system

Abstract

We provide a system that quickly acquires useful information from corporate data and external data, and performs real-time data analysis based on this information. [Solution] A system comprising: means for collecting corporate data from an internal database and external data from external data sources as data collection means; data preprocessing means for cleansing the collected raw data and converting it into features; real-time data analysis means for analyzing the preprocessed data and extracting business-related insights; predictive analysis means for predicting future market trends and corporate performance using machine learning models and proposing scenarios; decision support means for presenting insights in real time during meetings and proposing agenda items; and trend analysis means for analyzing past records and proposing future agenda items.

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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern corporate environment, quick and accurate decision-making is essential to maintain a competitive edge. However, many companies are overwhelmed by vast amounts of data and are struggling to formulate effective strategies. In particular, there are major challenges in real-time data analysis, future prediction, and appropriate issue selection. Such situations may cause companies to reduce the quality of their decision-making.

Means for Solving the Problems

[0005] This invention provides a system that rapidly acquires useful information from corporate and external data and performs real-time data analysis based on this information. Furthermore, it predicts future market trends and corporate performance through predictive analytics using machine learning models. In addition, it proposes appropriate agenda items by providing decision support during meetings so that users can gain important insights. In this way, the invention provides a system that enables companies to make effective data-driven decisions quickly.

[0006] "Data collection means" refers to technologies and devices for acquiring necessary data from internal databases and external data sources.

[0007] "Data preprocessing means" refers to technologies and devices that perform the processing of cleansing collected raw data and converting it into features.

[0008] "Real-time data analysis means" refers to technologies and devices for instantly extracting business-related insights from pre-processed data.

[0009] "Predictive analytics tools" refer to technologies and devices that use machine learning models to predict future market trends and corporate performance, and to propose scenarios.

[0010] "Decision-making support tools" are technologies and devices that provide users with real-time insights during meetings and assist in selecting appropriate agenda items.

[0011] "Trend analysis tools" are technologies and devices used to propose future agenda items based on past decision-making history and industry trends. [Brief explanation of the drawing]

[0012] [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] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a processor with a reference numeral (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.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention describes an AI-powered business support system that effectively assists corporate decision-making. The system includes functions for data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, and trend analysis.

[0034] Data collection

[0035] The server periodically extracts financial, sales, and customer data from the company's internal databases, and retrieves data from external data sources on a scheduled basis. Data types include news articles, social media posts, and industry reports.

[0036] Data preprocessing

[0037] The server cleanses the collected raw data, imputing missing values ​​and removing outliers. Following this, it generates features suitable for analysis by the AI ​​model, such as converting text data into numerical vectors. This process prepares the dataset, improving the accuracy of subsequent analyses.

[0038] Real-time data analysis

[0039] The server feeds pre-processed data into an AI model, instantly extracting business-relevant insights. This makes it possible to instantly grasp, for example, market share fluctuations or customer satisfaction.

[0040] Predictive analysis

[0041] The server uses machine learning models to predict future market trends and corporate performance that are useful for corporate strategy and decision-making. Specifically, it forecasts sales for the next fiscal year and evaluates new products in the market, and provides optimal strategies based on these results.

[0042] decision support

[0043] The device provides users with real-time insights during board meetings and management conferences. It also improves meeting efficiency by having AI analyze and suggest important agenda items. Users can input new questions as needed and receive instant answers.

[0044] Trend Analysis

[0045] The server integrates and analyzes past decision-making history and industry trend data. Based on this, it suggests topics that should be prioritized for discussion at the next meeting, helping participants to be better prepared.

[0046] For example, if a manufacturer is considering entering a new market, the server can instantly analyze market trend data, customer feedback, and the competitive landscape, and present the user with the optimal timing and strategy for entry via a terminal. In this way, decision-makers at the company can make quick, data-driven, and effective decisions.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server periodically extracts relevant corporate data from the company's internal database and collects various market data from external data sources via APIs. This includes news articles, social media posts, and industry reports.

[0050] Step 2:

[0051] The server cleanses the collected data. Specifically, it imputes missing values ​​and detects and removes outliers. It also standardizes the data format and converts text data into numerical vectors to extract features necessary for AI analysis.

[0052] Step 3:

[0053] The server feeds pre-processed data into an AI model and performs real-time data analysis. Here, important company metrics such as market share and sales trends are instantly visualized.

[0054] Step 4:

[0055] The server performs predictive analysis using machine learning models based on the analysis results. This generates scenarios for future market trends and product demand, creating materials for formulating optimal business strategies.

[0056] Step 5:

[0057] The terminal presents users with analysis results and predictive scenarios during board meetings and management conferences. It responds to user questions in real time and presents data-driven agenda items provided by AI.

[0058] Step 6:

[0059] The server analyzes the latest industry trend data based on past meeting records and decision-making history. This allows it to identify and suggest key topics that should be prioritized for discussion in the next meeting.

[0060] (Example 1)

[0061] 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."

[0062] In modern business management, effective decision-making based on vast amounts of internal and external data is essential. Achieving this requires a system that seamlessly handles data acquisition, preprocessing, analysis, and immediate delivery of results. However, traditional methods fragment these processes, making real-time decision-making support difficult. This hinders quick and accurate judgment, forcing many managers to waste time and resources.

[0063] 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.

[0064] In this invention, the server includes, as a data collection means, a mechanism for acquiring organizational data from an internal database and external data from an external data source; a data processing mechanism for purifying the acquired raw data and converting it into a numerical representation; and a data analysis mechanism for analyzing the processed data and immediately extracting business-related insights. This enables organizations to support real-time, precise data-driven decision-making and enhance their competitiveness.

[0065] A "data collection method" is a mechanism for extracting organizational data from an internal database and acquiring external data from external data sources.

[0066] A "data processing mechanism" is a method for purifying acquired raw data and converting it into a numerical representation.

[0067] A "data analysis mechanism" is a process for analyzing processed data and immediately extracting business-related insights.

[0068] A "predictive mechanism" is a system that uses learning models to predict future market changes and organizational performance, and to provide strategies based on those predictions.

[0069] The "decision-making support mechanism" is a process that presents insights and provides agenda items in real time during a meeting.

[0070] A "trend analysis mechanism" is a method for analyzing past history and providing future agenda items.

[0071] A "display surface" is an interface that provides information in response to user inquiries.

[0072] The present invention is a business intelligence system for supporting organizational decision-making, enabling effective decision-making through data collection, processing, analysis, and prediction. The following describes embodiments for carrying out this invention.

[0073] The system consists of servers, terminals, and users, each performing data processing according to its role. The servers function as data collection tools, periodically extracting financial data, sales information, and customer relationship data from the organization's databases. In addition, information from external data sources, such as news articles and social media, is collected using technologies like APIs and web scraping. This forms a broad information base necessary for decision-making.

[0074] The collected data is cleansed by a data processing mechanism on the server. Specifically, missing values ​​and outliers are removed using libraries such as Pandas and NumPy in the Python language. In addition, natural language processing is performed using NLTK and spaCy to convert text data into numerical representations, creating a dataset that can be analyzed by AI models. This improves data quality and increases the accuracy of the analysis.

[0075] The server inputs pre-processed data into an AI model and performs data analysis in real time. This analysis uses learning frameworks such as TENSORFLOW® and PyTorch to clarify market trends and customer segmentation based on features extracted from the data. Subsequently, time series analysis and regression models are used to estimate future sales and market changes using a prediction mechanism. This process has a significant impact on a company's strategy formulation and risk management.

[0076] The terminal acts as a decision support mechanism, providing users with immediate analysis results. This involves using data visualization tools such as Tableau and Power BI to create an environment where users can intuitively view the data. Users can input prompts as needed to elicit responses from the generated AI model.

[0077] For example, if a user enters a prompt such as, "Forecast next quarter's sales and tell me the optimal time to enter a new market," the system can analyze the relevant data and provide appropriate action suggestions. This allows users to make quick, data-driven decisions.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server accesses internal databases and external data sources for data collection. Inputs include corporate financial information, sales statistics, customer data, and data from external news articles and social media. The server utilizes APIs and scraping techniques to collect this data and outputs it as a standardized dataset. This collection process is performed regularly to ensure the completeness and timeliness of the information.

[0081] Step 2:

[0082] The server performs data preprocessing. It receives the unified formatted dataset output in step 1 as input. Specific actions include cleaning the raw data using Pandas and NumPy. After imputing missing values ​​and removing outliers, the data is converted into a format usable by the AI ​​model (e.g., numerical vectors). As a result, the system outputs the formatted dataset to the next processing step.

[0083] Step 3:

[0084] The server performs real-time data analysis. By using pre-processed data from Step 2 as input, it feeds it into an AI model (using TensorFlow or PyTorch) to instantly extract business-related insights. Specifically, this involves identifying customer segments and understanding market trends. The resulting insights are provided as output, forming the foundation for the next steps.

