a document expressed in a digital format that can be read on a computer or digital device.

[0678] "Financial indicators" are statistical data used to quantify a company's financial condition and performance, and include sales revenue and profit margins.

[0679] A "data storage device" is a device or system for recording and retaining information for later use.

[0680] An "outlier" is a value that falls outside the normal range and exhibits specific or unexpected behavior within a dataset.

[0681] A "generative AI model" is a mathematical model that uses machine learning or artificial intelligence technology to generate new insights and predictions from data.

[0682] "Natural language generation technology" is a technology that enables computers to express analysis results and information in natural language that is easy for humans to understand.

[0683] "Natural language processing technology" refers to the techniques and methods used to enable computers to understand, interpret, and generate human language.

[0684] "Machine learning techniques" refer to a set of algorithms and methods for finding patterns in data and using them to learn and make predictions.

[0685] This invention is implemented as a system for efficiently managing and analyzing corporate financial data. Its embodiments are described in detail below.

[0686] First, users upload their company's financial statements to the system as electronic documents using a device. Typically, a PC or tablet is used as the device, connecting to the server via the internet. This upload process is carried out through an upload form provided in a web browser.

[0687] The server operates natural language processing (NLP) technology in an independent computing environment to analyze received electronic documents. Open-source libraries such as spaCy and NLTK are utilized for this purpose, automatically extracting financial indicators from documents. Furthermore, libraries such as pdf-lib and SheetJS are used to convert the contents of electronic documents into text data.

[0688] The extracted information is converted into a structured data format and stored in a data storage device, such as a relational database like MySQL or PostgreSQL. This makes it easier to search and analyze the data.

[0689] Using the stored data, the server drives generative AI models and performs analytical processing to perform financial comparisons with competitors and detect anomalies. This analysis utilizes libraries such as Scikit-learn, TensorFlow, or PyTorch, enabling machine learning models to provide insights.

[0690] As a concrete example, a prompt message such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," can be generated and passed to the generation AI.

[0691] Finally, a report is created based on the generated analysis results and predictions, and natural language generation technology is applied to make this report understandable even to non-experts. This report is displayed on the device via a web dashboard, and users can view it in real time and download it as needed.

[0692] This invention is a powerful means for companies to manage their financial information more quickly and effectively and to enhance their business intelligence.

[0693] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0694] Step 1:

[0695] Users upload their company's financial statements to the system using a terminal. Input is expected to be electronic documents in PDF or Excel format, which are sent to the server via a web browser. Output is an electronic document file temporarily stored on the server. This process begins with the user dragging and dropping the file into the upload form.

[0696] Step 2:

[0697] The server prepares to analyze the contents of the received electronic document. Specifically, it uses libraries such as pdf-lib for PDF analysis and SheetJS for Excel analysis. The uploaded electronic document is provided as input. The server converts its contents into text data and performs preprocessing for extracting financial indicators. The output is parseable text data. This step also verifies that the file is properly formatted.

[0698] Step 3:

[0699] The server extracts financial indicators from text data converted using natural language processing technology. Here, spaCy and NLTK are used to identify specific information such as amounts, dates, and department names within the document. The input is pre-processed text data, and the output is the extracted financial indicators. At this stage, processes such as tokenization and part-of-speech tagging are performed to ensure that the necessary information can be reliably extracted.

[0700] Step 4:

[0701] The server stores the extracted financial indicators in a structured data format in a data storage device. Specifically, it performs data insertion operations on SQL databases such as MySQL and PostgreSQL. A dataset of the extracted financial indicators is prepared as input. The structured data recorded in the database is obtained as output. This storage process also includes verification to prevent data duplication and inconsistencies.

[0702] Step 5:

[0703] The server uses stored financial indicators to perform comparisons with competitors and detect outliers. Here, machine learning models are operated using libraries such as Scikit-learn and TensorFlow. Financial indicators stored in the database are used as input, and the output generates a list of outliers and comparative analysis results with competitors. Regression analysis and clustering techniques are often applied to this analysis.

[0704] Step 6:

[0705] The server generates prompts using a generative AI model and creates a report based on the analysis results. Natural language generation technology is used to organize the information in a way that is easy for non-experts to understand. The input is the analysis results obtained in step 5. The output is a detailed report document. This report may include graphs and tables, along with explanatory text.

[0706] Step 7:

[0707] The terminal displays reports on a dashboard accessible to the user. Reports are provided in HTML or PDF format, and users can view and download them directly from their browser. Server-generated reports serve as input. A specific UI framework (e.g., React or Vue.js) is used to present information while maintaining a good user experience.

