system

Abstract

We provide the system. [Solution] A means for obtaining economic information from users and integrating and processing that information as needed, A means for performing trend prediction and analysis based on input information using machine learning technology, Means for visualizing and warning about analysis results through an information display device, A means of updating machine learning models using generated opinions to improve prediction accuracy, A method for extracting useful information from non-economic data using natural language processing technology and proposing savings plans based on spending trends, A method to analyze price trends of specific products and notify users of the optimal purchase timing. A system that includes this.

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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] In modern times, while enterprises and individuals have a large amount of financial data and related non-financial data, they have not fully utilized it. As a result, reasonable decision-making and detailed strategic planning based on data cannot be fully carried out, which may lead to economic losses and opportunity losses. In addition, in a situation where specialized knowledge is lacking, it is difficult to internalize advanced financial analysis. When relying on external consultants, it lacks flexibility in the modern business environment where quick responses are required. Therefore, there is a need for a system that can efficiently and quickly analyze financial data, make predictions, and propose strategies.

Means for Solving the Problems

[0005] This invention provides means for acquiring financial information from users and integrating and processing the information as needed, means for performing predictions and analyses based on the input information using machine learning technology, and means for visualizing and notifying the analysis results through a user interface. Furthermore, it proposes a system that includes means for updating the machine learning model using generated feedback to improve prediction accuracy. In addition, by extracting useful information from non-financial data using natural language processing technology, it is possible to update and analyze financial information in real time and provide suggestions based on the results as they arise. This system enables advanced analysis and rapid support for data-driven decision-making, even without specialized knowledge.

[0006] A "user" refers to a company or individual that utilizes the system, providing financial information and receiving analysis results and suggestions.

[0007] "Financial information" refers to numerical and documentary data related to the economic activities of companies and individuals, including details such as revenue, costs, assets, and liabilities.

[0008] "Non-financial data" refers to external data that is not directly included in financial information but influences financial analysis, such as economic indicators, market trends, and news articles.

[0009] "Machine learning technology" is a collection of algorithms and methods that enable computers to learn patterns from data and make future predictions and decisions.

[0010] "Prediction" is an information processing process that estimates future states or outcomes based on collected data.

[0011] "Analysis" is a method of thoroughly examining data and extracting meaningful information from it, and it forms the basis for supporting user decision-making.

[0012] A "user interface" refers to the screens and operating environments that allow a user to interact with a system, enabling the input of information and the display of results.

[0013] "Feedback" refers to information and evaluations provided by users, which the system uses to improve its performance.

[0014] "Natural language processing technology" is a technology that enables computers to understand and process human language, and is used to extract useful knowledge from text information. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 2 when the 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 the emotion engine is combined.

Mode 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, a 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, a 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 signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[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] The system of the present invention aims to efficiently integrate financial and non-financial data provided by users and to perform advanced analysis and predictions based on that data. This system is primarily implemented with the involvement of three entities: a server, a terminal, and a user.

[0037] First, users upload financial information to the server via their devices. This information includes revenue and expense history, and details of assets and liabilities. In addition, the server collects non-financial data from the internet. This non-financial data includes economic indicators, industry trends, and news reports.

[0038] Next, the server integrates these different datasets. Data cleaning and preprocessing are performed, removing unnecessary data, imputing missing values, and standardizing data formats. This process ensures consistency across each dataset, laying the foundation for analysis.

[0039] The server then analyzes the data using machine learning techniques. The server has the ability to run models such as sales forecasts and investment risk assessments, thereby improving the accuracy of predictions. For example, it can use regression analysis to forecast next year's sales or classification algorithms to assess investment risk.

[0040] The analysis results are sent from the server to the terminal and displayed in a format accessible to the user. The terminal visualizes the information in a dashboard format, providing an intuitive user experience. This allows users to easily understand complex datasets and use them to inform their decision-making.

[0041] Furthermore, the server also utilizes natural language processing technology to extract useful information from non-financial data. The server extracts keywords from news articles and reports and uses them to provide users with new insights.

[0042] Finally, the server continuously optimizes its machine learning model based on user feedback. This will enable more accurate predictions in the future, allowing it to respond to user requests more quickly and precisely.

[0043] In this way, the system of the present invention functions as a powerful tool for users to perform advanced and comprehensive financial analysis and make rational decisions based on it.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] Users upload financial information to the server using their devices. The data is typically in CSV or Excel file format, making data entry easy.

[0047] Step 2:

[0048] The server automatically collects non-financial data such as economic indicators and news articles via the internet. This data is obtained using APIs or web scraping.

[0049] Step 3:

[0050] The server integrates uploaded financial information with collected non-financial data. Data cleaning is performed to remove duplicate data and fill in missing data.

[0051] Step 4:

[0052] The server uses machine learning models to analyze data. For example, it uses regression analysis to predict sales trends and classification algorithms to evaluate investment risk.

[0053] Step 5:

[0054] The server uses natural language processing technology to extract useful information from non-financial data. It extracts keywords from news articles and identifies important market trends.

[0055] Step 6:

[0056] The server generates analysis results and sends them to the terminal. The results are visualized in a dashboard format and presented to the user as graphs and tables.

[0057] Step 7:

[0058] Users refer to the dashboard on their device to evaluate the analysis results and make decisions. The dashboard has an intuitive interface and is designed to allow users to quickly grasp the information they need.

[0059] Step 8:

[0060] Users take actions based on the analysis results and provide the system with feedback on the outcomes.

[0061] Step 9:

[0062] The server incorporates user feedback, adjusts the parameters of the machine learning model, and improves the accuracy of future predictions.

[0063] (Example 1)

[0064] 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."

[0065] In today's business environment, there is a demand for the rapid integration of data from multiple sources and for advanced analysis based on this data. However, efficiently integrating financial and non-financial data and performing consistent analysis is technically challenging. Furthermore, optimizing models to reflect user feedback is not easy, and there is a need to improve prediction accuracy. To solve these challenges, it is necessary to automate information aggregation and analysis to improve prediction accuracy and usability.

[0066] 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.

[0067] In this invention, the server includes means for acquiring financial information from users via an information processing device and integrating and preprocessing the information; means for performing predictions and analyses based on the input information using computer learning methods; means for visually presenting and notifying the analysis results through a user interface; means for optimizing the computer learning model using feedback generated by the user to improve prediction accuracy; means for actively collecting information from external information sources and integrating the information into the analysis; and means for ensuring consistency between each dataset and converting the data into a unified format. This enables the integration and centralized management of diverse information, leading to improved accuracy in practical predictions and analyses, and the realization of highly adaptable models that utilize user feedback.

[0068] An "information processing device" is a device that receives data from a user and performs necessary data preprocessing.

[0069] "Financial information" is a general term for data that represents a company's financial situation, including revenue, expenses, assets, and liabilities.

[0070] "Computer learning techniques" are technologies in which computers learn patterns using large amounts of data and then use that information to make predictions and perform analyses.

[0071] A "user interface" is a general term for the display and operating devices that allow computers and humans to exchange information.

[0072] "Feedback" refers to evaluations and improvement suggestions provided by users, which are used to improve the system.

[0073] "External information sources" refer to information obtained from outside the company, such as economic indicators and news found on the internet.

[0074] "Consistency" means that there are no inconsistencies between different datasets, and that a consistent data state is maintained.

[0075] A "unified format" is a means of standardizing analytical processing by converting data provided in different formats into a consistent format.

[0076] The embodiment for carrying out this invention is a system composed of three entities: a user, a terminal, and a server. This system performs predictions and analyses based on financial information provided by the user, and provides the results to the user in a visualized format.

[0077] First, the user sends financial information to the server via their device. The device provides an interface for uploading information on revenue, expenses, assets, and liabilities in Excel or CSV file formats. The device features a user-friendly UI and seamlessly transfers the entered information to the server.

[0078] Next, the server integrates the received financial information with non-financial data collected from external sources. This process uses the Python Pandas library and includes cleaning operations such as imputing missing values, standardizing data formats, and deleting unnecessary data to ensure data integrity. The server also collects the latest economic indicators, market trends, and news reports via the internet using APIs and web scraping.

[0079] After the data is integrated, the server performs data analysis using computer learning techniques. Utilizing the Python Scikit-learn library, it performs regression analysis and classification algorithms to predict sales and assess investment risk. This entire process is designed to be intuitive for the user; for example, a prompt using the generative AI model can be entered as, "Please predict sales for a specific product category next year."

[0080] Finally, the analyzed results are sent from the server to the terminal. The terminal displays the results in graph and chart format using visualization libraries such as D3.js. This allows users to visually understand the analysis results and use them to make decisions. Furthermore, based on feedback provided by the user, the server continuously optimizes the machine learning model to improve prediction accuracy.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] Users transmit financial information to the server via their terminal. The input consists of revenue, expense, asset, and liability information contained in Excel or CSV files. The terminal receives this data and uploads it to the server. During this process, the terminal performs a format check to ensure the accuracy of the input.

[0084] Step 2:

[0085] The server receives uploaded financial information and collects non-financial data from external sources. It uses economic indicators and news reports obtained via APIs as input. The server uses the Python Pandas library to clean the data, removing duplicates and imputing missing values. This ensures data consistency and integrates it into a format suitable for analysis.

[0086] Step 3:

[0087] The server performs computational learning based on integrated data. It uses cleaned financial and non-financial data as input. The server utilizes the Scikit-learn library to perform regression analysis and predict sales. It also applies classification algorithms to assess investment risk. The output includes numerical data for prediction results and risk assessment.

[0088] Step 4:

[0089] The server sends the analysis results to the terminal. The generated prediction results and risk assessment data are used as input. The terminal uses the D3.js library to visualize these results. The terminal displays the data in graphs and charts for easy understanding by the user, supporting their decision-making.

[0090] Step 5:

[0091] Users provide feedback to the server based on the analysis results. The server uses user comments and specific improvement suggestions as input. Based on this feedback, the server optimizes the generated AI model. Prompts such as "Please further improve prediction accuracy" are used. This improves accuracy in subsequent data analyses and enhances overall system performance.

[0092] (Application Example 1)

[0093] 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."

[0094] In modern society, users are expected to acquire information on a daily basis and engage in wise consumer behavior. However, amidst a vast amount of economic information and fluctuating price trends, it is difficult for individual users to determine the optimal timing for purchases and savings plans. Traditional methods lacked real-time information acquisition and analysis, and were insufficient to support users' decision-making. Furthermore, determining the optimal purchase time for a particular product in light of price fluctuations is a challenging task.

[0095] 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.

[0096] In this invention, the server includes means for acquiring economic information from the user and integrating and processing the information as needed, means for performing trend prediction and analysis based on the input information using machine learning technology, and means for visualizing and warning the analysis results through an information display device. This enables the user to receive real-time information analysis and optimal savings plans. Furthermore, by evaluating price trends of specific products and notifying consumers of the appropriate timing for purchase, consumers can engage in more efficient and wiser consumer activities.

[0097] "Economic information" refers to data related to a user's consumption and spending, including consumption history, income, spending, and other financial information.

[0098] "Integration" is the process of unifying data obtained from multiple different sources and compiling it into a consistent format.

[0099] "Processing" refers to the process of shaping acquired data into a format suitable for analysis and prediction, removing unnecessary data, and imputing missing values.

[0100] "Machine learning technology" is a technique in which computers automatically identify patterns based on large amounts of data and use that information to support predictions and decision-making.

[0101] "Trend forecasting" is a method of predicting future economic activity and price trends based on past data.

[0102] "Analysis" is the process of conducting detailed evaluations and examinations based on data, and deriving insights from those evaluations.

[0103] An "information display device" is a hardware and software system that allows users to visually confirm the results of data analysis.

[0104] "Visualization" is the process of representing analysis results using visual aids such as graphs and charts, and providing them in a way that is easy for users to understand.

[0105] "Warning" refers to a notification function that clearly informs users of important situations or changes.

[0106] "Non-economic data" refers to information about factors other than economics, and may include social, environmental, and cultural factors.

[0107] "Spending trends" refer to patterns and developments related to users' spending habits, and enable future predictions based on these trends.

[0108] A "savings plan" is a method that provides users with specific guidelines and steps to reduce waste and make efficient use of resources.

[0109] "Price trends" refer to patterns or flows that show how the price of a particular product or service changes over time.

[0110] "Purchase timing" refers to the most opportune time for consumers to buy a particular product or service, and is determined based on price and market conditions.

[0111] To implement this invention, a server, a terminal, and a user must cooperate to form a system. The server plays a central role, aggregating economic and non-economic information. Users provide information about their income and expenses via the terminal. The server receives this information and preprocesses the data as needed.

[0112] Data preprocessing involves removing unnecessary data, imputing missing values, and ensuring consistent data formats. This prepares the aggregated data for machine learning. The server uses machine learning techniques, specifically Scikit-Learn, to predict future spending trends and price movements based on economic information. The analysis results are displayed to the user in a dashboard format on their terminal.

[0113] Furthermore, the server uses natural language processing techniques to analyze non-economic data, such as news articles. This provides new insights that may influence the user. Libraries such as TextBlob are used for text analysis. Through this process, the server suggests optimal purchase times and savings plans for specific products to the user.