[0085] Step 4:

[0086] The server performs predictive analytics. Using the insights obtained in Step 3 as input, it uses a learning model to predict future market trends and organizational performance. Here, methods such as time series analysis and linear regression are employed. The output is predicted sales and market trends, which serve as foundational information for strategic planning.

[0087] Step 5:

[0088] The terminal provides decision support to the user. Output data from the server is used as input for visualization in Tableau and Power BI. The user can view this in real time and, if necessary, enter prompts to obtain more detailed analysis results. Specifically, prompts such as "Forecast next quarter's sales and tell me the optimal time for entering new markets" are used. As a result, concrete insights are presented to the user.

[0089] Step 6:

[0090] The server performs trend analysis. It analyzes past decision-making history and industry trend data as input and proposes future agenda items. Here, data mining techniques are used to compare past and present data and automatically suggest priority agenda items for the next meeting. This provides users with the information they need to strategically plan.

[0091] (Application Example 1)

[0092] 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."

[0093] In today's business environment, it is necessary to quickly interpret large amounts of data and utilize it for decision-making, but there is a lack of appropriate support systems for this purpose. Furthermore, there is a demand for real-time information based on individual consumer behavior and market trends, but no system exists that can efficiently achieve this.

[0094] 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.

[0095] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables companies to predict future market trends and provide personalized recommendations and real-time notifications to consumers.

[0096] "Data collection means" refers to a mechanism for obtaining necessary information from internal databases and external data sources.

[0097] "Data preprocessing means" refers to a system that has the function of cleansing collected raw data and converting it into a format suitable for analysis.

[0098] A "real-time data analysis method" is a technology that sequentially analyzes pre-processed data and immediately extracts insights relevant to business operations.

[0099] "Predictive analytics tools" are tools that use machine learning models to predict market trends and organizational performance in the future.

[0100] "Decision-making support tools" are means of supporting the decision-making process by presenting necessary analysis results and agenda items in real time during meetings.

[0101] "Trend analysis tools" are technologies that integrate historical data and market trends to propose future priority issues.

[0102] A "recommendation engine" is an algorithm that recommends products and services based on the user's behavior.

[0103] A "push notification method" is a communication method that reflects real-time market information and delivers messages directly to users.

[0104] The business support system implementing the present invention consists of multiple hardware and software components. The server acquires organizational data from internal and external data sources using data acquisition means. This data is cleansed and converted into feature vectors by data preprocessing means.

[0105] Pre-processed data is sequentially analyzed using real-time data analysis tools to extract business insights. This analysis utilizes AI models based on TensorFlow. The server also leverages machine learning models through predictive analytics tools to forecast the organization's future market trends and performance.

[0106] The device visualizes these insights and provides them to the user in real time. Furthermore, recommended products and sales information generated by the server are individually optimized by the recommendation engine and sent to the user via push notifications.

[0107] For example, when a user is online shopping, data on the products they have viewed is collected in real time, and an AI model recommends appropriate products to encourage their next purchase. A specific example is a prompt message generated and sent to the user saying, "Special offers related to items you've recently viewed are available for the upcoming big sale. Check the app for details!"

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server retrieves organizational data from internal databases and external data sources using data collection methods. Input data includes financial data, sales data, and social media posts. Output is a compilation of the collected raw data.

[0111] Step 2:

[0112] The server cleanses the raw data collected by the data preprocessing mechanism and converts it into feature vectors. The raw data obtained as input is then converted into a format suitable for analysis through missing value imputation and outlier removal. The output is a cleansed and feature-enhanced dataset.

[0113] Step 3:

[0114] The server uses real-time data analysis tools to sequentially analyze pre-processed data and extract business-related insights. The input data is analyzed using a TensorFlow-based generative AI model. The output provides insights into customer satisfaction and market share fluctuations.

[0115] Step 4:

[0116] The server leverages machine learning models through predictive analytics to forecast future market trends and performance for an organization. It receives analysis results as input and uses them to build future sales forecasts and product strategies. The output consists of predicted market trends and strategic recommendations.

[0117] Step 5:

[0118] The terminal uses decision support tools to visualize generated insights in real time and provide them to the user during the meeting. Input consists of prediction results and insights sent from the server. Output is visually represented data, allowing for quick identification of important agenda items.

[0119] Step 6:

[0120] The server also uses a recommendation engine to analyze user behavior data and generate personalized product and service information. Input data includes the user's browsing and purchase history, while output is appropriately personalized product recommendations based on that data.

[0121] Step 7:

[0122] The device notifies the user of personalized product recommendations and campaign information via push notifications. The input is product recommendations sent from the server, and the output is a notification message displayed on the user's device.

[0123] 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.

[0124] This invention relates to an AI system with enhanced capabilities to effectively support a company's decision-making process, particularly one that recognizes user emotions and incorporates them into decision-making. The system consists of data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, trend analysis, and emotion recognition.

[0125] Data collection

[0126] The server periodically collects necessary data from the company's internal databases and external data sources. This includes financial data, sales data, news articles, social media posts, and industry reports.

[0127] Data preprocessing

[0128] The server cleanses the collected data, imputing missing values ​​and removing outliers. Furthermore, it transforms the data into features in a format that the model can learn from.

[0129] Real-time data analysis and predictive analytics

[0130] The server analyzes pre-processed data using an AI model, instantly extracts key business metrics, and predicts future market trends using machine learning techniques.

[0131] decision support

[0132] The device presents users with analysis results and predictive scenarios, and also responds to real-time questions during meetings. Furthermore, the AI ​​automatically generates and presents important agenda items to users, supporting efficient decision-making.

[0133] Trend Analysis

[0134] The server analyzes past records and industry trends to suggest priority agenda items for the next meeting. This allows meeting participants to prepare more effectively.

[0135] emotion recognition

[0136] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize emotions in real time. This allows the server to adjust the agenda and approach according to the emotional state. For example, if the user shows anxiety, it will provide more information and different perspectives.

[0137] For example, when discussing the market launch of a new product during a board meeting, the server analyzes market data and suggests the optimal strategy. The terminal also monitors the user's emotional state, recommending a challenging strategy if optimistic feelings are present, and a more conservative approach if concerns are expressed. This allows for the integration of user emotions into data-driven decision-making, leading to more balanced conclusions.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server collects various corporate data from the company's internal database and retrieves market data, news articles, and social media posts from external data sources via external APIs. This creates a comprehensive dataset.

[0141] Step 2:

[0142] The server performs data cleansing on the acquired data, imputing missing values ​​and detecting and removing outliers. It converts the data format to a standard format usable by the AI ​​model and prepares it for extracting necessary features.

[0143] Step 3:

[0144] The server processes pre-processed data through an AI model to extract business insights in real time. Market share and trend analysis are performed at this stage.

[0145] Step 4:

[0146] The server uses machine learning models to predict future market trends and company performance, and generates strategic scenarios based on the results.

[0147] Step 5:

[0148] The terminal displays real-time insights and predictive scenarios from the server during various meetings and provides immediate answers to user questions. It also dynamically suggests agenda items based on AI analysis to support meeting progress.

[0149] Step 6:

[0150] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize their emotional state in real time. This allows the system to reflect the user's emotions and perform appropriate agenda adjustments.

[0151] Step 7:

[0152] The server analyzes sentiment data and past decision-making history to suggest agenda items that should be prioritized in the next meeting. These suggestions are made in conjunction with trend data to help users select the most relevant agenda items.

[0153] (Example 2)

[0154] 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".

[0155] In corporate decision-making processes, it is necessary not only to conduct data-driven analysis but also to reflect the emotions of decision-makers. Current systems face the challenge of automatically and efficiently carrying out decision-making processes that take emotions into account. Furthermore, they lack the functionality to answer questions in real time during meetings and to automatically generate and present important agenda items.

[0156] 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.

[0157] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables efficient extraction of insights from vast amounts of data and flexible responses that reflect user emotions in the decision-making process.

[0158] "Data collection means" refers to methods for obtaining company-related information and external information from internal information recording media and external information sources.

[0159] "Data preprocessing means" refers to the process of purifying collected raw data and converting it into characteristic numerical values.

[0160] "Immediate data analysis methods" refer to methods for quickly deriving business-related insights using prepared data.

[0161] "Predictive analytics" refers to technologies that utilize machine learning models to predict future market trends and company performance, and then propose concrete solutions.

[0162] A "decision-making support tool" is a tool that has the function of presenting information in real time during a meeting and automatically generating and proposing new agenda items.

[0163] "Trend analysis methods" are analytical techniques that propose future priority issues based on past records and industry trends.

[0164] "Emotion recognition means" refers to technologies that understand a user's emotions and take those emotions into consideration in the decision-making process.

[0165] This invention is an AI system for supporting corporate decision-making processes, and in particular, it has the function of recognizing user emotions and reflecting them in decision-making. This system is mainly composed of a server and terminals.