[0708] Step 8:

[0709] The server drives a machine learning algorithm using historical data to predict future financial conditions. Historical financial data is used as input. The output reports forecasts for future sales growth and profitability. This allows users to gain visual insights for strategic decision-making. Specifically, a prompt such as, "Based on sales data from the past five years, predict sales growth for the next fiscal year," is used.

[0710] (Application Example 1)

[0711] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0712] Managing and analyzing financial data within companies often involves manual processes, which are time-consuming, labor-intensive, and prone to input errors. Furthermore, comparing financial performance with competitors and detecting anomalies can be inconsistent. There is a need for rapid and highly accurate financial data management and forecasting, along with the creation of easily understandable reports.

[0713] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0714] In this invention, the server includes means for automatically extracting information including financial information, means for storing the extracted financial data in a storage area, and means for comparing the stored financial data with the financial data of competitors. This enables efficient management of financial data, immediate detection of abnormal events, highly accurate prediction of future financial indicators, and support for re-evaluating business strategies based on the results.

[0715] "Financial information" refers to data that shows a company's financial condition and economic activities, and includes profits, expenses, assets, liabilities, etc.

[0716] "Information" refers to data that represents facts, events, concepts, etc., and is used for a specific purpose.

[0717] "Extraction" refers to the operation of taking specific data or information out of a large dataset.

[0718] "Storage area" refers to a physical or virtual space used to record and hold digital data.

[0719] An "abnormal event" refers to a value or situation that exceeds the normal range, indicating an unexpected fluctuation or anomaly.

[0720] A "report" is a document that summarizes specific information or analytical results and is used to support judgment and decision-making.

[0721] An "analysis algorithm" refers to a series of procedures or calculation methods used to extract useful patterns and information from large amounts of data.

[0722] "Future financial indicators" are indicators that show projected or predicted future financial conditions of a company, and include sales and profits.

[0723] "Visualization" is the process of representing data and information visually, and it is a technique used to improve ease of understanding.

[0724] "Business strategy" refers to the means and methods that a company plans to use to achieve its goals, and it is the framework that supports its management policies.

[0725] "Sales data" refers to data relating to the revenue generated from the sale of products and services provided by a company.

[0726] "Notification" is the act of informing a person or system of specific information, and is used to attract attention.

[0727] This invention is a system for efficiently managing and analyzing financial information. The server receives electronic documents containing financial information sent by users and automatically extracts specific information. This reduces manual data entry and improves data accuracy.

[0728] The primary software used is the Python pandas library, which is used for loading and manipulating data. Additionally, the scikit-learn library is used to detect anomalies using machine learning algorithms. Matplotlib and seaborn are used for data visualization, generating clean and clear visuals.

[0729] The server compares stored financial data with that of competitors and immediately detects anomalies. Information about detected anomalies is reported to the user through notifications. Furthermore, analytical algorithms predict future financial indicators and support the re-evaluation of business strategies based on this data. The visualized results are presented as a report on the user's terminal and used as a basis for decision-making.

[0730] For example, if a company inputs its quarterly sales data into this system, the system can quickly detect anomalies in sales and use that information to make informed business decisions. It can also forecast sales considering specific seasons and campaign effects, providing opportunities to improve marketing strategies.

[0731] By utilizing a generative AI model, it is possible to automate a portion of the program that performs the aforementioned series of processes. As an example of a prompt statement to be used for this, the following text could be used as input data: "Analyze the latest sales data, detect anomalies, and create a report. Compare it with competitors and include suggestions for adjusting business strategies if necessary."

[0732] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0733] Step 1:

[0734] The user uploads an electronic document containing financial information from their terminal. The terminal sends this electronic document to the server, which prepares to store the received document in a database for analysis. This input includes sales information, expense information, etc., and the server prepares this as data for analysis.

[0735] Step 2:

[0736] The server automatically analyzes the stored electronic documents. Specifically, it uses a generative AI model to select the necessary financial information and extracts it as structured data using the pandas library. This process yields a dataset of financial indicators as output.

[0737] Step 3:

[0738] The server stores the extracted financial data in a storage area according to the schema. This storage area is the database used for subsequent analytical processing. The input data is converted to an appropriate format and stored securely.

[0739] Step 4:

[0740] Based on the stored data, the server uses the scikit-learn library to detect anomalies. Specifically, it runs anomaly detection algorithms such as Isolation Forest to identify outliers in the financial data. The output of this step is the location and value of the data points identified as anomalies.