[0114] For example, when a user is about to purchase a particular product, the server can predict relevant price fluctuations and provide specific advice such as, "There's a discount sale this month, so you can buy it at a good price." In this way, users can engage in economical and efficient consumer activities.

[0115] As an example of a prompt, you can input a request such as, "Please predict my spending for the next three months and suggest possible savings plans," and then use the generative AI model to obtain the analysis results.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] Users send financial information, including income and expenses, to the server via their devices. This allows the financial data to be aggregated on the server. The server stores the received information in a database and prepares it for further processing.

[0119] Step 2:

[0120] The server collects non-economic data via the internet. This data includes general trends and economic news. The collected data is processed using a natural language processing library to extract relevant keywords. The results are stored in a database, preparing it to provide information that users may find interesting.

[0121] Step 3:

[0122] The server preprocesses the aggregated economic information. This stage involves removing unnecessary data and imputing missing values. Specifically, it standardizes the data format and performs data cleansing. This process generates a clean dataset that can be used by machine learning models.

[0123] Step 4:

[0124] The server analyzes processed data using machine learning models. It leverages Scikit-Learn to predict future spending trends and price movements. Historical consumption data is used as input, and the output generates predictions of purchasing patterns and specific suggestions.

[0125] Step 5:

[0126] The server sends the analysis results to the terminal and provides them to the user in a visualized format. The terminal displays a dashboard on its display device, making it easy for the user to understand intuitively. Information is presented using specific graphs and notification messages.

[0127] Step 6:

[0128] Users review the information provided from their devices and use it as a reference for specific consumer behavior. They also send feedback from their devices to the server, which helps evaluate the analysis results and improve the model for future use.

[0129] 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.

[0130] This invention is a system that efficiently integrates financial and non-financial data and incorporates an emotion engine to analyze and recognize user emotions, thereby providing more personalized analysis results and suggestions. Embodiments of this system primarily consist of a server, terminals, and users.

[0131] First, users upload financial information to the server via their devices. This includes data such as revenue, expenses, and assets. In addition, the server retrieves non-financial data from the internet. This consists of external information such as economic indicators and news.

[0132] The server integrates the received financial and non-financial data and analyzes the data using machine learning techniques. For example, it runs models to perform sales forecasts and risk assessments, and provides strategic insights based on the results.

[0133] Furthermore, the server is equipped with an emotion engine that analyzes user input and responses through the user interface to recognize emotions. This enables the presentation of information tailored to the user's mental state. For example, in a stressful situation with high investment risk, it can output reassuring messages to encourage calm decision-making.

[0134] The device receives analysis results from the server and personalized content tailored to the user's emotional state, which is then intuitively visualized through a dashboard. This allows users to review analysis results that resonate with their own emotions and decide on their next course of action.

[0135] Furthermore, the server records a history of user emotions and continuously uses this information to optimize the user experience. By analyzing past emotional data, it is possible to understand how users felt and responded in different situations, and use this information to inform future suggestions.

[0136] Thus, the system of the present invention supports more effective decision-making and functions in a way that meets individual needs by analyzing the user's financial information and providing insights that correspond to the user's emotional state.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] Users upload financial information to the server using their devices. This information includes numerical data such as revenue, expenses, and assets, as well as related text files.

[0140] Step 2:

[0141] The server collects non-financial data via the internet. This includes economic indicators, industry news, and general market trends. Data collection is performed using APIs and scraping techniques.

[0142] Step 3:

[0143] The server integrates and cleans the collected financial and non-financial data. It standardizes data formats and imputes missing values ​​to prepare the data for analysis.

[0144] Step 4:

[0145] The server begins analyzing data using a machine learning model. It forecasts sales and assesses investment risks, generating analytical results based on these findings.

[0146] Step 5:

[0147] The server uses an emotion engine to analyze user input and reactions obtained from the user interface and recognize the user's emotional state.

[0148] Step 6:

[0149] Based on the results from the emotion engine, the server adjusts the displayed analysis and suggestions according to the user's emotional state. For example, if the user is feeling stressed, it prioritizes displaying information that provides a sense of reassurance.

[0150] Step 7:

[0151] The device displays the optimized analysis results and suggestions to the user via a user interface. The dashboard includes visually organized graphs and reports.

[0152] Step 8:

[0153] Users review the displayed dashboard and make decisions as needed. Based on the suggestions and information presented, users can decide on specific actions.

[0154] Step 9:

[0155] The system receives feedback on the actions taken by the user and their emotional responses to those actions.

[0156] Step 10:

[0157] Based on the feedback, the server readjusts the parameters of the machine learning model and emotion engine to optimize prediction accuracy and user experience.

[0158] (Example 2)

[0159] 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 as the "terminal".

[0160] In modern information technology, the analysis of numerical information and decision support play crucial roles in various fields. However, conventional systems are specialized in the analysis of numerical information, making it difficult to provide personalized information that takes into account the emotional state of the user. Furthermore, there is a lack of mechanisms to utilize past history in order to improve the accuracy of information and accurately predict the future needs of users. Thus, there is a demand for providing effective decision support to users and solutions that meet their individual needs.

[0161] 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.

[0162] In this invention, the server includes means for acquiring numerical information from the user and integrating and preprocessing the information as necessary, means for performing estimation and evaluation based on the input information using a machine learning algorithm, and means for visualizing and notifying the evaluation results through a display device. This enables data analysis that takes into account the user's emotional state and the provision of personalized information.

[0163] "User" refers to an individual who uses the system to provide numerical information and receives the results.

[0164] "Numerical information" refers to information that includes financial data such as revenue, expenses, and assets.

[0165] A "server" refers to a computer system that receives, processes, and analyzes data from users.

[0166] A "machine learning algorithm" refers to a computational method or model that uses data to make predictions and perform analyses.

[0167] "Estimation and evaluation" refers to predictions and their analysis results calculated using machine learning algorithms based on the input numerical information.

[0168] A "display device" refers to a device used to present information to a user in a visual or other format.

[0169] "Visualization" means presenting analysis results in a visual form, such as diagrams or graphs, to make them easier for users to understand.

[0170] "Emotional state" refers to the psychological and emotional state inferred from the user's input and responses.

[0171] "History" refers to records of information that users have provided in the past, as well as feedback received from the system at that time.

[0172] "Non-numerical data" refers to data that represents information other than numerical values, such as text and news articles, and is analyzed by a system.

[0173] This invention is a system that efficiently integrates numerical and non-numerical data of users and performs sentiment analysis to provide more personalized analysis results and suggestions. This system mainly consists of a server, terminals, and users.

[0174] The server plays a central role in processing numerical and non-numerical data. It receives financial data such as revenue, expenses, and assets transmitted from users via their devices. This data is retrieved via the HTTP protocol and securely stored in a database. The server also uses APIs to retrieve non-numerical data such as economic indicators and news from the internet.

[0175] For data integration and analysis, we use the Python Pandas library. Pandas allows for efficient merging of numerical and non-numerical data using dataframes. As for machine learning algorithms, we use Tensorflow® and PyTorch to run predictive models and make predictions and evaluations about users' financial situations.

[0176] The system utilizes natural language processing (NLP) technology for emotion analysis. Specifically, it analyzes user input data and uses an emotion engine to infer the user's emotional state. This allows for the provision of customized information tailored to the user's mental state.

[0177] The terminal is a device that visually displays the analysis results received from the server. Using the JavaScript (registered trademark) library D3.js, it generates intuitive graphs and charts on the dashboard, presenting information to the user in an easy-to-understand manner.

[0178] Furthermore, the server records the user's past activity history and emotional responses, and uses this information to optimize future suggestions. This enables personalized suggestions for each user.

[0179] As a concrete example, here is an example of a prompt message: "Based on the latest revenue data and economic news, forecast business growth and propose measures to address user concerns."

[0180] Thus, the present invention functions to support more effective decision-making by performing comprehensive information processing based on the user's numerical information and emotions.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] Users upload their financial data using their device. The input is, for example, a CSV file containing revenue, expense, and asset information. When a dedicated upload button on the device is clicked, the file is sent to the server, which receives this data via the HTTP protocol and stores it in the database.

[0184] Step 2:

[0185] The server uses APIs to collect the latest non-numerical data from the internet. The input data consists of economic indicators and news articles, which are retrieved in JSON format. The data is processed in real time and stored in the server's database. This step involves making requests to external APIs and storing the response data.

[0186] Step 3:

[0187] The server integrates financial and non-numerical data using the Pandas library. The input data consists of the information collected in steps 1 and 2. This integration process merges dataframes with common key items to create a consistent dataset. The output is the integrated dataset.

[0188] Step 4:

[0189] The server executes machine learning algorithms on the integrated dataset. The input is the integrated dataset, and the model used is a pre-trained model using TensorFlow. This model is used to predict sales and assess risks, and the output is these analytical results.

[0190] Step 5:

[0191] The server uses natural language processing technology to analyze the user's emotions. The input is text data from the user. The emotion analysis engine classifies the text and infers the user's emotional state. The output is information about the user's emotional state.

[0192] Step 6:

[0193] The server generates personalized information based on the results of machine learning analysis and sentiment analysis. The input is the output from steps 4 and 5, which are used to construct textual content such as investment advice or risk management strategies.

[0194] Step 7:

[0195] The terminal displays personalized information received from the server. The input is information from the server, and a JavaScript library is used to generate interactive graphs and charts, which are then visually presented on the dashboard. The output is the visual information displayed on the user's screen.

[0196] Step 8:

[0197] The server records the user's behavior history and emotional data. The input is the user's past interaction history. This history is stored in a database and used to continuously optimize the user experience.

[0198] (Application Example 2)

[0199] 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".

[0200] Modern electronic payment systems are not adequately capable of managing users' financial situations while providing personalized suggestions and warnings. In particular, there is a need for decision-making support that takes into account users' emotional states. Current technologies make decisions based solely on financial information, making it difficult to provide optimal support for users. Furthermore, there is a lack of advanced prediction and suggestions that utilize emotional data, and these challenges need to be addressed.

[0201] 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.

[0202] In this invention, the server includes means for acquiring numerical information from the user and integrating and processing the information as necessary; means for performing predictions and analyses based on the input information using machine learning techniques; and means for generating personalized suggestions and warnings based on the analyzed sentiment data. This enables users to make appropriate decisions tailored to their emotional state and manage resources more safely and effectively.

[0203] "Numerical information" refers to quantitative data related to finance, including money, assets, revenue, and expenses.

[0204] "Machine learning technology" is a general term for algorithms and methods used to learn patterns and relationships from large amounts of data and perform predictions and analyses.

[0205] "Analyzed emotional data" refers to data indicating the emotional state, extracted by the emotion engine based on the user's input and responses.

[0206] "Personalized suggestions and warnings" refer to advice and alerts that are uniquely customized to the user's specific situation or emotional state.

[0207] A "presentation device" is a device or interface used to provide users with analysis results or suggestions visually or audibly.

[0208] "Natural language processing technology" refers to the technologies and methods used by computers to understand, interpret, and generate human language.

[0209] "Real-time updates" refers to a process where data is instantly collected and processed the moment it is generated, and the analysis results are immediately reflected.

[0210] To implement this invention, a system consisting of a user terminal, a server, and an external information source is configured. The user accesses an electronic payment platform they use on a daily basis and manages and updates their financial information through the terminal. The terminal collects numerical information such as the user's current assets, revenue, and expenses, and transmits it to the server.

[0211] The server is built on a cloud platform (e.g., AWS® S3) and uses Python and Django to build the backend. Machine learning techniques are implemented here, for example, running a sentiment analysis model using TensorFlow. The server integrates and analyzes numerical information received from users with non-numerical data obtained from external information services. This analysis enables predictions based on the user's financial situation and generates personalized suggestions and warnings based on sentiment data.

[0212] The analysis results are transmitted to the terminal's display device and intuitively visualized for the user through a user interface utilizing React Native. This allows users to receive decision-making support based on their own emotional state and financial situation.

[0213] As a concrete example, consider a situation where a user is about to purchase an expensive item while online shopping. In this case, the server's emotion engine analyzes the user's emotional state, and if anxiety or hesitation is detected, it displays a message on the device saying, "Please reconsider your current financial situation before purchasing." This encourages the user to make a more rational decision.

[0214] An example of a prompt to input into the generating AI model is: "The user is currently feeling anxious about spending. Please provide appropriate advice considering their current financial situation."

[0215] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0216] Step 1:

[0217] Financial information is entered on the user's terminal through everyday transaction activities. Users input data on revenue, expenses, and assets, which is collected by the terminal's control program. This information is formatted as data packets and sent to the server. Input is numerical data, and output is appropriately formatted data packets.

[0218] Step 2:

[0219] The server stores the received data packets in a storage service such as AWS S3. This data is then decoded using a Python script and prepared for the next analysis step. The input is data packets from the terminal, and the output is a data stream in a parseable format.

[0220] Step 3:

[0221] The server begins analyzing the integrated data using Python and TensorFlow. First, machine learning algorithms predict and analyze the information, thereby enabling future revenue and expenditure forecasts and investment risk assessments. The input is integrated data of numerical and non-numerical data, and the output is the prediction and analysis results based on this data.

[0222] Step 4:

[0223] The server activates an emotion engine to analyze emotional data obtained from user input. Here, it rapidly analyzes the user's emotional responses and generates personalized suggestions and warnings based on their state. The input is non-numerical data obtained from user behavior, and the output is feedback messages based on the user's emotional state.