[0166] The server is equipped with data collection means to collect corporate-related and external information from internal information storage media and external information sources. This includes information retrieval using APIs and database access using SQL queries. The collected data is pre-processed using software such as Pandas and Scikit-learn to purify the data and convert it into characteristic values.

[0167] The server also uses machine learning libraries such as TensorFlow and PyTorch to gain business-related insights through immediate data analysis. Furthermore, it utilizes predictive analytics to forecast future market trends and company performance based on this data, generating concrete proposals.

[0168] The terminal has an interface for presenting analysis results to the user in real time and is equipped with decision support means for asking questions and providing agenda items during meetings. This interface allows the user to freely input prompts to the generated AI model. For example, by inputting a question such as "What will the sales forecast for the next quarter be?", a direct answer can be obtained.

[0169] The emotion recognition system built into the device collects and analyzes the user's facial expressions and tone of voice to recognize the emotions the user is expressing in real time. This includes data acquisition using a webcam and microphone. Based on this emotion information, the server optimizes decision-making according to the user's emotions, for example, by providing supplementary information if the user shows anxiety.

[0170] An example of a prompt using a generative AI model is: "When launching a new product, please suggest the optimal strategy that takes into account current trends and user sentiment."

[0171] Thus, the present invention is a system that can efficiently utilize large amounts of data and provide complete decision-making support, including the user's emotions.

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server collects information from internal information storage media and external information sources. It receives company-related information and external information as input and retrieves data using APIs. As output, it stores the collected data in raw data format.

[0175] Step 2:

[0176] The server preprocesses the collected raw data through cleansing and feature transformation. It accepts raw data as input and uses Pandas and Scikit-learn to remove outliers, impute missing values, and perform numerical transformations on the data. As output, it generates a preprocessed and analyzable dataset.

[0177] Step 3:

[0178] The server performs immediate data analysis using pre-processed data. It uses pre-processed data as input and performs analysis using TensorFlow or PyTorch to extract business-related insights. The output provides key business metrics.

[0179] Step 4:

[0180] The server performs predictive analysis based on the analysis results. It receives the results of data analysis as input and uses a machine learning model to predict future market trends and company performance. As output, it generates predictive data to propose specific scenarios.

[0181] Step 5:

[0182] The terminal presents analysis results and prediction scenarios to the user in real time. It receives prediction data sent from the server as input and displays answers to prompts in the user interface. Users can dynamically view results by entering questions through the terminal. The output provides information to support the user's decision-making.

[0183] Step 6:

[0184] The device analyzes the user's emotions through emotion recognition. It receives data from a webcam and microphone as input, and uses an emotion engine to analyze facial expressions and voice tone. As output, it sends the recognized emotion data to a server to help adjust decision-making in real time.

[0185] (Application Example 2)

[0186] 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 device 14 will be referred to as the "terminal."

[0187] In face-to-face services such as brick-and-mortar stores, it is difficult to recognize customer emotions in real time and propose appropriate services. Therefore, providing optimal services that meet customer needs and emotions is challenging, limiting the potential for improving customer satisfaction. Solving this problem and improving service quality is essential.

[0188] 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.

[0189] In this invention, the server includes, as a data collection means, means for collecting organizational data from an internal information storage device and external information from an external information source; data preprocessing means for cleansing the collected raw data and converting it into feature quantities; and emotion recognition means for analyzing the user's facial expressions and voice to recognize emotions and dynamically adjust the service provided. This makes it possible to provide services that reflect the customer's emotions in real time.

[0190] "Data collection means" refers to the function of collecting organizational data from internal information storage devices and collecting external information from external information sources.

[0191] "Data preprocessing means" refers to the process of cleansing collected raw data and converting it into features that can be easily handled by machine learning models.

[0192] A "real-time data analysis method" is a method for immediately analyzing pre-processed data and extracting important insights related to the activity.

[0193] "Predictive analytics" refers to technologies that use machine learning models to predict future market trends and organizational performance, and to propose appropriate scenarios.

[0194] A "decision-making support tool" is a system that facilitates decision-making by providing real-time opinions and proposing agenda items during a meeting.

[0195] "Trend analysis methods" are techniques for analyzing past records and effectively prioritizing future agenda items.

[0196] An "emotion recognition system" is a system that identifies emotions by analyzing the user's facial expressions and voice, and dynamically adjusts services and suggestions based on that state.

[0197] This invention realizes a system that recognizes customer emotions in a physical store and dynamically adjusts service content based on those emotions. The system utilizes smart glasses as its main hardware, collects data through various means, and performs emotion recognition after processing.

[0198] The server collects necessary data from information storage devices and external information sources. For example, it incorporates past customer purchase history and industry trends to form the foundational data for service provision. The collected data is cleansed using data preprocessing means and converted into analyzable features. The preprocessed data is quickly analyzed by real-time data analysis means, and valuable insights are provided to the user.

[0199] The smart glasses, which serve as the terminal, capture and analyze the customer's facial expressions and voice in real time as a means of emotion recognition. The software used is a deep learning framework such as TensorFlow or PyTorch. This allows the service content to be determined based on the customer's emotions. For example, if the customer is smiling, it would be appropriate to provide more detailed product information.

[0200] The generative AI model dynamically adjusts the service suggestions based on the input provided by the user. An example of a prompt is, "Infer the customer's purchase intent from their facial expressions and suggest actions that will lead to sales promotion." This prompt allows the AI ​​model to uncover the customer's latent needs and generate the optimal customer service approach.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The server collects organizational data from internal storage devices and external information from external information sources. The input at this stage consists of data obtained from both internal storage devices and external information sources. The server aggregates this data and outputs it as raw data.

[0204] Step 2:

[0205] The server cleanses the raw data and converts it into features. The input is the raw data from step 1, which is then cleansed to remove noise and processed to extract the necessary information. The output is clean feature data suitable for analysis.

[0206] Step 3:

[0207] The server analyzes feature data in real time and extracts key insights. The input is the feature data obtained in step 2, and data calculations are performed using machine learning algorithms. The output is business-related insights.

[0208] Step 4:

[0209] The smart glasses, which act as the terminal, capture the customer's facial expressions and voice and perform emotion recognition. The input is real-time customer data from the camera and microphone. Emotion recognition software analyzes this data and performs data calculations to identify the emotional state. The output is the customer's emotional state.

[0210] Step 5:

[0211] The server generates adaptive service suggestions based on the emotional state. The inputs are the emotional state from step 4 and the business insights from step 3. The generating AI model processes the data according to the prompts and outputs specific service suggestions.

[0212] Step 6:

[0213] The user, acting as a store employee, presents the customer with the most suitable service suggestions through the display of smart glasses. The input is the service suggestion from step 5, which the user applies and uses to approach the customer. The output is the customer's service satisfaction.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] 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.

[0220] 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).

[0221] 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.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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".

[0230] This invention describes an AI-powered business support system that effectively assists corporate decision-making. The system includes functions for data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, and trend analysis.

[0231] Data collection

[0232] The server periodically extracts financial, sales, and customer data from the company's internal databases, and retrieves data from external data sources on a scheduled basis. Data types include news articles, social media posts, and industry reports.

[0233] Data preprocessing

[0234] The server cleanses the collected raw data, imputing missing values ​​and removing outliers. Following this, it generates features suitable for analysis by the AI ​​model, such as converting text data into numerical vectors. This process prepares the dataset, improving the accuracy of subsequent analyses.

[0235] Real-time data analysis

[0236] The server feeds pre-processed data into an AI model, instantly extracting business-relevant insights. This makes it possible to instantly grasp, for example, market share fluctuations or customer satisfaction.

[0237] Predictive analysis

[0238] The server uses machine learning models to predict future market trends and corporate performance that are useful for corporate strategy and decision-making. Specifically, it forecasts sales for the next fiscal year and evaluates new products in the market, and provides optimal strategies based on these results.

[0239] decision support

[0240] The device provides users with real-time insights during board meetings and management conferences. It also improves meeting efficiency by having AI analyze and suggest important agenda items. Users can input new questions as needed and receive instant answers.

[0241] Trend Analysis

[0242] The server integrates and analyzes past decision-making history and industry trend data. Based on this, it suggests topics that should be prioritized for discussion at the next meeting, helping participants to be better prepared.

[0243] For example, if a manufacturer is considering entering a new market, the server can instantly analyze market trend data, customer feedback, and the competitive landscape, and present the user with the optimal timing and strategy for entry via a terminal. In this way, decision-makers at the company can make quick, data-driven, and effective decisions.

[0244] The following describes the processing flow.

[0245] Step 1:

[0246] The server periodically extracts relevant corporate data from the company's internal database and collects various market data from external data sources via APIs. This includes news articles, social media posts, and industry reports.

[0247] Step 2:

[0248] The server cleanses the collected data. Specifically, it imputes missing values ​​and detects and removes outliers. It also standardizes the data format and converts text data into numerical vectors to extract features necessary for AI analysis.