[0741] Step 5:

[0742] The server compares outliers with financial data from competitors as a baseline. When an anomaly is detected, it generates and sends alerts and notifications to the user. This process allows the user to immediately recognize significant performance fluctuations.

[0743] Step 6:

[0744] The user receives a report generated by the server. The server uses matplotlib and seaborn to visualize the data and formats it into a report using natural language generation technology. This allows the user to receive materials for future sales forecasts and strategic planning.

[0745] Step 7:

[0746] The server runs machine learning models based on historical financial data to visualize future financial indicators. This includes sales forecasts and expense trend graphs, presented to users in a visually easy-to-understand format. The analysis results are output as data to be incorporated into business strategies.

[0747] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0748] This invention efficiently analyzes a company's financial data and is implemented as an interactive system that takes user emotions into consideration. This system includes an emotion engine for managing, analyzing, and optimizing the user interface of financial information.

[0749] First, the user uploads electronic documents containing the company's financial data from their device. This data is received by a server, and the necessary financial information is automatically extracted using natural language processing technology. The extracted data is stored in a database and used for future anomaly detection and industry comparisons.

[0750] Next, the server uses the stored financial information to compare with competitors, and automatically generates an alert if anomalies are detected. Furthermore, it analyzes the user's emotions through an emotion engine and selects the most considerate report content and presentation style to provide a report that is as easy to understand as possible for the user.

[0751] When a report is generated, natural language generation technology is used to create a simple and easy-to-understand text, and then the report is refined based on sentiment analysis results. On the device, the dashboard design, colors, and font size are dynamically changed according to the user's emotional state to provide an optimal user experience.

[0752] Furthermore, based on past data, the server uses machine learning algorithms to predict future financial conditions. This predictive information is also refined by an emotion engine and displayed on the device in a visually easy-to-understand format.

[0753] For example, if the emotion engine determines that a user has negative feelings about a particular financial indicator, the system will highlight that indicator and automatically suggest detailed explanations and improvement measures. In this way, the present invention significantly advances conventional financial management systems by supporting rapid and accurate decision-making for companies and providing a flexible interface adapted to individual users.

[0754] The following describes the processing flow.

[0755] Step 1:

[0756] Users upload electronic documents containing company financial data from their devices. The system supports file formats such as PDF and Excel.

[0757] Step 2:

[0758] The server receives uploaded electronic documents, selects the appropriate file parser, and analyzes the documents. Using natural language processing technology, it automatically extracts necessary financial information such as sales and profits.

[0759] Step 3:

[0760] The server extracts financial data, structures it, and stores it in a database. This creates a data base that can be used for subsequent analysis and anomaly detection.

[0761] Step 4:

[0762] The server uses stored data to compare it with data from competitors and runs an algorithm to detect anomalies. Analysis is performed on the detected anomalies, and alerts are generated as needed.

[0763] Step 5:

[0764] The server uses an emotion engine to analyze the user's emotional state based on their past feedback and behavioral patterns. This emotional data is considered when generating reports.

[0765] Step 6:

[0766] The server generates a report based on financial data and anomaly analysis results. It uses natural language generation technology to create plain text and adjusts the expression based on sentiment engine analysis results.

[0767] Step 7:

[0768] The generated report is displayed on the device and can be viewed on the dashboard. The system dynamically changes the interface colors and layout according to the user's emotional state to provide an optimal display.

[0769] Step 8:

[0770] The server uses historical data to train machine learning models and predict future financial indicators. These predictions are then refined based on the analysis results of the emotion engine and presented to the device in a visually easy-to-understand format.

[0771] Step 9:

[0772] Users review detailed forecast data and reports, and restructure their corporate strategy as needed. The emotion engine continuously receives user feedback and incorporates it into future interface and content creation.

[0773] (Example 2)

[0774] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0775] In analyzing corporate financial data, a major challenge is the significant time and effort required for data extraction, anomaly detection, and future forecasting. Furthermore, the lack of information provision that considers user sentiment leads to a lack of understanding and acceptance of the information users receive.

[0776] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0777] In this invention, the server includes means for receiving and automatically extracting information including financial data, means for storing the extracted financial information in a storage device, means for analyzing the stored financial information to detect anomalies and further predict future indicators, and means for analyzing user sentiment information and optimizing the method of presenting information. This enables efficient analysis of financial data and the provision of information optimized for the user.

[0778] "Financial data" refers to numerical information related to the economic activities of a company or organization, and generally includes information such as sales, profits, costs, assets, and liabilities.