[0224] Step 5:

[0225] Suggestions and warnings generated on the server are sent to the terminal's display device. The terminal visualizes this using a user interface built with React Native. The input is instruction data from the server, and the output is an intuitive message presented to the user.

[0226] Step 6:

[0227] Users make decisions based on the information presented. This feedback is collected again, sent to the server, and used for future predictive models. The input is user feedback, and the output is continuous data updates aimed at improving the machine learning model.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] [Second Embodiment]

[0232] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0233] 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.

[0234] 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).

[0235] 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.

[0236] 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.

[0237] 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).

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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".

[0244] The system of the present invention aims to efficiently integrate financial and non-financial data provided by users and to perform advanced analysis and predictions based on that data. This system is primarily implemented with the involvement of three entities: a server, a terminal, and a user.

[0245] First, users upload financial information to the server via their devices. This information includes revenue and expense history, and details of assets and liabilities. In addition, the server collects non-financial data from the internet. This non-financial data includes economic indicators, industry trends, and news reports.

[0246] Next, the server integrates these different datasets. Data cleaning and preprocessing are performed, removing unnecessary data, imputing missing values, and standardizing data formats. This process ensures consistency across each dataset, laying the foundation for analysis.

[0247] The server then analyzes the data using machine learning techniques. The server has the ability to run models such as sales forecasts and investment risk assessments, thereby improving the accuracy of predictions. For example, it can use regression analysis to forecast next year's sales or classification algorithms to assess investment risk.

[0248] The analysis results are sent from the server to the terminal and displayed in a format accessible to the user. The terminal visualizes the information in a dashboard format, providing an intuitive user experience. This allows users to easily understand complex datasets and use them to inform their decision-making.

[0249] Furthermore, the server also utilizes natural language processing technology to extract useful information from non-financial data. The server extracts keywords from news articles and reports and uses them to provide users with new insights.

[0250] Finally, the server continuously optimizes its machine learning model based on user feedback. This will enable more accurate predictions in the future, allowing it to respond to user requests more quickly and precisely.

[0251] In this way, the system of the present invention functions as a powerful tool for users to perform advanced and comprehensive financial analysis and make rational decisions based on it.

[0252] The following describes the processing flow.

[0253] Step 1:

[0254] Users upload financial information to the server using their devices. The data is typically in CSV or Excel file format, making data entry easy.

[0255] Step 2:

[0256] The server automatically collects non-financial data such as economic indicators and news articles via the internet. This data is obtained using APIs or web scraping.

[0257] Step 3:

[0258] The server integrates uploaded financial information with collected non-financial data. Data cleaning is performed to remove duplicate data and fill in missing data.

[0259] Step 4:

[0260] The server uses machine learning models to analyze data. For example, it uses regression analysis to predict sales trends and classification algorithms to evaluate investment risk.

[0261] Step 5:

[0262] The server uses natural language processing technology to extract useful information from non-financial data. It extracts keywords from news articles and identifies important market trends.

[0263] Step 6:

[0264] The server generates analysis results and sends them to the terminal. The results are visualized in a dashboard format and presented to the user as graphs and tables.

[0265] Step 7:

[0266] Users refer to the dashboard on their device to evaluate the analysis results and make decisions. The dashboard has an intuitive interface and is designed to allow users to quickly grasp the information they need.

[0267] Step 8:

[0268] Users take actions based on the analysis results and provide the system with feedback on the outcomes.

[0269] Step 9:

[0270] The server incorporates user feedback, adjusts the parameters of the machine learning model, and improves the accuracy of future predictions.

[0271] (Example 1)

[0272] 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."

[0273] In today's business environment, there is a demand for the rapid integration of data from multiple sources and for advanced analysis based on this data. However, efficiently integrating financial and non-financial data and performing consistent analysis is technically challenging. Furthermore, optimizing models to reflect user feedback is not easy, and there is a need to improve prediction accuracy. To solve these challenges, it is necessary to automate information aggregation and analysis to improve prediction accuracy and usability.

[0274] 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.

[0275] In this invention, the server includes means for acquiring financial information from users via an information processing device and integrating and preprocessing the information; means for performing predictions and analyses based on the input information using computer learning methods; means for visually presenting and notifying the analysis results through a user interface; means for optimizing the computer learning model using feedback generated by the user to improve prediction accuracy; means for actively collecting information from external information sources and integrating the information into the analysis; and means for ensuring consistency between each dataset and converting the data into a unified format. This enables the integration and centralized management of diverse information, leading to improved accuracy in practical predictions and analyses, and the realization of highly adaptable models that utilize user feedback.

[0276] An "information processing device" is a device that receives data from a user and performs necessary data preprocessing.

[0277] "Financial information" is a general term for data that represents a company's financial situation, including revenue, expenses, assets, and liabilities.

[0278] "Computer learning techniques" are technologies in which computers learn patterns using large amounts of data and then use that information to make predictions and perform analyses.

[0279] A "user interface" is a general term for the display and operating devices that allow computers and humans to exchange information.

[0280] "Feedback" refers to evaluations and improvement suggestions provided by users, which are used to improve the system.

[0281] "External information sources" refer to information obtained from outside the company, such as economic indicators and news found on the internet.

[0282] "Consistency" means that there are no inconsistencies between different datasets, and that a consistent data state is maintained.

[0283] The "unified format" means converting data provided in different formats into a consistent format, which is a means of standardizing analysis processing.

[0284] The embodiment for implementing this invention is a system composed of three entities: a user, a terminal, and a server. This system performs prediction and analysis based on the financial information provided by the user and visualizes and provides the results to the user.

[0285] First, the user transmits financial information to the server via their terminal. At this time, the terminal provides an interface for uploading information on revenue, expenses, assets, and liabilities in the Excel or CSV file format that the user has. The terminal has a user-friendly UI and seamlessly transfers the input information to the server.

[0286] Next, the server integrates the received financial information with non-financial data collected from external information sources. For this process, the Pandas library of Python is used to perform cleaning processes such as complementing missing values, unifying data formats, and deleting unnecessary data to ensure data consistency. Also, the server collects the latest economic indicators, market trends, and news reports through the Internet using APIs and scraping.

[0287] After the data is integrated, the server performs data analysis using machine learning techniques. Using the Scikit-learn library of Python, it performs prediction of sales and evaluation of investment risks through regression analysis and classification algorithms. This series of processes is designed to be intuitively usable by the user and can be performed by inputting, for example, "I want to predict the sales of a specific product category for next year" as an example of a prompt sentence using a generative AI model.

[0288] Finally, the analyzed results are sent from the server to the terminal. The terminal displays the results in graph and chart format using visualization libraries such as D3.js. This allows users to visually understand the analysis results and use them to make decisions. Furthermore, based on feedback provided by the user, the server continuously optimizes the machine learning model to improve prediction accuracy.

[0289] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0290] Step 1:

[0291] Users transmit financial information to the server via their terminal. The input consists of revenue, expense, asset, and liability information contained in Excel or CSV files. The terminal receives this data and uploads it to the server. During this process, the terminal performs a format check to ensure the accuracy of the input.

[0292] Step 2:

[0293] The server receives uploaded financial information and collects non-financial data from external sources. It uses economic indicators and news reports obtained via APIs as input. The server uses the Python Pandas library to clean the data, removing duplicates and imputing missing values. This ensures data consistency and integrates it into a format suitable for analysis.

[0294] Step 3:

[0295] The server performs computational learning based on integrated data. It uses cleaned financial and non-financial data as input. The server utilizes the Scikit-learn library to perform regression analysis and predict sales. It also applies classification algorithms to assess investment risk. The output includes numerical data for prediction results and risk assessment.

[0296] Step 4:

[0297] The server sends the analysis results to the terminal. The generated prediction results and risk assessment data are used as input. The terminal uses the D3.js library to visualize these results. The terminal displays the data in graphs and charts for easy understanding by the user, supporting their decision-making.

[0298] Step 5:

[0299] Users provide feedback to the server based on the analysis results. The server uses user comments and specific improvement suggestions as input. Based on this feedback, the server optimizes the generated AI model. Prompts such as "Please further improve prediction accuracy" are used. This improves accuracy in subsequent data analyses and enhances overall system performance.

[0300] (Application Example 1)

[0301] 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."

[0302] In modern society, users are expected to acquire information on a daily basis and engage in wise consumer behavior. However, amidst a vast amount of economic information and fluctuating price trends, it is difficult for individual users to determine the optimal timing for purchases and savings plans. Traditional methods lacked real-time information acquisition and analysis, and were insufficient to support users' decision-making. Furthermore, determining the optimal purchase time for a particular product in light of price fluctuations is a challenging task.

[0303] 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.

[0304] In this invention, the server includes means for acquiring economic information from a user, integrating and processing the relevant information as necessary, means for performing trend prediction and analysis based on the input information using machine learning technology, and means for visualizing and warning the analysis results through an information display device. As a result, the user can receive real-time information analysis and the provision of an optimal savings plan. In addition, by evaluating the price trend of a specific product and informing the appropriate purchase timing, consumers can achieve more efficient and wise consumption activities.

[0305] "Economic information" refers to data related to a user's consumption and expenditures, including consumption history, income, expenditures, and other financial-related information.

[0306] "Integration" is a process of unifying data obtained from multiple different information sources and summarizing it in a consistent format.

[0307] "Processing" is a process of shaping the acquired data into a form suitable for analysis and prediction, and performing deletion of unnecessary data and supplementation of missing values.

[0308] "Machine learning technology" is a technology in which a computer automatically identifies patterns based on a large amount of data and supports prediction and decision-making.

[0309] "Trend prediction" is a method of predicting future economic activities, price trends, etc. based on past data.

[0310] "Analysis" is a process of performing detailed evaluation and examination based on data and deriving insights obtained thereby.

[0311] "Information display device" is a hardware or software mechanism for a user to visually confirm the analysis results of data.

[0312] "Visualization" is a process of expressing analysis results using visual aid tools such as graphs and charts and providing them in a form that is easy for users to understand.

[0313] "Warning" refers to a notification function that clearly informs users of important situations or changes.

[0314] "Non-economic data" refers to information about factors other than economics, and may include social, environmental, and cultural factors.

[0315] "Spending trends" refer to patterns and developments related to users' spending habits, and enable future predictions based on these trends.

[0316] A "savings plan" is a method that provides users with specific guidelines and steps to reduce waste and make efficient use of resources.

[0317] "Price trends" refer to patterns or flows that show how the price of a particular product or service changes over time.

[0318] "Purchase timing" refers to the most opportune time for consumers to buy a particular product or service, and is determined based on price and market conditions.

[0319] To implement this invention, a server, a terminal, and a user must cooperate to form a system. The server plays a central role, aggregating economic and non-economic information. Users provide information about their income and expenses via the terminal. The server receives this information and preprocesses the data as needed.

[0320] Data preprocessing involves removing unnecessary data, imputing missing values, and ensuring consistent data formats. This prepares the aggregated data for machine learning. The server uses machine learning techniques, specifically Scikit-Learn, to predict future spending trends and price movements based on economic information. The analysis results are displayed to the user in a dashboard format on their terminal.

[0321] Furthermore, the server uses natural language processing techniques to analyze non-economic data, such as news articles. This provides new insights that may influence the user. Libraries such as TextBlob are used for text analysis. Through this process, the server suggests optimal purchase times and savings plans for specific products to the user.

[0322] For example, when a user is about to purchase a particular product, the server can predict relevant price fluctuations and provide specific advice such as, "There's a discount sale this month, so you can buy it at a good price." In this way, users can engage in economical and efficient consumer activities.

[0323] As an example of a prompt, you can input a request such as, "Please predict my spending for the next three months and suggest possible savings plans," and then use the generative AI model to obtain the analysis results.

[0324] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0325] Step 1:

[0326] Users send financial information, including income and expenses, to the server via their devices. This allows the financial data to be aggregated on the server. The server stores the received information in a database and prepares it for further processing.

[0327] Step 2:

[0328] The server collects non-economic data via the internet. This data includes general trends and economic news. The collected data is processed using a natural language processing library to extract relevant keywords. The results are stored in a database, preparing it to provide information that users may find interesting.

[0329] Step 3:

[0330] The server preprocesses the aggregated economic information. This stage involves removing unnecessary data and imputing missing values. Specifically, it standardizes the data format and performs data cleansing. This process generates a clean dataset that can be used by machine learning models.

[0331] Step 4:

[0332] The server analyzes processed data using machine learning models. It leverages Scikit-Learn to predict future spending trends and price movements. Historical consumption data is used as input, and the output generates predictions of purchasing patterns and specific suggestions.

[0333] Step 5:

[0334] The server sends the analysis results to the terminal and provides them to the user in a visualized format. The terminal displays a dashboard on its display device, making it easy for the user to understand intuitively. Information is presented using specific graphs and notification messages.

[0335] Step 6:

[0336] Users review the information provided from their devices and use it as a reference for specific consumer behavior. They also send feedback from their devices to the server, which helps evaluate the analysis results and improve the model for future use.

[0337] 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.