[0249] Step 3:

[0250] The server feeds pre-processed data into an AI model and performs real-time data analysis. Here, important company metrics such as market share and sales trends are instantly visualized.

[0251] Step 4:

[0252] The server performs predictive analysis using machine learning models based on the analysis results. This generates scenarios for future market trends and product demand, creating materials for formulating optimal business strategies.

[0253] Step 5:

[0254] The terminal presents users with analysis results and predictive scenarios during board meetings and management conferences. It responds to user questions in real time and presents data-driven agenda items provided by AI.

[0255] Step 6:

[0256] The server analyzes the latest industry trend data based on past meeting records and decision-making history. This allows it to identify and suggest key topics that should be prioritized for discussion in the next meeting.

[0257] (Example 1)

[0258] 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."

[0259] In modern business management, effective decision-making based on vast amounts of internal and external data is essential. Achieving this requires a system that seamlessly handles data acquisition, preprocessing, analysis, and immediate delivery of results. However, traditional methods fragment these processes, making real-time decision-making support difficult. This hinders quick and accurate judgment, forcing many managers to waste time and resources.

[0260] 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.

[0261] In this invention, the server includes, as a data collection means, a mechanism for acquiring organizational data from an internal database and external data from an external data source; a data processing mechanism for purifying the acquired raw data and converting it into a numerical representation; and a data analysis mechanism for analyzing the processed data and immediately extracting business-related insights. This enables organizations to support real-time, precise data-driven decision-making and enhance their competitiveness.

[0262] A "data collection method" is a mechanism for extracting organizational data from an internal database and acquiring external data from external data sources.

[0263] A "data processing mechanism" is a method for purifying acquired raw data and converting it into a numerical representation.

[0264] A "data analysis mechanism" is a process for analyzing processed data and immediately extracting business-related insights.

[0265] A "predictive mechanism" is a system that uses learning models to predict future market changes and organizational performance, and to provide strategies based on those predictions.

[0266] The "decision-making support mechanism" is a process that presents insights and provides agenda items in real time during a meeting.

[0267] A "trend analysis mechanism" is a method for analyzing past history and providing future agenda items.

[0268] A "display surface" is an interface that provides information in response to user inquiries.

[0269] The present invention is a business intelligence system for supporting organizational decision-making, enabling effective decision-making through data collection, processing, analysis, and prediction. The following describes embodiments for carrying out this invention.

[0270] The system consists of servers, terminals, and users, each performing data processing according to its role. The servers function as data collection tools, periodically extracting financial data, sales information, and customer relationship data from the organization's databases. In addition, information from external data sources, such as news articles and social media, is collected using technologies like APIs and web scraping. This forms a broad information base necessary for decision-making.

[0271] The collected data is cleansed by a data processing mechanism on the server. Specifically, missing values ​​and outliers are removed using libraries such as Pandas and NumPy in the Python language. In addition, natural language processing is performed using NLTK and spaCy to convert text data into numerical representations, creating a dataset that can be analyzed by AI models. This improves data quality and increases the accuracy of the analysis.

[0272] The server inputs pre-processed data into an AI model and performs data analysis in real time. This analysis uses learning frameworks such as TensorFlow and PyTorch to clarify market trends and customer segmentation based on features extracted from the data. Subsequently, time series analysis and regression models are used to estimate future sales and market changes using a prediction mechanism. This process has a significant impact on a company's strategy formulation and risk management.

[0273] The terminal acts as a decision support mechanism, providing users with immediate analysis results. This involves using data visualization tools such as Tableau and Power BI to create an environment where users can intuitively view the data. Users can input prompts as needed to elicit responses from the generated AI model.

[0274] For example, if a user enters a prompt such as, "Forecast next quarter's sales and tell me the optimal time to enter a new market," the system can analyze the relevant data and provide appropriate action suggestions. This allows users to make quick, data-driven decisions.

[0275] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0276] Step 1:

[0277] The server accesses internal databases and external data sources for data collection. The inputs include a company's financial information, sales statistics, customer data, and external news articles and social media data. The server utilizes APIs and scraping techniques to collect this data and outputs it as a unified-form dataset. This collection process is executed regularly to ensure the completeness and currency of the information.

[0278] Step 2:

[0279] The server performs data preprocessing. It receives as input the unified-form dataset output in Step 1. Specific operations include cleansing the raw data using Pandas and NumPy. After filling in missing values and removing outliers, the data is converted into a form (e.g., numerical vectors) that can be utilized by the AI model. As a result, the system outputs the formatted dataset to the next processing step.

[0280] Step 3:

[0281] The server conducts real-time data analysis. By taking the preprocessed data from Step 2 as input, it feeds it into an AI model (using TensorFlow or PyTorch) to immediately extract business-related insights. Specifically, customer segments are identified and market trends are grasped. As output, the obtained insights are provided, serving as a basis for proceeding to the next step.

[0282] Step 4:

[0283] The server performs predictive analysis. Using the insights obtained in Step 3 as input, it uses a learning model to predict future market trends and organizational performance. Here, techniques such as time series analysis and linear regression are employed. The output is the predicted sales and market trends, which serve as information for strategic planning.

[0284] Step 5:

[0285] The terminal provides decision-making support to the user. Using the output data from the server as input, visualization is performed with Tableau or Power BI. The user checks this in real time and, if necessary, inputs a prompt sentence to obtain more detailed analysis results. Specifically, prompt sentences such as "Predict next quarter's sales and tell me the optimal timing for entering a new market" are used. As a result, specific insights are presented to the user.

[0286] Step 6:

[0287] The server performs trend analysis. Using past decision-making history and industry trend data as input, it conducts analysis and proposes future issues. Here, data mining technology is used to compare past and current data and automatically propose priority issues for the next meeting. This enables the user to obtain materials for strategic planning.

[0288] (Application Example 1)

[0289] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0290] In the modern corporate environment, there is a need to quickly interpret a large amount of data and utilize it for decision-making, but there is a lack of an appropriate support system for this. In addition, real-time information provision based on individual consumer behavior and market trends is required, but there is no system that can efficiently achieve this.

[0291] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0292] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables enterprises to predict future market trends and provide individual recommendations and real-time notifications to consumers.

[0293] "Data collection means" refers to a mechanism for obtaining necessary information from internal databases and external data sources.

[0294] "Data preprocessing means" refers to a system that has the function of cleansing collected raw data and converting it into a format suitable for analysis.

[0295] A "real-time data analysis method" is a technology that sequentially analyzes pre-processed data and immediately extracts insights relevant to business operations.

[0296] "Predictive analytics tools" are tools that use machine learning models to predict market trends and organizational performance in the future.

[0297] "Decision-making support tools" are means of supporting the decision-making process by presenting necessary analysis results and agenda items in real time during meetings.

[0298] "Trend analysis tools" are technologies that integrate historical data and market trends to propose future priority issues.

[0299] A "recommendation engine" is an algorithm that recommends products and services based on the user's behavior.

[0300] A "push notification method" is a communication method that reflects real-time market information and delivers messages directly to users.

[0301] The business support system implementing the present invention consists of multiple hardware and software components. The server acquires organizational data from internal and external data sources using data acquisition means. This data is cleansed and converted into feature vectors by data preprocessing means.

[0302] Through real-time data analysis means, the preprocessed data is sequentially analyzed to extract insights related to business. An AI model using TensorFlow is utilized for this analysis. The server also leverages a machine learning model through predictive analysis means to predict the future market trends and performance of the organization.

[0303] The terminal visualizes these insights and provides them to the user in real time. Furthermore, the recommended products and sales information generated by the server are individually optimized by the recommendation engine means and sent to the user via the push notification means.

[0304] For example, when a user is engaged in online shopping, the viewed product data is collected in real time, and the AI model recommends appropriate products to promote the next purchase. As a specific example, a prompt text such as "For the next big sale, there is a special offer related to the items you recently viewed. Check the details in the app!" is generated and notified to the user.

[0305] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0306] Step 1:

[0307] The server uses data collection means to obtain organizational data from the internal database and external data sources. The input data includes financial data, sales data, and social media posts, etc. The output is the construction of the collected raw data.

[0308] Step 2:

[0309] The server cleans the raw data collected by the data preprocessing means and converts it into feature vectors. The raw data obtained as input is converted into a form suitable for analysis through missing value imputation and outlier removal. The output is a dataset that has been cleaned and feature-quantified.

[0310] Step 3:

[0311] The server uses real-time data analysis tools to sequentially analyze pre-processed data and extract business-related insights. The input data is analyzed using a TensorFlow-based generative AI model. The output provides insights into customer satisfaction and market share fluctuations.

[0312] Step 4:

[0313] The server leverages machine learning models through predictive analytics to forecast future market trends and performance for an organization. It receives analysis results as input and uses them to build future sales forecasts and product strategies. The output consists of predicted market trends and strategic recommendations.