[0779] "Information" refers to knowledge or news about facts, events, or data, expressed in this context in an electronically stored or processed form.

[0780] "Storage device" refers to computer hardware capable of storing and retrieving information, and generally includes hard disks, SSDs, databases, and so on.

[0781] An "outlier" refers to a value that deviates significantly from the standard or expected value, and in data analysis, it is used to identify values ​​that exceed the normal range.

[0782] "Data analysis technology" refers to methods and techniques for extracting meaning and value from large amounts of information, and includes statistical analysis, machine learning, and artificial intelligence.

[0783] "User sentiment information" refers to the emotional reactions and states of information users, and is usually evaluated through natural language processing and sentiment analysis technologies.

[0784] "Natural language processing technology" refers to technology that enables computers to understand human language and interact with humans.

[0785] This invention provides an interactive system that efficiently analyzes a company's financial data and takes user emotions into consideration. The system includes a series of means for managing, analyzing, and optimizing the user interface of financial information.

[0786] The process begins with the user using a terminal to upload electronic documents containing company financial data. The terminal supports common data formats such as PDF and Excel files, which are sent to the server. The server processes and extracts the uploaded information using data analysis techniques. Here, the Python pandas library is used to analyze the data structure, and natural language processing software is used for natural language processing.

[0787] The server stores the extracted financial information in a storage device (database software). This information is later compared with information from other organizations and used for statistical analysis and anomaly detection. Anomaly detection is performed based on a statistical model utilizing the SciPy library, and if an anomaly is detected, the user is immediately notified.

[0788] Furthermore, the server uses sentiment analysis software to analyze the user's emotional information and adjust the tone and presentation of the information it provides. In this process, for example, a computer can analyze the user's responses and generate the most considerate information in an appropriate tone.

[0789] Furthermore, the user interface on the device dynamically changes according to the user's emotional state. This provides an optimal user experience, allowing users to understand important information without stress.

[0790] For example, when a user is interested in a particular financial metric, the system will focus on displaying information related to that metric and explain it in an easy-to-understand way. For instance, by entering a prompt such as, "What is the sales growth rate this year?", the system will generate and visually present detailed information about sales.

[0791] With this configuration, companies can efficiently obtain data to make quick and accurate decisions, and information tailored to the user can be provided.

[0792] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0793] Step 1:

[0794] Users upload electronic documents, including company financial data, via their terminals. Inputs include PDF and Excel files. The terminals send these files to the server. The server receives the uploaded data as output.

[0795] Step 2:

[0796] The server processes received electronic documents using advanced data analysis techniques. Specifically, it uses the Python pandas library to extract financial information in the required format. This process yields structured data that can be stored in a database. The input is electronic documents, and the output is structured financial information.

[0797] Step 3:

[0798] The server stores the extracted financial information in storage. The data stored in the database forms the basis for subsequent analysis and anomaly detection. The input here is the extracted structured data, and the output is that data stored in the database.

[0799] Step 4:

[0800] The server performs statistical analysis based on stored financial information and compares it with information from other organizations. During this process, it uses the SciPy library to detect outliers. When an outlier is detected, an automated process is initiated to notify the user. The input is stored financial information, and the output is notification information regarding the outlier.

[0801] Step 5:

[0802] The server drives a generative AI model and, as needed, uses natural language generation technology to generate records in plain language. Specifically, it automatically creates reports based on financial information. The input is analysis results, including outliers, and the output is a written report.

[0803] Step 6:

[0804] The server uses emotion analysis software to analyze the user's emotional information. Based on the analysis results, it adjusts the tone and visual presentation of the information provided. Specifically, the user interface on the terminal dynamically adapts according to the user's emotional state. The input is data related to the user's emotions, and the output is the adjusted user interface.

[0805] (Application Example 2)

[0806] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0807] In today's economic environment, individuals and businesses need to accurately understand financial indicators and make future financial forecasts, but this is an extremely complex task. Furthermore, there is a problem where information is not fully utilized because it does not take into account user sentiment. Information overload and complexity make it difficult for users to make accurate decisions.

[0808] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0809] In this invention, the server includes means for receiving electronic documents containing financial data and automatically extracting economic information from said electronic documents; means for storing the extracted economic information in an information management system; means for comparing the stored economic information with economic information from other industries and detecting anomalies; means for automatically generating information displays based on the detected anomalies; means for driving a learning algorithm using past financial data and predicting future economic indicators; and means for analyzing the user's emotions using emotion analysis technology and adjusting the content and display method of the report. This makes it possible to provide financial information in a way that is easy for the user to understand and to present the information with an emotion-sensitive interface.