[0338] This invention is a system that efficiently integrates financial and non-financial data and incorporates an emotion engine to analyze and recognize user emotions, thereby providing more personalized analysis results and suggestions. Embodiments of this system primarily consist of a server, terminals, and users.

[0339] First, users upload financial information to the server via their devices. This includes data such as revenue, expenses, and assets. In addition, the server retrieves non-financial data from the internet. This consists of external information such as economic indicators and news.

[0340] The server integrates the received financial and non-financial data and analyzes the data using machine learning techniques. For example, it runs models to perform sales forecasts and risk assessments, and provides strategic insights based on the results.

[0341] Furthermore, the server is equipped with an emotion engine that analyzes user input and responses through the user interface to recognize emotions. This enables the presentation of information tailored to the user's mental state. For example, in a stressful situation with high investment risk, it can output reassuring messages to encourage calm decision-making.

[0342] The device receives analysis results from the server and personalized content tailored to the user's emotional state, which is then intuitively visualized through a dashboard. This allows users to review analysis results that resonate with their own emotions and decide on their next course of action.

[0343] Furthermore, the server records a history of user emotions and continuously uses this information to optimize the user experience. By analyzing past emotional data, it is possible to understand how users felt and responded in different situations, and use this information to inform future suggestions.

[0344] Thus, the system of the present invention supports more effective decision-making and functions in a way that meets individual needs by analyzing the user's financial information and providing insights that correspond to the user's emotional state.

[0345] The following describes the processing flow.

[0346] Step 1:

[0347] Users upload financial information to the server using their devices. This information includes numerical data such as revenue, expenses, and assets, as well as related text files.

[0348] Step 2:

[0349] The server collects non-financial data via the internet. This includes economic indicators, industry news, and general market trends. Data collection is performed using APIs and scraping techniques.

[0350] Step 3:

[0351] The server integrates and cleans the collected financial and non-financial data. It standardizes data formats and imputes missing values ​​to prepare the data for analysis.

[0352] Step 4:

[0353] The server begins analyzing data using a machine learning model. It forecasts sales and assesses investment risks, generating analytical results based on these findings.

[0354] Step 5:

[0355] The server uses an emotion engine to analyze user input and reactions obtained from the user interface and recognize the user's emotional state.

[0356] Step 6:

[0357] Based on the results from the emotion engine, the server adjusts the displayed analysis and suggestions according to the user's emotional state. For example, if the user is feeling stressed, it prioritizes displaying information that provides a sense of reassurance.

[0358] Step 7:

[0359] The device displays the optimized analysis results and suggestions to the user via a user interface. The dashboard includes visually organized graphs and reports.

[0360] Step 8:

[0361] Users review the displayed dashboard and make decisions as needed. Based on the suggestions and information presented, users can decide on specific actions.

[0362] Step 9:

[0363] The system receives feedback on the actions taken by the user and their emotional responses to those actions.

[0364] Step 10:

[0365] Based on the feedback, the server readjusts the parameters of the machine learning model and emotion engine to optimize prediction accuracy and user experience.

[0366] (Example 2)

[0367] 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".

[0368] In modern information technology, the analysis of numerical information and decision support play crucial roles in various fields. However, conventional systems are specialized in the analysis of numerical information, making it difficult to provide personalized information that takes into account the emotional state of the user. Furthermore, there is a lack of mechanisms to utilize past history in order to improve the accuracy of information and accurately predict the future needs of users. Thus, there is a demand for providing effective decision support to users and solutions that meet their individual needs.

[0369] 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.

[0370] In this invention, the server includes means for acquiring numerical information from the user and integrating and preprocessing the information as necessary, means for performing estimation and evaluation based on the input information using a machine learning algorithm, and means for visualizing and notifying the evaluation results through a display device. This enables data analysis that takes into account the user's emotional state and the provision of personalized information.

[0371] "User" refers to an individual who uses the system to provide numerical information and receives the results.

[0372] "Numerical information" refers to information that includes financial data such as revenue, expenses, and assets.

[0373] A "server" refers to a computer system that receives, processes, and analyzes data from users.

[0374] A "machine learning algorithm" refers to a computational method or model that uses data to make predictions and perform analyses.

[0375] "Estimation and evaluation" refers to predictions and their analysis results calculated using machine learning algorithms based on the input numerical information.

[0376] A "display device" refers to a device used to present information to a user in a visual or other format.

[0377] "Visualization" means presenting analysis results in a visual form, such as diagrams or graphs, to make them easier for users to understand.

[0378] "Emotional state" refers to the psychological and emotional state inferred from the user's input and responses.

[0379] "History" refers to records of information that users have provided in the past, as well as feedback received from the system at that time.

[0380] "Non-numerical data" refers to data that represents information other than numerical values, such as text and news articles, and is analyzed by a system.

[0381] This invention is a system that efficiently integrates numerical and non-numerical data of users and performs sentiment analysis to provide more personalized analysis results and suggestions. This system mainly consists of a server, terminals, and users.

[0382] The server plays a central role in processing numerical and non-numerical data. It receives financial data such as revenue, expenses, and assets transmitted from users via their devices. This data is retrieved via the HTTP protocol and securely stored in a database. The server also uses APIs to retrieve non-numerical data such as economic indicators and news from the internet.

[0383] For data integration and analysis, we will use the Python Pandas library. Pandas allows for efficient merging of numerical and non-numerical data using dataframes. As for machine learning algorithms, we will use TensorFlow and PyTorch to run predictive models and make predictions and evaluations about users' financial situations.

[0384] The system utilizes natural language processing (NLP) technology for emotion analysis. Specifically, it analyzes user input data and uses an emotion engine to infer the user's emotional state. This allows for the provision of customized information tailored to the user's mental state.

[0385] The terminal is a device that visually displays the analysis results received from the server. Using the JavaScript library D3.js, it generates intuitive graphs and charts on the dashboard, presenting information to the user in an easy-to-understand manner.

[0386] Furthermore, the server records the user's past activity history and emotional responses, and uses this information to optimize future suggestions. This enables personalized suggestions for each user.

[0387] As a concrete example, here is an example of a prompt message: "Based on the latest revenue data and economic news, forecast business growth and propose measures to address user concerns."

[0388] Thus, the present invention functions to support more effective decision-making by performing comprehensive information processing based on the user's numerical information and emotions.

[0389] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0390] Step 1:

[0391] Users upload their financial data using their device. The input is, for example, a CSV file containing revenue, expense, and asset information. When a dedicated upload button on the device is clicked, the file is sent to the server, which receives this data via the HTTP protocol and stores it in the database.

[0392] Step 2:

[0393] The server uses APIs to collect the latest non-numerical data from the internet. The input data consists of economic indicators and news articles, which are retrieved in JSON format. The data is processed in real time and stored in the server's database. This step involves making requests to external APIs and storing the response data.

[0394] Step 3:

[0395] The server integrates financial and non-numerical data using the Pandas library. The input data consists of the information collected in steps 1 and 2. This integration process merges dataframes with common key items to create a consistent dataset. The output is the integrated dataset.

[0396] Step 4:

[0397] The server executes machine learning algorithms on the integrated dataset. The input is the integrated dataset, and the model used is a pre-trained model using TensorFlow. This model is used to predict sales and assess risks, and the output is these analytical results.

[0398] Step 5:

[0399] The server uses natural language processing technology to analyze the user's emotions. The input is text data from the user. The emotion analysis engine classifies the text and infers the user's emotional state. The output is information about the user's emotional state.

[0400] Step 6:

[0401] The server generates personalized information based on the results of machine learning analysis and sentiment analysis. The input is the output from steps 4 and 5, which are used to construct textual content such as investment advice or risk management strategies.

[0402] Step 7:

[0403] The terminal displays personalized information received from the server. The input is information from the server, and a JavaScript library is used to generate interactive graphs and charts, which are then visually presented on the dashboard. The output is the visual information displayed on the user's screen.

[0404] Step 8:

[0405] The server records the user's behavior history and emotional data. The input is the user's past interaction history. This history is stored in a database and used to continuously optimize the user experience.

[0406] (Application Example 2)

[0407] 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."

[0408] Modern electronic payment systems are not adequately capable of managing users' financial situations while providing personalized suggestions and warnings. In particular, there is a need for decision-making support that takes into account users' emotional states. Current technologies make decisions based solely on financial information, making it difficult to provide optimal support for users. Furthermore, there is a lack of advanced prediction and suggestions that utilize emotional data, and these challenges need to be addressed.

[0409] 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.

[0410] In this invention, the server includes means for acquiring numerical information from the user and integrating and processing the information as necessary; means for performing predictions and analyses based on the input information using machine learning techniques; and means for generating personalized suggestions and warnings based on the analyzed sentiment data. This enables users to make appropriate decisions tailored to their emotional state and manage resources more safely and effectively.

[0411] "Numerical information" refers to quantitative data related to finance, including money, assets, revenue, and expenses.

[0412] "Machine learning technology" is a general term for algorithms and methods used to learn patterns and relationships from large amounts of data and perform predictions and analyses.

[0413] "Analyzed emotional data" refers to data indicating the emotional state, extracted by the emotion engine based on the user's input and responses.

[0414] "Personalized suggestions and warnings" refer to advice and alerts that are uniquely customized to the user's specific situation or emotional state.

[0415] A "presentation device" is a device or interface used to provide users with analysis results or suggestions visually or audibly.

[0416] "Natural language processing technology" refers to the technologies and methods used by computers to understand, interpret, and generate human language.

[0417] "Real-time updates" refers to a process where data is instantly collected and processed the moment it is generated, and the analysis results are immediately reflected.

[0418] To implement this invention, a system consisting of a user terminal, a server, and an external information source is configured. The user accesses an electronic payment platform they use on a daily basis and manages and updates their financial information through the terminal. The terminal collects numerical information such as the user's current assets, revenue, and expenses, and transmits it to the server.

[0419] The server is built on a cloud platform (e.g., AWS S3), and the backend is built using Python and Django. Machine learning techniques are implemented here, for example, running a sentiment analysis model using TensorFlow. The server integrates and analyzes numerical information received from users with non-numerical data obtained from external information services. This analysis enables predictions based on the user's financial situation and generates personalized suggestions and warnings based on sentiment data.

[0420] The analysis results are transmitted to the terminal's display device and intuitively visualized for the user through a user interface utilizing React Native. This allows users to receive decision-making support based on their own emotional state and financial situation.

[0421] As a concrete example, consider a situation where a user is about to purchase an expensive item while online shopping. In this case, the server's emotion engine analyzes the user's emotional state, and if anxiety or hesitation is detected, it displays a message on the device saying, "Please reconsider your current financial situation before purchasing." This encourages the user to make a more rational decision.

[0422] An example of a prompt to input into the generating AI model is: "The user is currently feeling anxious about spending. Please provide appropriate advice considering their current financial situation."

[0423] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0424] Step 1:

[0425] Financial information is entered on the user's terminal through everyday transaction activities. Users input data on revenue, expenses, and assets, which is collected by the terminal's control program. This information is formatted as data packets and sent to the server. Input is numerical data, and output is appropriately formatted data packets.

[0426] Step 2:

[0427] The server stores the received data packets in a storage service such as AWS S3. This data is then decoded using a Python script and prepared for the next analysis step. The input is data packets from the terminal, and the output is a data stream in a parseable format.

[0428] Step 3:

[0429] The server begins analyzing the integrated data using Python and TensorFlow. First, machine learning algorithms predict and analyze the information, thereby enabling future revenue and expenditure forecasts and investment risk assessments. The input is integrated data of numerical and non-numerical data, and the output is the prediction and analysis results based on this data.

[0430] Step 4:

[0431] The server activates an emotion engine to analyze emotional data obtained from user input. Here, it rapidly analyzes the user's emotional responses and generates personalized suggestions and warnings based on their state. The input is non-numerical data obtained from user behavior, and the output is feedback messages based on the user's emotional state.

[0432] Step 5:

[0433] Suggestions and warnings generated on the server are sent to the terminal's display device. The terminal visualizes this using a user interface built with React Native. The input is instruction data from the server, and the output is an intuitive message presented to the user.

[0434] Step 6:

[0435] Users make decisions based on the information presented. This feedback is collected again, sent to the server, and used for future predictive models. The input is user feedback, and the output is continuous data updates aimed at improving the machine learning model.

[0436] 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.

[0437] 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.

[0438] 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.

[0439] [Third Embodiment]

[0440] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0441] 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.

[0442] 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).

[0443] 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.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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".

[0452] The system of the present invention aims to efficiently integrate financial and non-financial data provided by users and to perform advanced analysis and predictions based on that data. This system is primarily implemented with the involvement of three entities: a server, a terminal, and a user.

[0453] First, users upload financial information to the server via their devices. This information includes revenue and expense history, and details of assets and liabilities. In addition, the server collects non-financial data from the internet. This non-financial data includes economic indicators, industry trends, and news reports.

[0454] Next, the server integrates these different datasets. Data cleaning and preprocessing are performed, removing unnecessary data, imputing missing values, and standardizing data formats. This process ensures consistency across each dataset, laying the foundation for analysis.

[0455] The server then analyzes the data using machine learning techniques. The server has the ability to run models such as sales forecasts and investment risk assessments, thereby improving the accuracy of predictions. For example, it can use regression analysis to forecast next year's sales or classification algorithms to assess investment risk.