[0314] Step 5:

[0315] The terminal uses decision support tools to visualize generated insights in real time and provide them to the user during the meeting. Input consists of prediction results and insights sent from the server. Output is visually represented data, allowing for quick identification of important agenda items.

[0316] Step 6:

[0317] The server also uses a recommendation engine to analyze user behavior data and generate personalized product and service information. Input data includes the user's browsing and purchase history, while output is appropriately personalized product recommendations based on that data.

[0318] Step 7:

[0319] The device notifies the user of personalized product recommendations and campaign information via push notifications. The input is product recommendations sent from the server, and the output is a notification message displayed on the user's device.

[0320] 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.

[0321] This invention relates to an AI system with enhanced capabilities to effectively support a company's decision-making process, particularly one that recognizes user emotions and incorporates them into decision-making. The system consists of data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, trend analysis, and emotion recognition.

[0322] Data collection

[0323] The server periodically collects necessary data from the company's internal databases and external data sources. This includes financial data, sales data, news articles, social media posts, and industry reports.

[0324] Data preprocessing

[0325] The server cleanses the collected data, imputing missing values ​​and removing outliers. Furthermore, it transforms the data into features in a format that the model can learn from.

[0326] Real-time data analysis and predictive analytics

[0327] The server analyzes pre-processed data using an AI model, instantly extracts key business metrics, and predicts future market trends using machine learning techniques.

[0328] decision support

[0329] The device presents users with analysis results and predictive scenarios, and also responds to real-time questions during meetings. Furthermore, the AI ​​automatically generates and presents important agenda items to users, supporting efficient decision-making.

[0330] Trend Analysis

[0331] The server analyzes past records and industry trends to suggest priority agenda items for the next meeting. This allows meeting participants to prepare more effectively.

[0332] emotion recognition

[0333] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize emotions in real time. This allows the server to adjust the agenda and approach according to the emotional state. For example, if the user shows anxiety, it will provide more information and different perspectives.

[0334] For example, when discussing the market launch of a new product during a board meeting, the server analyzes market data and suggests the optimal strategy. The terminal also monitors the user's emotional state, recommending a challenging strategy if optimistic feelings are present, and a more conservative approach if concerns are expressed. This allows for the integration of user emotions into data-driven decision-making, leading to more balanced conclusions.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The server collects various corporate data from the company's internal database and retrieves market data, news articles, and social media posts from external data sources via external APIs. This creates a comprehensive dataset.

[0338] Step 2:

[0339] The server performs data cleansing on the acquired data, imputing missing values ​​and detecting and removing outliers. It converts the data format to a standard format usable by the AI ​​model and prepares it for extracting necessary features.

[0340] Step 3:

[0341] The server processes pre-processed data through an AI model to extract business insights in real time. Market share and trend analysis are performed at this stage.

[0342] Step 4:

[0343] The server uses machine learning models to predict future market trends and company performance, and generates strategic scenarios based on the results.

[0344] Step 5:

[0345] The terminal displays real-time insights and predictive scenarios from the server during various meetings and provides immediate answers to user questions. It also dynamically suggests agenda items based on AI analysis to support meeting progress.

[0346] Step 6:

[0347] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize their emotional state in real time. This allows the system to reflect the user's emotions and perform appropriate agenda adjustments.

[0348] Step 7:

[0349] The server analyzes sentiment data and past decision-making history to suggest agenda items that should be prioritized in the next meeting. These suggestions are made in conjunction with trend data to help users select the most relevant agenda items.

[0350] (Example 2)

[0351] 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".

[0352] In corporate decision-making processes, it is necessary not only to conduct data-driven analysis but also to reflect the emotions of decision-makers. Current systems face the challenge of automatically and efficiently carrying out decision-making processes that take emotions into account. Furthermore, they lack the functionality to answer questions in real time during meetings and to automatically generate and present important agenda items.

[0353] 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.

[0354] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables efficient extraction of insights from vast amounts of data and flexible responses that reflect user emotions in the decision-making process.

[0355] "Data collection means" refers to methods for obtaining company-related information and external information from internal information recording media and external information sources.

[0356] "Data preprocessing means" refers to the process of purifying collected raw data and converting it into characteristic numerical values.

[0357] "Immediate data analysis methods" refer to methods for quickly deriving business-related insights using prepared data.

[0358] "Predictive analytics" refers to technologies that utilize machine learning models to predict future market trends and company performance, and then propose concrete solutions.

[0359] A "decision-making support tool" is a tool that has the function of presenting information in real time during a meeting and automatically generating and proposing new agenda items.

[0360] "Trend analysis methods" are analytical techniques that propose future priority issues based on past records and industry trends.

[0361] "Emotion recognition means" refers to technologies that understand a user's emotions and take those emotions into consideration in the decision-making process.

[0362] This invention is an AI system for supporting corporate decision-making processes, and in particular, it has the function of recognizing user emotions and reflecting them in decision-making. This system is mainly composed of a server and terminals.

[0363] The server is equipped with data collection means to collect corporate-related and external information from internal information storage media and external information sources. This includes information retrieval using APIs and database access using SQL queries. The collected data is pre-processed using software such as Pandas and Scikit-learn to purify the data and convert it into characteristic values.

[0364] The server also uses machine learning libraries such as TensorFlow and PyTorch to gain business-related insights through immediate data analysis. Furthermore, it utilizes predictive analytics to forecast future market trends and company performance based on this data, generating concrete proposals.

[0365] The terminal has an interface for presenting analysis results to the user in real time and is equipped with decision support means for asking questions and providing agenda items during meetings. This interface allows the user to freely input prompts to the generated AI model. For example, by inputting a question such as "What will the sales forecast for the next quarter be?", a direct answer can be obtained.

[0366] The emotion recognition system built into the device collects and analyzes the user's facial expressions and tone of voice to recognize the emotions the user is expressing in real time. This includes data acquisition using a webcam and microphone. Based on this emotion information, the server optimizes decision-making according to the user's emotions, for example, by providing supplementary information if the user shows anxiety.

[0367] An example of a prompt using a generative AI model is: "When launching a new product, please suggest the optimal strategy that takes into account current trends and user sentiment."

[0368] Thus, the present invention is a system that can efficiently utilize large amounts of data and provide complete decision-making support, including the user's emotions.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The server collects information from internal information storage media and external information sources. It receives company-related information and external information as input and retrieves data using APIs. As output, it stores the collected data in raw data format.

[0372] Step 2:

[0373] The server preprocesses the collected raw data through cleansing and feature transformation. It accepts raw data as input and uses Pandas and Scikit-learn to remove outliers, impute missing values, and perform numerical transformations on the data. As output, it generates a preprocessed and analyzable dataset.

[0374] Step 3:

[0375] The server performs immediate data analysis using pre-processed data. It uses pre-processed data as input and performs analysis using TensorFlow or PyTorch to extract business-related insights. The output provides key business metrics.

[0376] Step 4:

[0377] The server performs predictive analysis based on the analysis results. It receives the results of data analysis as input and uses a machine learning model to predict future market trends and company performance. As output, it generates predictive data to propose specific scenarios.

[0378] Step 5:

[0379] The terminal presents analysis results and prediction scenarios to the user in real time. It receives prediction data sent from the server as input and displays answers to prompts in the user interface. Users can dynamically view results by entering questions through the terminal. The output provides information to support the user's decision-making.

[0380] Step 6:

[0381] The device analyzes the user's emotions through emotion recognition. It receives data from a webcam and microphone as input, and uses an emotion engine to analyze facial expressions and voice tone. As output, it sends the recognized emotion data to a server to help adjust decision-making in real time.

[0382] (Application Example 2)

[0383] 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 as the "terminal".

[0384] In face-to-face services such as brick-and-mortar stores, it is difficult to recognize customer emotions in real time and propose appropriate services. Therefore, providing optimal services that meet customer needs and emotions is challenging, limiting the potential for improving customer satisfaction. Solving this problem and improving service quality is essential.

[0385] 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.

[0386] In this invention, the server includes, as a data collection means, means for collecting organizational data from an internal information storage device and external information from an external information source; data preprocessing means for cleansing the collected raw data and converting it into feature quantities; and emotion recognition means for analyzing the user's facial expressions and voice to recognize emotions and dynamically adjust the service provided. This makes it possible to provide services that reflect the customer's emotions in real time.

[0387] "Data collection means" refers to the function of collecting organizational data from internal information storage devices and collecting external information from external information sources.

[0388] "Data preprocessing means" refers to the process of cleansing collected raw data and converting it into features that can be easily handled by machine learning models.

[0389] A "real-time data analysis method" is a method for immediately analyzing pre-processed data and extracting important insights related to the activity.

[0390] "Predictive analytics" refers to technologies that use machine learning models to predict future market trends and organizational performance, and to propose appropriate scenarios.

[0391] A "decision-making support tool" is a system that facilitates decision-making by providing real-time opinions and proposing agenda items during a meeting.