[0810] "Financial data" refers to information, including economic indicators and records, that companies and individuals use to manage their economic activities.

[0811] An "electronic document" is a document recorded in a format that can be read by an information processing device such as a computer.

[0812] "Economic information" refers to specific figures, categories, and indicators extracted from financial data, and is information used for analysis and comparison.

[0813] An "information management system" is a system for storing and managing various types of collected data, and for retrieving and utilizing it as needed.

[0814] An "outlier" refers to a value that falls outside the normal range and is considered a statistically unique data point.

[0815] "Information display" is a means of visually representing analysis results and data and communicating them to users.

[0816] A "learning algorithm" is a method for computers to automatically learn patterns and insights from data.

[0817] An "economic indicator" is a numerical value used as a standard to measure the state of the economy.

[0818] "Emotional analysis technology" is a technology that estimates and analyzes a user's emotional state from text, voice, and other sources.

[0819] An "interface" refers to the points of contact or means of exchanging information between a user and a system.

[0820] To implement this invention, the server first receives an electronic document containing financial data from a user. The server then uses natural language processing techniques to automatically extract the necessary economic information. Libraries such as Python and TensorFlow can be utilized for this process. The extracted economic information is stored in an information management system and used for detecting outliers and comparing it with economic information from other industries.

[0821] The server automatically detects anomalies based on this data and automatically generates information displays from the data analysis results. In this process, the user's emotional state is detected by sentiment analysis technology and influences the report display. For example, if a user feels anxious due to economic fluctuations, the interface visually displays information that promotes the user's sense of security. Machine learning libraries such as SciKit-Learn and Keras are often used for this process.

[0822] Furthermore, the device dynamically adjusts the interface design, colors, font sizes, and other elements based on the user's emotions. This adjustment is performed using JavaScript and CSS techniques to provide the most comfortable user experience.

[0823] For example, if a user purchases a new, large home appliance and wants to know how it will affect their budget, this invention predicts in real time how the purchase will change the user's financial situation and provides reassuring information. An example of a prompt using the generative AI model would be: "If a user is feeling anxious about purchasing a large item, create a report on its economic impact and provide reassurance."

[0824] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0825] Step 1:

[0826] The server receives electronic documents containing financial data submitted by users. This input includes data in CSV or Excel format. The server uses natural language processing technology to automatically extract economic information from these documents. This process tokenizes the documents and identifies necessary financial indicators using a pre-trained model. The extracted economic information is output as variable data.

[0827] Step 2:

[0828] The server stores the extracted economic information in an information management system. This information is stored using a database management system (DBMS). The database efficiently stores the economic information and generates indexes to allow for quick access in subsequent processing. This output is a dataset used in subsequent processing.

[0829] Step 3:

[0830] The server detects anomalies by comparing stored economic data with economic data from other industries. This involves using statistical analysis methods and rule-based algorithms to identify unusual patterns. The output includes data flagged as singularities.

[0831] Step 4:

[0832] The server automatically generates information displays based on detected anomalies. Using a generation AI model, it generates prompts indicating the causes of the anomalies and providing guidelines. This output is presented in the form of graphs and dashboards for visualization.

[0833] Step 5:

[0834] The terminal displays information received from the server according to the user's emotional state. In this step, emotion analysis technology analyzes the user's past behavior history and current interactions, dynamically changing the interface design, colors, and font size. The output is an interface adjusted to best suit the user's emotions.

[0835] Step 6:

[0836] Based on the displayed information, users review their own economic behavior. They refer to the provided improvement suggestions and information on ongoing budget adjustments to make decisions for the next steps. This output is a concrete action plan that will become part of the user's future financial plan.

[0837] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0838] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0839] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0840] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0841] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0842] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0843] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0844] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0845] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0846] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0847] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0848] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0849] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0850] 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.

[0851] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0852] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0853] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0854] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0855] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0856] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0857] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0858] The following is further disclosed regarding the embodiments described above.

[0859] (Claim 1)

[0860] A means for receiving electronic documents containing financial data and automatically extracting financial information from said electronic documents,

[0861] A means for storing the extracted financial information in a database,

[0862] A means for comparing the stored financial information with the financial information of other companies in the same industry and detecting anomalies,

[0863] A means for automatically generating a report based on the detected anomaly,

[0864] A method for driving machine learning algorithms using historical financial data to predict future financial indicators,

[0865] A system that includes this.