[0456] The analysis results are sent from the server to the terminal and displayed in a format accessible to the user. The terminal visualizes the information in a dashboard format, providing an intuitive user experience. This allows users to easily understand complex datasets and use them to inform their decision-making.

[0457] Furthermore, the server also utilizes natural language processing technology to extract useful information from non-financial data. The server extracts keywords from news articles and reports and uses them to provide users with new insights.

[0458] Finally, the server continuously optimizes its machine learning model based on user feedback. This will enable more accurate predictions in the future, allowing it to respond to user requests more quickly and precisely.

[0459] In this way, the system of the present invention functions as a powerful tool for users to perform advanced and comprehensive financial analysis and make rational decisions based on it.

[0460] The following describes the processing flow.

[0461] Step 1:

[0462] Users upload financial information to the server using their devices. The data is typically in CSV or Excel file format, making data entry easy.

[0463] Step 2:

[0464] The server automatically collects non-financial data such as economic indicators and news articles via the internet. This data is obtained using APIs or web scraping.

[0465] Step 3:

[0466] The server integrates uploaded financial information with collected non-financial data. Data cleaning is performed to remove duplicate data and fill in missing data.

[0467] Step 4:

[0468] The server uses machine learning models to analyze data. For example, it uses regression analysis to predict sales trends and classification algorithms to evaluate investment risk.

[0469] Step 5:

[0470] The server uses natural language processing technology to extract useful information from non-financial data. It extracts keywords from news articles and identifies important market trends.

[0471] Step 6:

[0472] The server generates analysis results and sends them to the terminal. The results are visualized in a dashboard format and presented to the user as graphs and tables.

[0473] Step 7:

[0474] Users refer to the dashboard on their device to evaluate the analysis results and make decisions. The dashboard has an intuitive interface and is designed to allow users to quickly grasp the information they need.

[0475] Step 8:

[0476] Users take actions based on the analysis results and provide the system with feedback on the outcomes.

[0477] Step 9:

[0478] The server incorporates user feedback, adjusts the parameters of the machine learning model, and improves the accuracy of future predictions.

[0479] (Example 1)

[0480] 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."

[0481] In today's business environment, there is a demand for the rapid integration of data from multiple sources and for advanced analysis based on this data. However, efficiently integrating financial and non-financial data and performing consistent analysis is technically challenging. Furthermore, optimizing models to reflect user feedback is not easy, and there is a need to improve prediction accuracy. To solve these challenges, it is necessary to automate information aggregation and analysis to improve prediction accuracy and usability.

[0482] 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.

[0483] In this invention, the server includes means for acquiring financial information from users via an information processing device and integrating and preprocessing the information; means for performing predictions and analyses based on the input information using computer learning methods; means for visually presenting and notifying the analysis results through a user interface; means for optimizing the computer learning model using feedback generated by the user to improve prediction accuracy; means for actively collecting information from external information sources and integrating the information into the analysis; and means for ensuring consistency between each dataset and converting the data into a unified format. This enables the integration and centralized management of diverse information, leading to improved accuracy in practical predictions and analyses, and the realization of highly adaptable models that utilize user feedback.

[0484] An "information processing device" is a device that receives data from a user and performs necessary data preprocessing.

[0485] "Financial information" is a general term for data that represents a company's financial situation, including revenue, expenses, assets, and liabilities.

[0486] "Computer learning techniques" are technologies in which computers learn patterns using large amounts of data and then use that information to make predictions and perform analyses.

[0487] A "user interface" is a general term for the display and operating devices that allow computers and humans to exchange information.

[0488] "Feedback" refers to evaluations and improvement suggestions provided by users, which are used to improve the system.

[0489] "External information sources" refer to information obtained from outside the company, such as economic indicators and news found on the internet.

[0490] "Consistency" means that there are no inconsistencies between different datasets, and that a consistent data state is maintained.

[0491] A "unified format" is a means of standardizing analytical processing by converting data provided in different formats into a consistent format.

[0492] The embodiment for carrying out this invention is a system composed of three entities: a user, a terminal, and a server. This system performs predictions and analyses based on financial information provided by the user, and provides the results to the user in a visualized format.

[0493] First, the user sends financial information to the server via their device. The device provides an interface for uploading information on revenue, expenses, assets, and liabilities in Excel or CSV file formats. The device features a user-friendly UI and seamlessly transfers the entered information to the server.

[0494] Next, the server integrates the received financial information with non-financial data collected from external sources. This process uses the Python Pandas library and includes cleaning operations such as imputing missing values, standardizing data formats, and deleting unnecessary data to ensure data integrity. The server also collects the latest economic indicators, market trends, and news reports via the internet using APIs and web scraping.

[0495] After the data is integrated, the server performs data analysis using computer learning techniques. Utilizing the Python Scikit-learn library, it performs regression analysis and classification algorithms to predict sales and assess investment risk. This entire process is designed to be intuitive for the user; for example, a prompt using the generative AI model can be entered as, "Please predict sales for a specific product category next year."

[0496] Finally, the analyzed results are sent from the server to the terminal. The terminal displays the results in graph and chart format using visualization libraries such as D3.js. This allows users to visually understand the analysis results and use them to make decisions. Furthermore, based on feedback provided by the user, the server continuously optimizes the machine learning model to improve prediction accuracy.

[0497] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0498] Step 1:

[0499] Users transmit financial information to the server via their terminal. The input consists of revenue, expense, asset, and liability information contained in Excel or CSV files. The terminal receives this data and uploads it to the server. During this process, the terminal performs a format check to ensure the accuracy of the input.

[0500] Step 2:

[0501] The server receives uploaded financial information and collects non-financial data from external sources. It uses economic indicators and news reports obtained via APIs as input. The server uses the Python Pandas library to clean the data, removing duplicates and imputing missing values. This ensures data consistency and integrates it into a format suitable for analysis.

[0502] Step 3:

[0503] The server performs computational learning based on integrated data. It uses cleaned financial and non-financial data as input. The server utilizes the Scikit-learn library to perform regression analysis and predict sales. It also applies classification algorithms to assess investment risk. The output includes numerical data for prediction results and risk assessment.

[0504] Step 4:

[0505] The server sends the analysis results to the terminal. The generated prediction results and risk assessment data are used as input. The terminal uses the D3.js library to visualize these results. The terminal displays the data in graphs and charts for easy understanding by the user, supporting their decision-making.

[0506] Step 5:

[0507] Users provide feedback to the server based on the analysis results. The server uses user comments and specific improvement suggestions as input. Based on this feedback, the server optimizes the generated AI model. Prompts such as "Please further improve prediction accuracy" are used. This improves accuracy in subsequent data analyses and enhances overall system performance.

[0508] (Application Example 1)

[0509] 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."

[0510] In modern society, users are expected to acquire information on a daily basis and engage in wise consumer behavior. However, amidst a vast amount of economic information and fluctuating price trends, it is difficult for individual users to determine the optimal timing for purchases and savings plans. Traditional methods lacked real-time information acquisition and analysis, and were insufficient to support users' decision-making. Furthermore, determining the optimal purchase time for a particular product in light of price fluctuations is a challenging task.

[0511] 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.

[0512] In this invention, the server includes means for acquiring economic information from the user and integrating and processing the information as needed, means for performing trend prediction and analysis based on the input information using machine learning technology, and means for visualizing and warning the analysis results through an information display device. This enables the user to receive real-time information analysis and optimal savings plans. Furthermore, by evaluating price trends of specific products and notifying consumers of the appropriate timing for purchase, consumers can engage in more efficient and wiser consumer activities.

[0513] "Economic information" refers to data related to a user's consumption and spending, including consumption history, income, spending, and other financial information.

[0514] "Integration" is the process of unifying data obtained from multiple different sources and compiling it into a consistent format.

[0515] "Processing" refers to the process of shaping acquired data into a format suitable for analysis and prediction, removing unnecessary data, and imputing missing values.

[0516] "Machine learning technology" is a technique in which computers automatically identify patterns based on large amounts of data and use that information to support predictions and decision-making.

[0517] "Trend forecasting" is a method of predicting future economic activity and price trends based on past data.

[0518] "Analysis" is the process of conducting detailed evaluations and examinations based on data, and deriving insights from those evaluations.

[0519] An "information display device" is a hardware and software system that allows users to visually confirm the results of data analysis.

[0520] "Visualization" is the process of representing analysis results using visual aids such as graphs and charts, and providing them in a way that is easy for users to understand.

[0521] "Warning" refers to a notification function that clearly informs users of important situations or changes.

[0522] "Non-economic data" refers to information about factors other than economics, and may include social, environmental, and cultural factors.

[0523] "Spending trends" refer to patterns and developments related to users' spending habits, and enable future predictions based on these trends.

[0524] A "savings plan" is a method that provides users with specific guidelines and steps to reduce waste and make efficient use of resources.

[0525] "Price trends" refer to patterns or flows that show how the price of a particular product or service changes over time.

[0526] "Purchase timing" refers to the most opportune time for consumers to buy a particular product or service, and is determined based on price and market conditions.

[0527] To implement this invention, a server, a terminal, and a user must cooperate to form a system. The server plays a central role, aggregating economic and non-economic information. Users provide information about their income and expenses via the terminal. The server receives this information and preprocesses the data as needed.

[0528] Data preprocessing involves removing unnecessary data, imputing missing values, and ensuring consistent data formats. This prepares the aggregated data for machine learning. The server uses machine learning techniques, specifically Scikit-Learn, to predict future spending trends and price movements based on economic information. The analysis results are displayed to the user in a dashboard format on their terminal.

[0529] Furthermore, the server uses natural language processing techniques to analyze non-economic data, such as news articles. This provides new insights that may influence the user. Libraries such as TextBlob are used for text analysis. Through this process, the server suggests optimal purchase times and savings plans for specific products to the user.

[0530] For example, when a user is about to purchase a particular product, the server can predict relevant price fluctuations and provide specific advice such as, "There's a discount sale this month, so you can buy it at a good price." In this way, users can engage in economical and efficient consumer activities.

[0531] As an example of a prompt, you can input a request such as, "Please predict my spending for the next three months and suggest possible savings plans," and then use the generative AI model to obtain the analysis results.

[0532] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0533] Step 1:

[0534] Users send financial information, including income and expenses, to the server via their devices. This allows the financial data to be aggregated on the server. The server stores the received information in a database and prepares it for further processing.

[0535] Step 2:

[0536] The server collects non-economic data via the internet. This data includes general trends and economic news. The collected data is processed using a natural language processing library to extract relevant keywords. The results are stored in a database, preparing it to provide information that users may find interesting.

[0537] Step 3:

[0538] The server preprocesses the aggregated economic information. This stage involves removing unnecessary data and imputing missing values. Specifically, it standardizes the data format and performs data cleansing. This process generates a clean dataset that can be used by machine learning models.

[0539] Step 4:

[0540] The server analyzes processed data using machine learning models. It leverages Scikit-Learn to predict future spending trends and price movements. Historical consumption data is used as input, and the output generates predictions of purchasing patterns and specific suggestions.

[0541] Step 5:

[0542] The server sends the analysis results to the terminal and provides them to the user in a visualized format. The terminal displays a dashboard on its display device, making it easy for the user to understand intuitively. Information is presented using specific graphs and notification messages.

[0543] Step 6:

[0544] Users review the information provided from their devices and use it as a reference for specific consumer behavior. They also send feedback from their devices to the server, which helps evaluate the analysis results and improve the model for future use.

[0545] 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.

[0546] This invention is a system that efficiently integrates financial and non-financial data and incorporates an emotion engine to analyze and recognize user emotions, thereby providing more personalized analysis results and suggestions. Embodiments of this system primarily consist of a server, terminals, and users.

[0547] First, users upload financial information to the server via their devices. This includes data such as revenue, expenses, and assets. In addition, the server retrieves non-financial data from the internet. This consists of external information such as economic indicators and news.

[0548] The server integrates the received financial and non-financial data and analyzes the data using machine learning techniques. For example, it runs models to perform sales forecasts and risk assessments, and provides strategic insights based on the results.

[0549] Furthermore, the server is equipped with an emotion engine that analyzes user input and responses through the user interface to recognize emotions. This enables the presentation of information tailored to the user's mental state. For example, in a stressful situation with high investment risk, it can output reassuring messages to encourage calm decision-making.

[0550] The device receives analysis results from the server and personalized content tailored to the user's emotional state, which is then intuitively visualized through a dashboard. This allows users to review analysis results that resonate with their own emotions and decide on their next course of action.

[0551] Furthermore, the server records a history of user emotions and continuously uses this information to optimize the user experience. By analyzing past emotional data, it is possible to understand how users felt and responded in different situations, and use this information to inform future suggestions.

[0552] Thus, the system of the present invention supports more effective decision-making and functions in a way that meets individual needs by analyzing the user's financial information and providing insights that correspond to the user's emotional state.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] Users upload financial information to the server using their devices. This information includes numerical data such as revenue, expenses, and assets, as well as related text files.

[0556] Step 2:

[0557] The server collects non-financial data via the internet. This includes economic indicators, industry news, and general market trends. Data collection is performed using APIs and scraping techniques.

[0558] Step 3:

[0559] The server integrates and cleans the collected financial and non-financial data. It standardizes data formats and imputes missing values ​​to prepare the data for analysis.