[0392] "Trend analysis methods" are techniques for analyzing past records and effectively prioritizing future agenda items.

[0393] An "emotion recognition system" is a system that identifies emotions by analyzing the user's facial expressions and voice, and dynamically adjusts services and suggestions based on that state.

[0394] This invention realizes a system that recognizes customer emotions in a physical store and dynamically adjusts service content based on those emotions. The system utilizes smart glasses as its main hardware, collects data through various means, and performs emotion recognition after processing.

[0395] The server collects necessary data from information storage devices and external information sources. For example, it incorporates past customer purchase history and industry trends to form the foundational data for service provision. The collected data is cleansed using data preprocessing means and converted into analyzable features. The preprocessed data is quickly analyzed by real-time data analysis means, and valuable insights are provided to the user.

[0396] The smart glasses, which serve as the terminal, capture and analyze the customer's facial expressions and voice in real time as a means of emotion recognition. The software used is a deep learning framework such as TensorFlow or PyTorch. This allows the service content to be determined based on the customer's emotions. For example, if the customer is smiling, it would be appropriate to provide more detailed product information.

[0397] The generative AI model dynamically adjusts the service suggestions based on the input provided by the user. An example of a prompt is, "Infer the customer's purchase intent from their facial expressions and suggest actions that will lead to sales promotion." This prompt allows the AI ​​model to uncover the customer's latent needs and generate the optimal customer service approach.

[0398] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0399] Step 1:

[0400] The server collects organizational data from internal storage devices and external information from external information sources. The input at this stage consists of data obtained from both internal storage devices and external information sources. The server aggregates this data and outputs it as raw data.

[0401] Step 2:

[0402] The server cleanses the raw data and converts it into features. The input is the raw data from step 1, which is then cleansed to remove noise and processed to extract the necessary information. The output is clean feature data suitable for analysis.

[0403] Step 3:

[0404] The server analyzes feature data in real time and extracts key insights. The input is the feature data obtained in step 2, and data calculations are performed using machine learning algorithms. The output is business-related insights.

[0405] Step 4:

[0406] The smart glasses, which act as the terminal, capture the customer's facial expressions and voice and perform emotion recognition. The input is real-time customer data from the camera and microphone. Emotion recognition software analyzes this data and performs data calculations to identify the emotional state. The output is the customer's emotional state.

[0407] Step 5:

[0408] The server generates adaptive service suggestions based on the emotional state. The inputs are the emotional state from step 4 and the business insights from step 3. The generating AI model processes the data according to the prompts and outputs specific service suggestions.

[0409] Step 6:

[0410] The user, acting as a store employee, presents the customer with the most suitable service suggestions through the display of smart glasses. The input is the service suggestion from step 5, which the user applies and uses to approach the customer. The output is the customer's service satisfaction.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] [Third Embodiment]

[0415] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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).

[0421] 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.

[0422] 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.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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".

[0427] This invention describes an AI-powered business support system that effectively assists corporate decision-making. The system includes functions for data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, and trend analysis.

[0428] Data collection

[0429] The server periodically extracts financial, sales, and customer data from the company's internal databases, and retrieves data from external data sources on a scheduled basis. Data types include news articles, social media posts, and industry reports.

[0430] Data preprocessing

[0431] The server cleanses the collected raw data, imputing missing values ​​and removing outliers. Following this, it generates features suitable for analysis by the AI ​​model, such as converting text data into numerical vectors. This process prepares the dataset, improving the accuracy of subsequent analyses.

[0432] Real-time data analysis

[0433] The server feeds pre-processed data into an AI model, instantly extracting business-relevant insights. This makes it possible to instantly grasp, for example, market share fluctuations or customer satisfaction.

[0434] Predictive analysis

[0435] The server uses machine learning models to predict future market trends and corporate performance that are useful for corporate strategy and decision-making. Specifically, it forecasts sales for the next fiscal year and evaluates new products in the market, and provides optimal strategies based on these results.

[0436] decision support

[0437] The device provides users with real-time insights during board meetings and management conferences. It also improves meeting efficiency by having AI analyze and suggest important agenda items. Users can input new questions as needed and receive instant answers.

[0438] Trend Analysis

[0439] The server integrates and analyzes past decision-making history and industry trend data. Based on this, it suggests topics that should be prioritized for discussion at the next meeting, helping participants to be better prepared.

[0440] For example, if a manufacturer is considering entering a new market, the server can instantly analyze market trend data, customer feedback, and the competitive landscape, and present the user with the optimal timing and strategy for entry via a terminal. In this way, decision-makers at the company can make quick, data-driven, and effective decisions.

[0441] The following describes the processing flow.

[0442] Step 1:

[0443] The server periodically extracts relevant corporate data from the company's internal database and collects various market data from external data sources via APIs. This includes news articles, social media posts, and industry reports.

[0444] Step 2:

[0445] The server cleanses the collected data. Specifically, it imputes missing values ​​and detects and removes outliers. It also standardizes the data format and converts text data into numerical vectors to extract features necessary for AI analysis.

[0446] Step 3:

[0447] The server feeds pre-processed data into an AI model and performs real-time data analysis. Here, important company metrics such as market share and sales trends are instantly visualized.

[0448] Step 4:

[0449] The server performs predictive analysis using machine learning models based on the analysis results. This generates scenarios for future market trends and product demand, creating materials for formulating optimal business strategies.

[0450] Step 5:

[0451] The terminal presents users with analysis results and predictive scenarios during board meetings and management conferences. It responds to user questions in real time and presents data-driven agenda items provided by AI.

[0452] Step 6:

[0453] The server analyzes the latest industry trend data based on past meeting records and decision-making history. This allows it to identify and suggest key topics that should be prioritized for discussion in the next meeting.

[0454] (Example 1)

[0455] 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."

[0456] In modern business management, effective decision-making based on vast amounts of internal and external data is essential. Achieving this requires a system that seamlessly handles data acquisition, preprocessing, analysis, and immediate delivery of results. However, traditional methods fragment these processes, making real-time decision-making support difficult. This hinders quick and accurate judgment, forcing many managers to waste time and resources.

[0457] 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.

[0458] In this invention, the server includes, as a data collection means, a mechanism for acquiring organizational data from an internal database and external data from an external data source; a data processing mechanism for purifying the acquired raw data and converting it into a numerical representation; and a data analysis mechanism for analyzing the processed data and immediately extracting business-related insights. This enables organizations to support real-time, precise data-driven decision-making and enhance their competitiveness.

[0459] A "data collection method" is a mechanism for extracting organizational data from an internal database and acquiring external data from external data sources.

[0460] A "data processing mechanism" is a method for purifying acquired raw data and converting it into a numerical representation.

[0461] A "data analysis mechanism" is a process for analyzing processed data and immediately extracting business-related insights.

[0462] A "predictive mechanism" is a system that uses learning models to predict future market changes and organizational performance, and to provide strategies based on those predictions.

[0463] The "decision-making support mechanism" is a process that presents insights and provides agenda items in real time during a meeting.

[0464] A "trend analysis mechanism" is a method for analyzing past history and providing future agenda items.

[0465] A "display surface" is an interface that provides information in response to user inquiries.

[0466] The present invention is a business intelligence system for supporting organizational decision-making, enabling effective decision-making through data collection, processing, analysis, and prediction. The following describes embodiments for carrying out this invention.

[0467] The system consists of servers, terminals, and users, each performing data processing according to its role. The servers function as data collection tools, periodically extracting financial data, sales information, and customer relationship data from the organization's databases. In addition, information from external data sources, such as news articles and social media, is collected using technologies like APIs and web scraping. This forms a broad information base necessary for decision-making.

[0468] The collected data is cleansed by a data processing mechanism on the server. Specifically, missing values ​​and outliers are removed using libraries such as Pandas and NumPy in the Python language. In addition, natural language processing is performed using NLTK and spaCy to convert text data into numerical representations, creating a dataset that can be analyzed by AI models. This improves data quality and increases the accuracy of the analysis.

[0469] The server inputs pre-processed data into an AI model and performs data analysis in real time. This analysis uses learning frameworks such as TensorFlow and PyTorch to clarify market trends and customer segmentation based on features extracted from the data. Subsequently, time series analysis and regression models are used to estimate future sales and market changes using a prediction mechanism. This process has a significant impact on a company's strategy formulation and risk management.

[0470] The terminal acts as a decision support mechanism, providing users with immediate analysis results. This involves using data visualization tools such as Tableau and Power BI to create an environment where users can intuitively view the data. Users can input prompts as needed to elicit responses from the generated AI model.

[0471] For example, if a user enters a prompt such as, "Forecast next quarter's sales and tell me the optimal time to enter a new market," the system can analyze the relevant data and provide appropriate action suggestions. This allows users to make quick, data-driven decisions.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] The server accesses internal databases and external data sources for data collection. Inputs include corporate financial information, sales statistics, customer data, and data from external news articles and social media. The server utilizes APIs and scraping techniques to collect this data and outputs it as a standardized dataset. This collection process is performed regularly to ensure the completeness and timeliness of the information.