[0866] (Claim 2)

[0867] The system according to claim 1, further comprising means for writing the generated report in plain language using natural language generation technology.

[0868] (Claim 3)

[0869] The system according to claim 1, further comprising means for extracting the aforementioned financial information and detecting anomalies using advanced natural language processing technology.

[0870] "Example 1"

[0871] (Claim 1)

[0872] A means for receiving information provided in the form of an electronic document and automatically extracting financial indicators from said information,

[0873] Means for storing the extracted financial indicators in a data storage device,

[0874] A means of comparing stored financial indicators with the financial indicators of other entities to identify outliers,

[0875] A means for automatically generating a report based on the identified anomaly,

[0876] A means of predicting future financial attributes by using machine learning techniques based on historically recorded financial data,

[0877] A means of assisting decision-making by providing input using a generative AI model,

[0878] A system that includes this.

[0879] (Claim 2)

[0880] The system according to claim 1, comprising a means for using natural language generation technology to describe the generated report in an easily understandable form.

[0881] (Claim 3)

[0882] The system according to claim 1, comprising means for extracting financial indicators and identifying outliers using advanced natural language processing technology.

[0883] "Application Example 1"

[0884] (Claim 1)

[0885] A means for receiving information including financial information and automatically extracting financial data from said information,

[0886] Means for storing the extracted financial data in a storage area,

[0887] A means for detecting abnormal events by comparing the stored financial data with the financial data of other companies in the same industry,

[0888] A means for automatically generating a report based on the detected abnormal event,

[0889] A means of driving analytical algorithms using historical financial data to predict future financial indicators,

[0890] A means to visualize the projected future financial indicators and support the re-evaluation of business strategies,

[0891] A means for visualizing sales data and notifying of abnormal events,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, further comprising means for describing the generated report in plain language using natural language generation technology.

[0895] (Claim 3)

[0896] The system according to claim 1, further comprising means for extracting the aforementioned financial data and detecting abnormal events using advanced natural language processing technology.

[0897] "Example 2 of combining an emotion engine"

[0898] (Claim 1)

[0899] A means for receiving information including financial data and automatically extracting financial information from said information,

[0900] Means for storing the extracted financial information in a storage device,

[0901] A means for comparing the stored financial information with information from other organizations and detecting anomalies,

[0902] A means for automatically generating a record based on the detected abnormal value,

[0903] A means of driving data analysis techniques using past financial information to predict future indicators,

[0904] A processing means for analyzing user emotional information and optimizing the method of presenting that information,

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, further comprising means for describing the generated record in plain language using an automatic generation technology.

[0908] (Claim 3)

[0909] The system according to claim 1, further comprising means for extracting the aforementioned financial information and detecting anomalies using natural language processing technology.

[0910] "Application example 2 when combining with an emotional engine"

[0911] (Claim 1)

[0912] A means for receiving electronic documents containing financial data and automatically extracting economic information from said electronic documents,

[0913] A means for storing the extracted economic information in an information management system,

[0914] A means for comparing the stored economic information with economic information from other industries and detecting outliers,

[0915] A means for automatically generating information displays based on the detected anomaly,

[0916] A means of driving a learning algorithm using historical financial data to predict future economic indicators,

[0917] A means for analyzing user emotions using emotion analysis technology and adjusting the content and display method of the report,

[0918] A system that includes this.

[0919] (Claim 2)

[0920] The system according to claim 1, comprising means for describing the generated information display in plain language using natural language generation technology and for adaptively changing the interface based on the user's emotional state.

[0921] (Claim 3)

[0922] The system according to claim 1, further comprising means for extracting economic information, detecting anomalies, and analyzing user sentiment using advanced natural language processing and sentiment analysis techniques. [Explanation of Symbols]

[0923] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving information including financial information and automatically extracting financial data from said information, Means for storing the extracted financial data in a storage area, A means for detecting abnormal events by comparing the stored financial data with the financial data of other companies in the same industry, A means for automatically generating a report based on the detected abnormal event, A means of driving analytical algorithms using historical financial data to predict future financial indicators, A means to visualize the projected future financial indicators and support the re-evaluation of business strategies, A means for visualizing sales data and notifying of abnormal events, A system that includes this.

2. The system according to claim 1, further comprising means for describing the generated report in plain language using natural language generation technology.

3. The system according to claim 1, further comprising means for extracting the aforementioned financial data and detecting abnormal events using advanced natural language processing technology.

Images