[0560] Step 4:

[0561] The server begins analyzing data using a machine learning model. It forecasts sales and assesses investment risks, generating analytical results based on these findings.

[0562] Step 5:

[0563] The server uses an emotion engine to analyze user input and reactions obtained from the user interface and recognize the user's emotional state.

[0564] Step 6:

[0565] Based on the results from the emotion engine, the server adjusts the displayed analysis and suggestions according to the user's emotional state. For example, if the user is feeling stressed, it prioritizes displaying information that provides a sense of reassurance.

[0566] Step 7:

[0567] The device displays the optimized analysis results and suggestions to the user via a user interface. The dashboard includes visually organized graphs and reports.

[0568] Step 8:

[0569] Users review the displayed dashboard and make decisions as needed. Based on the suggestions and information presented, users can decide on specific actions.

[0570] Step 9:

[0571] The system receives feedback on the actions taken by the user and their emotional responses to those actions.

[0572] Step 10:

[0573] Based on the feedback, the server readjusts the parameters of the machine learning model and emotion engine to optimize prediction accuracy and user experience.

[0574] (Example 2)

[0575] 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."

[0576] In modern information technology, the analysis of numerical information and decision support play crucial roles in various fields. However, conventional systems are specialized in the analysis of numerical information, making it difficult to provide personalized information that takes into account the emotional state of the user. Furthermore, there is a lack of mechanisms to utilize past history in order to improve the accuracy of information and accurately predict the future needs of users. Thus, there is a demand for providing effective decision support to users and solutions that meet their individual needs.

[0577] 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.

[0578] In this invention, the server includes means for acquiring numerical information from the user and integrating and preprocessing the information as necessary, means for performing estimation and evaluation based on the input information using a machine learning algorithm, and means for visualizing and notifying the evaluation results through a display device. This enables data analysis that takes into account the user's emotional state and the provision of personalized information.

[0579] "User" refers to an individual who uses the system to provide numerical information and receives the results.

[0580] "Numerical information" refers to information that includes financial data such as revenue, expenses, and assets.

[0581] A "server" refers to a computer system that receives, processes, and analyzes data from users.

[0582] A "machine learning algorithm" refers to a computational method or model that uses data to make predictions and perform analyses.

[0583] "Estimation and evaluation" refers to predictions and their analysis results calculated using machine learning algorithms based on the input numerical information.

[0584] A "display device" refers to a device used to present information to a user in a visual or other format.

[0585] "Visualization" means presenting analysis results in a visual form, such as diagrams or graphs, to make them easier for users to understand.

[0586] "Emotional state" refers to the psychological and emotional state inferred from the user's input and responses.

[0587] "History" refers to records of information that users have provided in the past, as well as feedback received from the system at that time.

[0588] "Non-numerical data" refers to data that represents information other than numerical values, such as text and news articles, and is analyzed by a system.

[0589] This invention is a system that efficiently integrates numerical and non-numerical data of users and performs sentiment analysis to provide more personalized analysis results and suggestions. This system mainly consists of a server, terminals, and users.

[0590] The server plays a central role in processing numerical and non-numerical data. It receives financial data such as revenue, expenses, and assets transmitted from users via their devices. This data is retrieved via the HTTP protocol and securely stored in a database. The server also uses APIs to retrieve non-numerical data such as economic indicators and news from the internet.

[0591] For data integration and analysis, we will use the Python Pandas library. Pandas allows for efficient merging of numerical and non-numerical data using dataframes. As for machine learning algorithms, we will use TensorFlow and PyTorch to run predictive models and make predictions and evaluations about users' financial situations.

[0592] The system utilizes natural language processing (NLP) technology for emotion analysis. Specifically, it analyzes user input data and uses an emotion engine to infer the user's emotional state. This allows for the provision of customized information tailored to the user's mental state.

[0593] The terminal is a device that visually displays the analysis results received from the server. Using the JavaScript library D3.js, it generates intuitive graphs and charts on the dashboard, presenting information to the user in an easy-to-understand manner.

[0594] Furthermore, the server records the user's past activity history and emotional responses, and uses this information to optimize future suggestions. This enables personalized suggestions for each user.

[0595] As a concrete example, here is an example of a prompt message: "Based on the latest revenue data and economic news, forecast business growth and propose measures to address user concerns."

[0596] Thus, the present invention functions to support more effective decision-making by performing comprehensive information processing based on the user's numerical information and emotions.

[0597] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0598] Step 1:

[0599] Users upload their financial data using their device. The input is, for example, a CSV file containing revenue, expense, and asset information. When a dedicated upload button on the device is clicked, the file is sent to the server, which receives this data via the HTTP protocol and stores it in the database.

[0600] Step 2:

[0601] The server uses APIs to collect the latest non-numerical data from the internet. The input data consists of economic indicators and news articles, which are retrieved in JSON format. The data is processed in real time and stored in the server's database. This step involves making requests to external APIs and storing the response data.

[0602] Step 3:

[0603] The server integrates financial and non-numerical data using the Pandas library. The input data consists of the information collected in steps 1 and 2. This integration process merges dataframes with common key items to create a consistent dataset. The output is the integrated dataset.

[0604] Step 4:

[0605] The server executes machine learning algorithms on the integrated dataset. The input is the integrated dataset, and the model used is a pre-trained model using TensorFlow. This model is used to predict sales and assess risks, and the output is these analytical results.

[0606] Step 5:

[0607] The server uses natural language processing technology to analyze the user's emotions. The input is text data from the user. The emotion analysis engine classifies the text and infers the user's emotional state. The output is information about the user's emotional state.

[0608] Step 6:

[0609] The server generates personalized information based on the results of machine learning analysis and sentiment analysis. The input is the output from steps 4 and 5, which are used to construct textual content such as investment advice or risk management strategies.

[0610] Step 7:

[0611] The terminal displays personalized information received from the server. The input is information from the server, and a JavaScript library is used to generate interactive graphs and charts, which are then visually presented on the dashboard. The output is the visual information displayed on the user's screen.

[0612] Step 8:

[0613] The server records the user's behavior history and emotional data. The input is the user's past interaction history. This history is stored in a database and used to continuously optimize the user experience.

[0614] (Application Example 2)

[0615] 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."

[0616] Modern electronic payment systems are not adequately capable of managing users' financial situations while providing personalized suggestions and warnings. In particular, there is a need for decision-making support that takes into account users' emotional states. Current technologies make decisions based solely on financial information, making it difficult to provide optimal support for users. Furthermore, there is a lack of advanced prediction and suggestions that utilize emotional data, and these challenges need to be addressed.

[0617] 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.

[0618] In this invention, the server includes means for acquiring numerical information from the user and integrating and processing the information as necessary; means for performing predictions and analyses based on the input information using machine learning techniques; and means for generating personalized suggestions and warnings based on the analyzed sentiment data. This enables users to make appropriate decisions tailored to their emotional state and manage resources more safely and effectively.

[0619] "Numerical information" refers to quantitative data related to finance, including money, assets, revenue, and expenses.

[0620] "Machine learning technology" is a general term for algorithms and methods used to learn patterns and relationships from large amounts of data and perform predictions and analyses.

[0621] "Analyzed emotional data" refers to data indicating the emotional state, extracted by the emotion engine based on the user's input and responses.

[0622] "Personalized suggestions and warnings" refer to advice and alerts that are uniquely customized to the user's specific situation or emotional state.

[0623] A "presentation device" is a device or interface used to provide users with analysis results or suggestions visually or audibly.

[0624] "Natural language processing technology" refers to the technologies and methods used by computers to understand, interpret, and generate human language.

[0625] "Real-time updates" refers to a process where data is instantly collected and processed the moment it is generated, and the analysis results are immediately reflected.

[0626] To implement this invention, a system consisting of a user terminal, a server, and an external information source is configured. The user accesses an electronic payment platform they use on a daily basis and manages and updates their financial information through the terminal. The terminal collects numerical information such as the user's current assets, revenue, and expenses, and transmits it to the server.

[0627] The server is built on a cloud platform (e.g., AWS S3), and the backend is built using Python and Django. Machine learning techniques are implemented here, for example, running a sentiment analysis model using TensorFlow. The server integrates and analyzes numerical information received from users with non-numerical data obtained from external information services. This analysis enables predictions based on the user's financial situation and generates personalized suggestions and warnings based on sentiment data.

[0628] The analysis results are transmitted to the terminal's display device and intuitively visualized for the user through a user interface utilizing React Native. This allows users to receive decision-making support based on their own emotional state and financial situation.

[0629] As a concrete example, consider a situation where a user is about to purchase an expensive item while online shopping. In this case, the server's emotion engine analyzes the user's emotional state, and if anxiety or hesitation is detected, it displays a message on the device saying, "Please reconsider your current financial situation before purchasing." This encourages the user to make a more rational decision.

[0630] An example of a prompt to input into the generating AI model is: "The user is currently feeling anxious about spending. Please provide appropriate advice considering their current financial situation."

[0631] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0632] Step 1:

[0633] Financial information is entered on the user's terminal through everyday transaction activities. Users input data on revenue, expenses, and assets, which is collected by the terminal's control program. This information is formatted as data packets and sent to the server. Input is numerical data, and output is appropriately formatted data packets.

[0634] Step 2:

[0635] The server stores the received data packets in a storage service such as AWS S3. This data is then decoded using a Python script and prepared for the next analysis step. The input is data packets from the terminal, and the output is a data stream in a parseable format.

[0636] Step 3:

[0637] The server begins analyzing the integrated data using Python and TensorFlow. First, machine learning algorithms predict and analyze the information, thereby enabling future revenue and expenditure forecasts and investment risk assessments. The input is integrated data of numerical and non-numerical data, and the output is the prediction and analysis results based on this data.

[0638] Step 4:

[0639] The server activates an emotion engine to analyze emotional data obtained from user input. Here, it rapidly analyzes the user's emotional responses and generates personalized suggestions and warnings based on their state. The input is non-numerical data obtained from user behavior, and the output is feedback messages based on the user's emotional state.

[0640] Step 5:

[0641] Suggestions and warnings generated on the server are sent to the terminal's display device. The terminal visualizes this using a user interface built with React Native. The input is instruction data from the server, and the output is an intuitive message presented to the user.

[0642] Step 6:

[0643] Users make decisions based on the information presented. This feedback is collected again, sent to the server, and used for future predictive models. The input is user feedback, and the output is continuous data updates aimed at improving the machine learning model.

[0644] 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.

[0645] 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.

[0646] 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.

[0647] [Fourth Embodiment]

[0648] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0649] 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.

[0650] 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).

[0651] 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.

[0652] 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.

[0653] 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).

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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".

[0661] The system of the present invention aims to efficiently integrate financial and non-financial data provided by users and to perform advanced analysis and predictions based on that data. This system is primarily implemented with the involvement of three entities: a server, a terminal, and a user.

[0662] First, users upload financial information to the server via their devices. This information includes revenue and expense history, and details of assets and liabilities. In addition, the server collects non-financial data from the internet. This non-financial data includes economic indicators, industry trends, and news reports.

[0663] Next, the server integrates these different datasets. Data cleaning and preprocessing are performed, removing unnecessary data, imputing missing values, and standardizing data formats. This process ensures consistency across each dataset, laying the foundation for analysis.

[0664] The server then analyzes the data using machine learning techniques. The server has the ability to run models such as sales forecasts and investment risk assessments, thereby improving the accuracy of predictions. For example, it can use regression analysis to forecast next year's sales or classification algorithms to assess investment risk.

[0665] The analysis results are sent from the server to the terminal and displayed in a format accessible to the user. The terminal visualizes the information in a dashboard format, providing an intuitive user experience. This allows users to easily understand complex datasets and use them to inform their decision-making.

[0666] Furthermore, the server also utilizes natural language processing technology to extract useful information from non-financial data. The server extracts keywords from news articles and reports and uses them to provide users with new insights.

[0667] Finally, the server continuously optimizes its machine learning model based on user feedback. This will enable more accurate predictions in the future, allowing it to respond to user requests more quickly and precisely.

[0668] In this way, the system of the present invention functions as a powerful tool for users to perform advanced and comprehensive financial analysis and make rational decisions based on it.

[0669] The following describes the processing flow.

[0670] Step 1:

[0671] Users upload financial information to the server using their devices. The data is typically in CSV or Excel file format, making data entry easy.

[0672] Step 2:

[0673] The server automatically collects non-financial data such as economic indicators and news articles via the internet. This data is obtained using APIs or web scraping.

[0674] Step 3:

[0675] The server integrates uploaded financial information with collected non-financial data. Data cleaning is performed to remove duplicate data and fill in missing data.

[0676] Step 4:

[0677] The server uses machine learning models to analyze data. For example, it uses regression analysis to predict sales trends and classification algorithms to evaluate investment risk.

[0678] Step 5:

[0679] The server uses natural language processing technology to extract useful information from non-financial data. It extracts keywords from news articles and identifies important market trends.

[0680] Step 6:

[0681] The server generates analysis results and sends them to the terminal. The results are visualized in a dashboard format and presented to the user as graphs and tables.

[0682] Step 7:

[0683] Users refer to the dashboard on their device to evaluate the analysis results and make decisions. The dashboard has an intuitive interface and is designed to allow users to quickly grasp the information they need.