[0475] Step 2:

[0476] The server performs data preprocessing. It receives the unified formatted dataset output in step 1 as input. Specific actions include cleaning the raw data using Pandas and NumPy. After imputing missing values ​​and removing outliers, the data is converted into a format usable by the AI ​​model (e.g., numerical vectors). As a result, the system outputs the formatted dataset to the next processing step.

[0477] Step 3:

[0478] The server performs real-time data analysis. By using pre-processed data from Step 2 as input, it feeds it into an AI model (using TensorFlow or PyTorch) to instantly extract business-related insights. Specifically, this involves identifying customer segments and understanding market trends. The resulting insights are provided as output, forming the foundation for the next steps.

[0479] Step 4:

[0480] The server performs predictive analytics. Using the insights obtained in Step 3 as input, it uses a learning model to predict future market trends and organizational performance. Here, methods such as time series analysis and linear regression are employed. The output is predicted sales and market trends, which serve as foundational information for strategic planning.

[0481] Step 5:

[0482] The terminal provides decision support to the user. Output data from the server is used as input for visualization in Tableau and Power BI. The user can view this in real time and, if necessary, enter prompts to obtain more detailed analysis results. Specifically, prompts such as "Forecast next quarter's sales and tell me the optimal time for entering new markets" are used. As a result, concrete insights are presented to the user.

[0483] Step 6:

[0484] The server performs trend analysis. It analyzes past decision-making history and industry trend data as input and proposes future agenda items. Here, data mining techniques are used to compare past and present data and automatically suggest priority agenda items for the next meeting. This provides users with the information they need to strategically plan.

[0485] (Application Example 1)

[0486] 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."

[0487] In today's business environment, it is necessary to quickly interpret large amounts of data and utilize it for decision-making, but there is a lack of appropriate support systems for this purpose. Furthermore, there is a demand for real-time information based on individual consumer behavior and market trends, but no system exists that can efficiently achieve this.

[0488] 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.

[0489] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables companies to predict future market trends and provide personalized recommendations and real-time notifications to consumers.

[0490] "Data collection means" refers to a mechanism for obtaining necessary information from internal databases and external data sources.

[0491] "Data preprocessing means" refers to a system that has the function of cleansing collected raw data and converting it into a format suitable for analysis.

[0492] A "real-time data analysis method" is a technology that sequentially analyzes pre-processed data and immediately extracts insights relevant to business operations.

[0493] "Predictive analytics tools" are tools that use machine learning models to predict market trends and organizational performance in the future.

[0494] "Decision-making support tools" are means of supporting the decision-making process by presenting necessary analysis results and agenda items in real time during meetings.

[0495] "Trend analysis tools" are technologies that integrate historical data and market trends to propose future priority issues.

[0496] A "recommendation engine" is an algorithm that recommends products and services based on the user's behavior.

[0497] A "push notification method" is a communication method that reflects real-time market information and delivers messages directly to users.

[0498] The business support system implementing the present invention consists of multiple hardware and software components. The server acquires organizational data from internal and external data sources using data acquisition means. This data is cleansed and converted into feature vectors by data preprocessing means.

[0499] Pre-processed data is sequentially analyzed using real-time data analysis tools to extract business insights. This analysis utilizes AI models based on TensorFlow. The server also leverages machine learning models through predictive analytics tools to forecast the organization's future market trends and performance.

[0500] The device visualizes these insights and provides them to the user in real time. Furthermore, recommended products and sales information generated by the server are individually optimized by the recommendation engine and sent to the user via push notifications.

[0501] For example, when a user is online shopping, data on the products they have viewed is collected in real time, and an AI model recommends appropriate products to encourage their next purchase. A specific example is a prompt message generated and sent to the user saying, "Special offers related to items you've recently viewed are available for the upcoming big sale. Check the app for details!"

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] The server retrieves organizational data from internal databases and external data sources using data collection methods. Input data includes financial data, sales data, and social media posts. Output is a compilation of the collected raw data.

[0505] Step 2:

[0506] The server cleanses the raw data collected by the data preprocessing mechanism and converts it into feature vectors. The raw data obtained as input is then converted into a format suitable for analysis through missing value imputation and outlier removal. The output is a cleansed and feature-enhanced dataset.

[0507] Step 3:

[0508] The server uses real-time data analysis tools to sequentially analyze pre-processed data and extract business-related insights. The input data is analyzed using a TensorFlow-based generative AI model. The output provides insights into customer satisfaction and market share fluctuations.

[0509] Step 4:

[0510] The server leverages machine learning models through predictive analytics to forecast future market trends and performance for an organization. It receives analysis results as input and uses them to build future sales forecasts and product strategies. The output consists of predicted market trends and strategic recommendations.

[0511] Step 5:

[0512] The terminal uses decision support tools to visualize generated insights in real time and provide them to the user during the meeting. Input consists of prediction results and insights sent from the server. Output is visually represented data, allowing for quick identification of important agenda items.

[0513] Step 6:

[0514] The server also uses a recommendation engine to analyze user behavior data and generate personalized product and service information. Input data includes the user's browsing and purchase history, while output is appropriately personalized product recommendations based on that data.

[0515] Step 7:

[0516] The device notifies the user of personalized product recommendations and campaign information via push notifications. The input is product recommendations sent from the server, and the output is a notification message displayed on the user's device.

[0517] 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.

[0518] This invention relates to an AI system with enhanced capabilities to effectively support a company's decision-making process, particularly one that recognizes user emotions and incorporates them into decision-making. The system consists of data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, trend analysis, and emotion recognition.

[0519] Data collection

[0520] The server periodically collects necessary data from the company's internal databases and external data sources. This includes financial data, sales data, news articles, social media posts, and industry reports.

[0521] Data preprocessing

[0522] The server cleanses the collected data, imputing missing values ​​and removing outliers. Furthermore, it transforms the data into features in a format that the model can learn from.

[0523] Real-time data analysis and predictive analytics

[0524] The server analyzes pre-processed data using an AI model, instantly extracts key business metrics, and predicts future market trends using machine learning techniques.

[0525] decision support

[0526] The device presents users with analysis results and predictive scenarios, and also responds to real-time questions during meetings. Furthermore, the AI ​​automatically generates and presents important agenda items to users, supporting efficient decision-making.

[0527] Trend Analysis

[0528] The server analyzes past records and industry trends to suggest priority agenda items for the next meeting. This allows meeting participants to prepare more effectively.

[0529] emotion recognition

[0530] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize emotions in real time. This allows the server to adjust the agenda and approach according to the emotional state. For example, if the user shows anxiety, it will provide more information and different perspectives.

[0531] For example, when discussing the market launch of a new product during a board meeting, the server analyzes market data and suggests the optimal strategy. The terminal also monitors the user's emotional state, recommending a challenging strategy if optimistic feelings are present, and a more conservative approach if concerns are expressed. This allows for the integration of user emotions into data-driven decision-making, leading to more balanced conclusions.

[0532] The following describes the processing flow.

[0533] Step 1:

[0534] The server collects various corporate data from the company's internal database and retrieves market data, news articles, and social media posts from external data sources via external APIs. This creates a comprehensive dataset.

[0535] Step 2:

[0536] The server performs data cleansing on the acquired data, imputing missing values ​​and detecting and removing outliers. It converts the data format to a standard format usable by the AI ​​model and prepares it for extracting necessary features.

[0537] Step 3:

[0538] The server processes pre-processed data through an AI model to extract business insights in real time. Market share and trend analysis are performed at this stage.

[0539] Step 4:

[0540] The server uses machine learning models to predict future market trends and company performance, and generates strategic scenarios based on the results.

[0541] Step 5:

[0542] The terminal displays real-time insights and predictive scenarios from the server during various meetings and provides immediate answers to user questions. It also dynamically suggests agenda items based on AI analysis to support meeting progress.

[0543] Step 6:

[0544] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize their emotional state in real time. This allows the system to reflect the user's emotions and perform appropriate agenda adjustments.

[0545] Step 7:

[0546] The server analyzes sentiment data and past decision-making history to suggest agenda items that should be prioritized in the next meeting. These suggestions are made in conjunction with trend data to help users select the most relevant agenda items.

[0547] (Example 2)

[0548] 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."

[0549] In corporate decision-making processes, it is necessary not only to conduct data-driven analysis but also to reflect the emotions of decision-makers. Current systems face the challenge of automatically and efficiently carrying out decision-making processes that take emotions into account. Furthermore, they lack the functionality to answer questions in real time during meetings and to automatically generate and present important agenda items.

[0550] 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.

[0551] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables efficient extraction of insights from vast amounts of data and flexible responses that reflect user emotions in the decision-making process.