[0684] Step 8:

[0685] Users take actions based on the analysis results and provide the system with feedback on the outcomes.

[0686] Step 9:

[0687] The server incorporates user feedback, adjusts the parameters of the machine learning model, and improves the accuracy of future predictions.

[0688] (Example 1)

[0689] 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".

[0690] In today's business environment, there is a demand for the rapid integration of data from multiple sources and for advanced analysis based on this data. However, efficiently integrating financial and non-financial data and performing consistent analysis is technically challenging. Furthermore, optimizing models to reflect user feedback is not easy, and there is a need to improve prediction accuracy. To solve these challenges, it is necessary to automate information aggregation and analysis to improve prediction accuracy and usability.

[0691] 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.

[0692] In this invention, the server includes means for acquiring financial information from users via an information processing device and integrating and preprocessing the information; means for performing predictions and analyses based on the input information using computer learning methods; means for visually presenting and notifying the analysis results through a user interface; means for optimizing the computer learning model using feedback generated by the user to improve prediction accuracy; means for actively collecting information from external information sources and integrating the information into the analysis; and means for ensuring consistency between each dataset and converting the data into a unified format. This enables the integration and centralized management of diverse information, leading to improved accuracy in practical predictions and analyses, and the realization of highly adaptable models that utilize user feedback.

[0693] An "information processing device" is a device that receives data from a user and performs necessary data preprocessing.

[0694] "Financial information" is a general term for data that represents a company's financial situation, including revenue, expenses, assets, and liabilities.

[0695] "Computer learning techniques" are technologies in which computers learn patterns using large amounts of data and then use that information to make predictions and perform analyses.

[0696] A "user interface" is a general term for the display and operating devices that allow computers and humans to exchange information.

[0697] "Feedback" refers to evaluations and improvement suggestions provided by users, which are used to improve the system.

[0698] "External information sources" refer to information obtained from outside the company, such as economic indicators and news found on the internet.

[0699] "Consistency" means that there are no inconsistencies between different datasets, and that a consistent data state is maintained.

[0700] A "unified format" is a means of standardizing analytical processing by converting data provided in different formats into a consistent format.

[0701] The embodiment for carrying out this invention is a system composed of three entities: a user, a terminal, and a server. This system performs predictions and analyses based on financial information provided by the user, and provides the results to the user in a visualized format.

[0702] First, the user sends financial information to the server via their device. The device provides an interface for uploading information on revenue, expenses, assets, and liabilities in Excel or CSV file formats. The device features a user-friendly UI and seamlessly transfers the entered information to the server.

[0703] Next, the server integrates the received financial information with non-financial data collected from external sources. This process uses the Python Pandas library and includes cleaning operations such as imputing missing values, standardizing data formats, and deleting unnecessary data to ensure data integrity. The server also collects the latest economic indicators, market trends, and news reports via the internet using APIs and web scraping.

[0704] After the data is integrated, the server performs data analysis using computer learning techniques. Utilizing the Python Scikit-learn library, it performs regression analysis and classification algorithms to predict sales and assess investment risk. This entire process is designed to be intuitive for the user; for example, a prompt using the generative AI model can be entered as, "Please predict sales for a specific product category next year."

[0705] Finally, the analyzed results are sent from the server to the terminal. The terminal displays the results in graph and chart format using visualization libraries such as D3.js. This allows users to visually understand the analysis results and use them to make decisions. Furthermore, based on feedback provided by the user, the server continuously optimizes the machine learning model to improve prediction accuracy.

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] Users transmit financial information to the server via their terminal. The input consists of revenue, expense, asset, and liability information contained in Excel or CSV files. The terminal receives this data and uploads it to the server. During this process, the terminal performs a format check to ensure the accuracy of the input.

[0709] Step 2:

[0710] The server receives uploaded financial information and collects non-financial data from external sources. It uses economic indicators and news reports obtained via APIs as input. The server uses the Python Pandas library to clean the data, removing duplicates and imputing missing values. This ensures data consistency and integrates it into a format suitable for analysis.

[0711] Step 3:

[0712] The server performs computational learning based on integrated data. It uses cleaned financial and non-financial data as input. The server utilizes the Scikit-learn library to perform regression analysis and predict sales. It also applies classification algorithms to assess investment risk. The output includes numerical data for prediction results and risk assessment.

[0713] Step 4:

[0714] The server sends the analysis results to the terminal. The generated prediction results and risk assessment data are used as input. The terminal uses the D3.js library to visualize these results. The terminal displays the data in graphs and charts for easy understanding by the user, supporting their decision-making.

[0715] Step 5:

[0716] Users provide feedback to the server based on the analysis results. The server uses user comments and specific improvement suggestions as input. Based on this feedback, the server optimizes the generated AI model. Prompts such as "Please further improve prediction accuracy" are used. This improves accuracy in subsequent data analyses and enhances overall system performance.

[0717] (Application Example 1)

[0718] 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".

[0719] In modern society, users are expected to acquire information on a daily basis and engage in wise consumer behavior. However, amidst a vast amount of economic information and fluctuating price trends, it is difficult for individual users to determine the optimal timing for purchases and savings plans. Traditional methods lacked real-time information acquisition and analysis, and were insufficient to support users' decision-making. Furthermore, determining the optimal purchase time for a particular product in light of price fluctuations is a challenging task.

[0720] 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.

[0721] In this invention, the server includes means for acquiring economic information from the user and integrating and processing the information as needed, means for performing trend prediction and analysis based on the input information using machine learning technology, and means for visualizing and warning the analysis results through an information display device. This enables the user to receive real-time information analysis and optimal savings plans. Furthermore, by evaluating price trends of specific products and notifying consumers of the appropriate timing for purchase, consumers can engage in more efficient and wiser consumer activities.

[0722] "Economic information" refers to data related to a user's consumption and spending, including consumption history, income, spending, and other financial information.

[0723] "Integration" is the process of unifying data obtained from multiple different sources and compiling it into a consistent format.

[0724] "Processing" refers to the process of shaping acquired data into a format suitable for analysis and prediction, removing unnecessary data, and imputing missing values.

[0725] "Machine learning technology" is a technique in which computers automatically identify patterns based on large amounts of data and use that information to support predictions and decision-making.

[0726] "Trend forecasting" is a method of predicting future economic activity and price trends based on past data.

[0727] "Analysis" is the process of conducting detailed evaluations and examinations based on data, and deriving insights from those evaluations.

[0728] An "information display device" is a hardware and software system that allows users to visually confirm the results of data analysis.

[0729] "Visualization" is the process of representing analysis results using visual aids such as graphs and charts, and providing them in a way that is easy for users to understand.

[0730] "Warning" refers to a notification function that clearly informs users of important situations or changes.

[0731] "Non-economic data" refers to information about factors other than economics, and may include social, environmental, and cultural factors.

[0732] "Spending trends" refer to patterns and developments related to users' spending habits, and enable future predictions based on these trends.

[0733] A "savings plan" is a method that provides users with specific guidelines and steps to reduce waste and make efficient use of resources.

[0734] "Price trends" refer to patterns or flows that show how the price of a particular product or service changes over time.

[0735] "Purchase timing" refers to the most opportune time for consumers to buy a particular product or service, and is determined based on price and market conditions.

[0736] To implement this invention, a server, a terminal, and a user must cooperate to form a system. The server plays a central role, aggregating economic and non-economic information. Users provide information about their income and expenses via the terminal. The server receives this information and preprocesses the data as needed.

[0737] Data preprocessing involves removing unnecessary data, imputing missing values, and ensuring consistent data formats. This prepares the aggregated data for machine learning. The server uses machine learning techniques, specifically Scikit-Learn, to predict future spending trends and price movements based on economic information. The analysis results are displayed to the user in a dashboard format on their terminal.

[0738] Furthermore, the server uses natural language processing techniques to analyze non-economic data, such as news articles. This provides new insights that may influence the user. Libraries such as TextBlob are used for text analysis. Through this process, the server suggests optimal purchase times and savings plans for specific products to the user.

[0739] For example, when a user is about to purchase a particular product, the server can predict relevant price fluctuations and provide specific advice such as, "There's a discount sale this month, so you can buy it at a good price." In this way, users can engage in economical and efficient consumer activities.

[0740] As an example of a prompt, you can input a request such as, "Please predict my spending for the next three months and suggest possible savings plans," and then use the generative AI model to obtain the analysis results.

[0741] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0742] Step 1:

[0743] Users send financial information, including income and expenses, to the server via their devices. This allows the financial data to be aggregated on the server. The server stores the received information in a database and prepares it for further processing.

[0744] Step 2:

[0745] The server collects non-economic data via the internet. This data includes general trends and economic news. The collected data is processed using a natural language processing library to extract relevant keywords. The results are stored in a database, preparing it to provide information that users may find interesting.

[0746] Step 3:

[0747] The server preprocesses the aggregated economic information. This stage involves removing unnecessary data and imputing missing values. Specifically, it standardizes the data format and performs data cleansing. This process generates a clean dataset that can be used by machine learning models.

[0748] Step 4:

[0749] The server analyzes processed data using machine learning models. It leverages Scikit-Learn to predict future spending trends and price movements. Historical consumption data is used as input, and the output generates predictions of purchasing patterns and specific suggestions.

[0750] Step 5:

[0751] The server sends the analysis results to the terminal and provides them to the user in a visualized format. The terminal displays a dashboard on its display device, making it easy for the user to understand intuitively. Information is presented using specific graphs and notification messages.

[0752] Step 6:

[0753] Users review the information provided from their devices and use it as a reference for specific consumer behavior. They also send feedback from their devices to the server, which helps evaluate the analysis results and improve the model for future use.

[0754] 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.

[0755] This invention is a system that efficiently integrates financial and non-financial data and incorporates an emotion engine to analyze and recognize user emotions, thereby providing more personalized analysis results and suggestions. Embodiments of this system primarily consist of a server, terminals, and users.

[0756] First, users upload financial information to the server via their devices. This includes data such as revenue, expenses, and assets. In addition, the server retrieves non-financial data from the internet. This consists of external information such as economic indicators and news.

[0757] The server integrates the received financial and non-financial data and analyzes the data using machine learning techniques. For example, it runs models to perform sales forecasts and risk assessments, and provides strategic insights based on the results.

[0758] Furthermore, the server is equipped with an emotion engine that analyzes user input and responses through the user interface to recognize emotions. This enables the presentation of information tailored to the user's mental state. For example, in a stressful situation with high investment risk, it can output reassuring messages to encourage calm decision-making.

[0759] The device receives analysis results from the server and personalized content tailored to the user's emotional state, which is then intuitively visualized through a dashboard. This allows users to review analysis results that resonate with their own emotions and decide on their next course of action.

[0760] Furthermore, the server records a history of user emotions and continuously uses this information to optimize the user experience. By analyzing past emotional data, it is possible to understand how users felt and responded in different situations, and use this information to inform future suggestions.

[0761] Thus, the system of the present invention supports more effective decision-making and functions in a way that meets individual needs by analyzing the user's financial information and providing insights that correspond to the user's emotional state.

[0762] The following describes the processing flow.

[0763] Step 1:

[0764] Users upload financial information to the server using their devices. This information includes numerical data such as revenue, expenses, and assets, as well as related text files.

[0765] Step 2:

[0766] The server collects non-financial data via the internet. This includes economic indicators, industry news, and general market trends. Data collection is performed using APIs and scraping techniques.

[0767] Step 3:

[0768] The server integrates and cleans the collected financial and non-financial data. It standardizes data formats and imputes missing values ​​to prepare the data for analysis.

[0769] Step 4:

[0770] The server begins analyzing data using a machine learning model. It forecasts sales and assesses investment risks, generating analytical results based on these findings.

[0771] Step 5:

[0772] The server uses an emotion engine to analyze user input and reactions obtained from the user interface and recognize the user's emotional state.

[0773] Step 6:

[0774] Based on the results from the emotion engine, the server adjusts the displayed analysis and suggestions according to the user's emotional state. For example, if the user is feeling stressed, it prioritizes displaying information that provides a sense of reassurance.

[0775] Step 7:

[0776] The device displays the optimized analysis results and suggestions to the user via a user interface. The dashboard includes visually organized graphs and reports.

[0777] Step 8:

[0778] Users review the displayed dashboard and make decisions as needed. Based on the suggestions and information presented, users can decide on specific actions.

[0779] Step 9:

[0780] The system receives feedback on the actions taken by the user and their emotional responses to those actions.

[0781] Step 10:

[0782] Based on the feedback, the server readjusts the parameters of the machine learning model and emotion engine to optimize prediction accuracy and user experience.

[0783] (Example 2)

[0784] 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".

[0785] In modern information technology, the analysis of numerical information and decision support play crucial roles in various fields. However, conventional systems are specialized in the analysis of numerical information, making it difficult to provide personalized information that takes into account the emotional state of the user. Furthermore, there is a lack of mechanisms to utilize past history in order to improve the accuracy of information and accurately predict the future needs of users. Thus, there is a demand for providing effective decision support to users and solutions that meet their individual needs.

[0786] 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.

[0787] In this invention, the server includes means for acquiring numerical information from the user and integrating and preprocessing the information as necessary, means for performing estimation and evaluation based on the input information using a machine learning algorithm, and means for visualizing and notifying the evaluation results through a display device. This enables data analysis that takes into account the user's emotional state and the provision of personalized information.

[0788] "User" refers to an individual who uses the system to provide numerical information and receives the results.

[0789] "Numerical information" refers to information that includes financial data such as revenue, expenses, and assets.

[0790] A "server" refers to a computer system that receives, processes, and analyzes data from users.

[0791] A "machine learning algorithm" refers to a computational method or model that uses data to make predictions and perform analyses.

[0792] "Estimation and evaluation" refers to predictions and their analysis results calculated using machine learning algorithms based on the input numerical information.

[0793] A "display device" refers to a device used to present information to a user in a visual or other format.

[0794] "Visualization" means presenting analysis results in a visual form, such as diagrams or graphs, to make them easier for users to understand.

[0795] "Emotional state" refers to the psychological and emotional state inferred from the user's input and responses.

[0796] "History" refers to records of information that users have provided in the past, as well as feedback received from the system at that time.

[0797] "Non-numerical data" refers to data that represents information other than numerical values, such as text and news articles, and is analyzed by a system.

[0798] This invention is a system that efficiently integrates numerical and non-numerical data of users and performs sentiment analysis to provide more personalized analysis results and suggestions. This system mainly consists of a server, terminals, and users.

[0799] The server plays a central role in processing numerical and non-numerical data. It receives financial data such as revenue, expenses, and assets transmitted from users via their devices. This data is retrieved via the HTTP protocol and securely stored in a database. The server also uses APIs to retrieve non-numerical data such as economic indicators and news from the internet.

[0800] For data integration and analysis, we will use the Python Pandas library. Pandas allows for efficient merging of numerical and non-numerical data using dataframes. As for machine learning algorithms, we will use TensorFlow and PyTorch to run predictive models and make predictions and evaluations about users' financial situations.

[0801] The system utilizes natural language processing (NLP) technology for emotion analysis. Specifically, it analyzes user input data and uses an emotion engine to infer the user's emotional state. This allows for the provision of customized information tailored to the user's mental state.

[0802] The terminal is a device that visually displays the analysis results received from the server. Using the JavaScript library D3.js, it generates intuitive graphs and charts on the dashboard, presenting information to the user in an easy-to-understand manner.

[0803] Furthermore, the server records the user's past activity history and emotional responses, and uses this information to optimize future suggestions. This enables personalized suggestions for each user.

[0804] As a concrete example, here is an example of a prompt message: "Based on the latest revenue data and economic news, forecast business growth and propose measures to address user concerns."

[0805] Thus, the present invention functions to support more effective decision-making by performing comprehensive information processing based on the user's numerical information and emotions.

[0806] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0807] Step 1:

[0808] Users upload their financial data using their device. The input is, for example, a CSV file containing revenue, expense, and asset information. When a dedicated upload button on the device is clicked, the file is sent to the server, which receives this data via the HTTP protocol and stores it in the database.

[0809] Step 2:

[0810] The server uses APIs to collect the latest non-numerical data from the internet. The input data consists of economic indicators and news articles, which are retrieved in JSON format. The data is processed in real time and stored in the server's database. This step involves making requests to external APIs and storing the response data.

[0811] Step 3:

[0812] The server integrates financial and non-numerical data using the Pandas library. The input data consists of the information collected in steps 1 and 2. This integration process merges dataframes with common key items to create a consistent dataset. The output is the integrated dataset.

[0813] Step 4:

[0814] The server executes machine learning algorithms on the integrated dataset. The input is the integrated dataset, and the model used is a pre-trained model using TensorFlow. This model is used to predict sales and assess risks, and the output is these analytical results.

[0815] Step 5:

[0816] The server uses natural language processing technology to analyze the user's emotions. The input is text data from the user. The emotion analysis engine classifies the text and infers the user's emotional state. The output is information about the user's emotional state.

[0817] Step 6:

[0818] The server generates personalized information based on the results of machine learning analysis and sentiment analysis. The input is the output from steps 4 and 5, which are used to construct textual content such as investment advice or risk management strategies.

[0819] Step 7:

[0820] The terminal displays personalized information received from the server. The input is information from the server, and a JavaScript library is used to generate interactive graphs and charts, which are then visually presented on the dashboard. The output is the visual information displayed on the user's screen.

[0821] Step 8:

[0822] The server records the user's behavior history and emotional data. The input is the user's past interaction history. This history is stored in a database and used to continuously optimize the user experience.

[0823] (Application Example 2)

[0824] 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".

[0825] Modern electronic payment systems are not adequately capable of managing users' financial situations while providing personalized suggestions and warnings. In particular, there is a need for decision-making support that takes into account users' emotional states. Current technologies make decisions based solely on financial information, making it difficult to provide optimal support for users. Furthermore, there is a lack of advanced prediction and suggestions that utilize emotional data, and these challenges need to be addressed.

[0826] 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.

[0827] In this invention, the server includes means for acquiring numerical information from the user and integrating and processing the information as necessary; means for performing predictions and analyses based on the input information using machine learning techniques; and means for generating personalized suggestions and warnings based on the analyzed sentiment data. This enables users to make appropriate decisions tailored to their emotional state and manage resources more safely and effectively.

[0828] "Numerical information" refers to quantitative data related to finance, including money, assets, revenue, and expenses.

[0829] "Machine learning technology" is a general term for algorithms and methods used to learn patterns and relationships from large amounts of data and perform predictions and analyses.

[0830] "Analyzed emotional data" refers to data indicating the emotional state, extracted by the emotion engine based on the user's input and responses.

[0831] "Personalized suggestions and warnings" refer to advice and alerts that are uniquely customized to the user's specific situation or emotional state.

[0832] A "presentation device" is a device or interface used to provide users with analysis results or suggestions visually or audibly.

[0833] "Natural language processing technology" refers to the technologies and methods used by computers to understand, interpret, and generate human language.

[0834] "Real-time updates" refers to a process where data is instantly collected and processed the moment it is generated, and the analysis results are immediately reflected.

[0835] To implement this invention, a system consisting of a user terminal, a server, and an external information source is configured. The user accesses an electronic payment platform they use on a daily basis and manages and updates their financial information through the terminal. The terminal collects numerical information such as the user's current assets, revenue, and expenses, and transmits it to the server.

[0836] The server is built on a cloud platform (e.g., AWS S3), and the backend is built using Python and Django. Machine learning techniques are implemented here, for example, running a sentiment analysis model using TensorFlow. The server integrates and analyzes numerical information received from users with non-numerical data obtained from external information services. This analysis enables predictions based on the user's financial situation and generates personalized suggestions and warnings based on sentiment data.

[0837] The analysis results are transmitted to the terminal's display device and intuitively visualized for the user through a user interface utilizing React Native. This allows users to receive decision-making support based on their own emotional state and financial situation.

[0838] As a concrete example, consider a situation where a user is about to purchase an expensive item while online shopping. In this case, the server's emotion engine analyzes the user's emotional state, and if anxiety or hesitation is detected, it displays a message on the device saying, "Please reconsider your current financial situation before purchasing." This encourages the user to make a more rational decision.

[0839] An example of a prompt to input into the generating AI model is: "The user is currently feeling anxious about spending. Please provide appropriate advice considering their current financial situation."

[0840] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0841] Step 1:

[0842] Financial information is entered on the user's terminal through everyday transaction activities. Users input data on revenue, expenses, and assets, which is collected by the terminal's control program. This information is formatted as data packets and sent to the server. Input is numerical data, and output is appropriately formatted data packets.

[0843] Step 2:

[0844] The server stores the received data packets in a storage service such as AWS S3. This data is then decoded using a Python script and prepared for the next analysis step. The input is data packets from the terminal, and the output is a data stream in a parseable format.

[0845] Step 3:

[0846] The server begins analyzing the integrated data using Python and TensorFlow. First, machine learning algorithms predict and analyze the information, thereby enabling future revenue and expenditure forecasts and investment risk assessments. The input is integrated data of numerical and non-numerical data, and the output is the prediction and analysis results based on this data.

[0847] Step 4:

[0848] The server activates an emotion engine to analyze emotional data obtained from user input. Here, it rapidly analyzes the user's emotional responses and generates personalized suggestions and warnings based on their state. The input is non-numerical data obtained from user behavior, and the output is feedback messages based on the user's emotional state.

[0849] Step 5:

[0850] Suggestions and warnings generated on the server are sent to the terminal's display device. The terminal visualizes this using a user interface built with React Native. The input is instruction data from the server, and the output is an intuitive message presented to the user.

[0851] Step 6:

[0852] Users make decisions based on the information presented. This feedback is collected again, sent to the server, and used for future predictive models. The input is user feedback, and the output is continuous data updates aimed at improving the machine learning model.

[0853] 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.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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."

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] The following is further disclosed regarding the embodiments described above.

[0875] (Claim 1)

[0876] A means for obtaining financial information from users and integrating and processing that information as needed,

[0877] A means of performing predictions and analyses based on input information using machine learning technology,

[0878] Means for visualizing and notifying analysis results through a user interface,

[0879] A system that includes means for updating a machine learning model using generated feedback to improve prediction accuracy.

[0880] (Claim 2)

[0881] The system according to claim 1, which extracts useful information from non-financial data using natural language processing technology.

[0882] (Claim 3)

[0883] The system according to claim 1, which updates and analyzes financial information in real time and provides the analysis results and suggestions as needed.

[0884] "Example 1"

[0885] (Claim 1)

[0886] A means for acquiring financial information from a user via an information processing device, and for integrating and pre-processing the relevant information,

[0887] A means for performing predictions and analyses based on input information using computer learning techniques,

[0888] A means of visually presenting and notifying the analysis results through a user interface,

[0889] A means to optimize a computer learning model using user-generated feedback and improve prediction accuracy,

[0890] A means of actively collecting information from external sources and integrating that information into analysis,

[0891] A means to ensure consistency between each dataset and to convert the data into a unified format,

[0892] A system that includes this.

[0893] (Claim 2)

[0894] The system according to claim 1, which uses language analysis techniques to extract useful information from non-financial data.

[0895] (Claim 3)

[0896] The system according to claim 1, which dynamically updates and analyzes financial information and continuously provides the results of that analysis and suggestions.

[0897] "Application Example 1"

[0898] (Claim 1)

[0899] A means for obtaining economic information from users and integrating and processing that information as needed,

[0900] A means for performing trend prediction and analysis based on input information using machine learning technology,

[0901] Means for visualizing and warning about analysis results through an information display device,

[0902] A means of updating machine learning models using generated opinions to improve prediction accuracy,

[0903] A method for extracting useful information from non-economic data using natural language processing technology and proposing savings plans based on spending trends,

[0904] A method to analyze price trends of specific products and notify users of the optimal purchase timing.

[0905] A system that includes this.

[0906] (Claim 2)

[0907] The system according to claim 1, which updates and analyzes economic information in real time and provides the analysis results and optimal savings plans as needed.

[0908] (Claim 3)

[0909] The system according to claim 1, which evaluates the price trends of specific goods or services and notifies the optimal time for purchase.

[0910] "Example 2 of combining an emotion engine"

[0911] (Claim 1)

[0912] A means for obtaining numerical information from users and integrating and preprocessing that information as needed,

[0913] A means for performing estimation and evaluation based on input information using machine learning algorithms,

[0914] Means for visualizing and notifying evaluation results through a display device,

[0915] A means of updating the machine learning module using the generated feedback to improve estimation accuracy,

[0916] A means of analyzing the user's emotions and providing corresponding information,

[0917] A system that includes means to record user history and optimize future suggestions.

[0918] (Claim 2)

[0919] The system according to claim 1, which extracts useful information from non-numerical data using language processing techniques.

[0920] (Claim 3)

[0921] The system according to claim 1, which instantly updates and evaluates numerical information and provides the evaluation results and suggestions as appropriate.

[0922] "Application example 2 when combining with an emotional engine"

[0923] (Claim 1)

[0924] A means for obtaining numerical information from users and integrating and processing that information as needed,

[0925] A means of performing predictions and analyses based on input information using machine learning technology,

[0926] A means of generating personalized suggestions and warnings based on analyzed sentiment data,

[0927] Means for visualizing and notifying analysis results through a presentation device,

[0928] A means of updating a machine learning model using the generated feedback to improve prediction accuracy,

[0929] A method of analyzing past emotional data and using it to make future suggestions.

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, which uses natural language processing techniques to extract useful information from non-numerical data.

[0933] (Claim 3)

[0934] The system according to claim 1, which updates and analyzes numerical information in real time and provides the analysis results and suggestions as they occur. [Explanation of Symbols]

[0935] 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 obtaining economic information from users and integrating and processing that information as needed, A means for performing trend prediction and analysis based on input information using machine learning technology, Means for visualizing and warning about analysis results through an information display device, A means of updating machine learning models using generated opinions to improve prediction accuracy, A method for extracting useful information from non-economic data using natural language processing technology and proposing savings plans based on spending trends, A method to analyze price trends of specific products and notify users of the optimal purchase timing. A system that includes this.

2. The system according to claim 1, which updates and analyzes economic information in real time and provides the analysis results and optimal savings plans as needed.

3. The system according to claim 1, which evaluates the price trends of specific goods or services and notifies the optimal time to purchase them.

Images