[0552] "Data collection means" refers to methods for obtaining company-related information and external information from internal information recording media and external information sources.

[0553] "Data preprocessing means" refers to the process of purifying collected raw data and converting it into characteristic numerical values.

[0554] "Immediate data analysis methods" refer to methods for quickly deriving business-related insights using prepared data.

[0555] "Predictive analytics" refers to technologies that utilize machine learning models to predict future market trends and company performance, and then propose concrete solutions.

[0556] A "decision-making support tool" is a tool that has the function of presenting information in real time during a meeting and automatically generating and proposing new agenda items.

[0557] "Trend analysis methods" are analytical techniques that propose future priority issues based on past records and industry trends.

[0558] "Emotion recognition means" refers to technologies that understand a user's emotions and take those emotions into consideration in the decision-making process.

[0559] This invention is an AI system for supporting corporate decision-making processes, and in particular, it has the function of recognizing user emotions and reflecting them in decision-making. This system is mainly composed of a server and terminals.

[0560] The server is equipped with data collection means to collect corporate-related and external information from internal information storage media and external information sources. This includes information retrieval using APIs and database access using SQL queries. The collected data is pre-processed using software such as Pandas and Scikit-learn to purify the data and convert it into characteristic values.

[0561] The server also uses machine learning libraries such as TensorFlow and PyTorch to gain business-related insights through immediate data analysis. Furthermore, it utilizes predictive analytics to forecast future market trends and company performance based on this data, generating concrete proposals.

[0562] The terminal has an interface for presenting analysis results to the user in real time and is equipped with decision support means for asking questions and providing agenda items during meetings. This interface allows the user to freely input prompts to the generated AI model. For example, by inputting a question such as "What will the sales forecast for the next quarter be?", a direct answer can be obtained.

[0563] The emotion recognition system built into the device collects and analyzes the user's facial expressions and tone of voice to recognize the emotions the user is expressing in real time. This includes data acquisition using a webcam and microphone. Based on this emotion information, the server optimizes decision-making according to the user's emotions, for example, by providing supplementary information if the user shows anxiety.

[0564] An example of a prompt using a generative AI model is: "When launching a new product, please suggest the optimal strategy that takes into account current trends and user sentiment."

[0565] Thus, the present invention is a system that can efficiently utilize large amounts of data and provide complete decision-making support, including the user's emotions.

[0566] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0567] Step 1:

[0568] The server collects information from internal information storage media and external information sources. It receives company-related information and external information as input and retrieves data using APIs. As output, it stores the collected data in raw data format.

[0569] Step 2:

[0570] The server preprocesses the collected raw data through cleansing and feature transformation. It accepts raw data as input and uses Pandas and Scikit-learn to remove outliers, impute missing values, and perform numerical transformations on the data. As output, it generates a preprocessed and analyzable dataset.

[0571] Step 3:

[0572] The server performs immediate data analysis using pre-processed data. It uses pre-processed data as input and performs analysis using TensorFlow or PyTorch to extract business-related insights. The output provides key business metrics.

[0573] Step 4:

[0574] The server performs predictive analysis based on the analysis results. It receives the results of data analysis as input and uses a machine learning model to predict future market trends and company performance. As output, it generates predictive data to propose specific scenarios.

[0575] Step 5:

[0576] The terminal presents analysis results and prediction scenarios to the user in real time. It receives prediction data sent from the server as input and displays answers to prompts in the user interface. Users can dynamically view results by entering questions through the terminal. The output provides information to support the user's decision-making.

[0577] Step 6:

[0578] The device analyzes the user's emotions through emotion recognition. It receives data from a webcam and microphone as input, and uses an emotion engine to analyze facial expressions and voice tone. As output, it sends the recognized emotion data to a server to help adjust decision-making in real time.

[0579] (Application Example 2)

[0580] 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."

[0581] In face-to-face services such as brick-and-mortar stores, it is difficult to recognize customer emotions in real time and propose appropriate services. Therefore, providing optimal services that meet customer needs and emotions is challenging, limiting the potential for improving customer satisfaction. Solving this problem and improving service quality is essential.

[0582] 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.

[0583] In this invention, the server includes, as a data collection means, means for collecting organizational data from an internal information storage device and external information from an external information source; data preprocessing means for cleansing the collected raw data and converting it into feature quantities; and emotion recognition means for analyzing the user's facial expressions and voice to recognize emotions and dynamically adjust the service provided. This makes it possible to provide services that reflect the customer's emotions in real time.

[0584] "Data collection means" refers to the function of collecting organizational data from internal information storage devices and collecting external information from external information sources.

[0585] "Data preprocessing means" refers to the process of cleansing collected raw data and converting it into features that can be easily handled by machine learning models.

[0586] A "real-time data analysis method" is a method for immediately analyzing pre-processed data and extracting important insights related to the activity.

[0587] "Predictive analytics" refers to technologies that use machine learning models to predict future market trends and organizational performance, and to propose appropriate scenarios.

[0588] A "decision-making support tool" is a system that facilitates decision-making by providing real-time opinions and proposing agenda items during a meeting.

[0589] "Trend analysis methods" are techniques for analyzing past records and effectively prioritizing future agenda items.

[0590] An "emotion recognition system" is a system that identifies emotions by analyzing the user's facial expressions and voice, and dynamically adjusts services and suggestions based on that state.

[0591] This invention realizes a system that recognizes customer emotions in a physical store and dynamically adjusts service content based on those emotions. The system utilizes smart glasses as its main hardware, collects data through various means, and performs emotion recognition after processing.

[0592] The server collects necessary data from information storage devices and external information sources. For example, it incorporates past customer purchase history and industry trends to form the foundational data for service provision. The collected data is cleansed using data preprocessing means and converted into analyzable features. The preprocessed data is quickly analyzed by real-time data analysis means, and valuable insights are provided to the user.

[0593] The smart glasses, which serve as the terminal, capture and analyze the customer's facial expressions and voice in real time as a means of emotion recognition. The software used is a deep learning framework such as TensorFlow or PyTorch. This allows the service content to be determined based on the customer's emotions. For example, if the customer is smiling, it would be appropriate to provide more detailed product information.

[0594] The generative AI model dynamically adjusts the service suggestions based on the input provided by the user. An example of a prompt is, "Infer the customer's purchase intent from their facial expressions and suggest actions that will lead to sales promotion." This prompt allows the AI ​​model to uncover the customer's latent needs and generate the optimal customer service approach.

[0595] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0596] Step 1:

[0597] The server collects organizational data from internal storage devices and external information from external information sources. The input at this stage consists of data obtained from both internal storage devices and external information sources. The server aggregates this data and outputs it as raw data.

[0598] Step 2:

[0599] The server cleanses the raw data and converts it into features. The input is the raw data from step 1, which is then cleansed to remove noise and processed to extract the necessary information. The output is clean feature data suitable for analysis.

[0600] Step 3:

[0601] The server analyzes feature data in real time and extracts key insights. The input is the feature data obtained in step 2, and data calculations are performed using machine learning algorithms. The output is business-related insights.

[0602] Step 4:

[0603] The smart glasses, which act as the terminal, capture the customer's facial expressions and voice and perform emotion recognition. The input is real-time customer data from the camera and microphone. Emotion recognition software analyzes this data and performs data calculations to identify the emotional state. The output is the customer's emotional state.

[0604] Step 5:

[0605] The server generates adaptive service suggestions based on the emotional state. The inputs are the emotional state from step 4 and the business insights from step 3. The generating AI model processes the data according to the prompts and outputs specific service suggestions.

[0606] Step 6:

[0607] The user, acting as a store employee, presents the customer with the most suitable service suggestions through the display of smart glasses. The input is the service suggestion from step 5, which the user applies and uses to approach the customer. The output is the customer's service satisfaction.

[0608] 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.

[0609] 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.

[0610] 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.

[0611] [Fourth Embodiment]

[0612] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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).

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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".

[0625] This invention describes an AI-powered business support system that effectively assists corporate decision-making. The system includes functions for data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, and trend analysis.

[0626] Data collection

[0627] The server periodically extracts financial, sales, and customer data from the company's internal databases, and retrieves data from external data sources on a scheduled basis. Data types include news articles, social media posts, and industry reports.

[0628] Data preprocessing

[0629] The server cleanses the collected raw data, imputing missing values ​​and removing outliers. Following this, it generates features suitable for analysis by the AI ​​model, such as converting text data into numerical vectors. This process prepares the dataset, improving the accuracy of subsequent analyses.

[0630] Real-time data analysis

[0631] The server feeds pre-processed data into an AI model, instantly extracting business-relevant insights. This makes it possible to instantly grasp, for example, market share fluctuations or customer satisfaction.

[0632] Predictive analysis

[0633] The server uses machine learning models to predict future market trends and corporate performance that are useful for corporate strategy and decision-making. Specifically, it forecasts sales for the next fiscal year and evaluates new products in the market, and provides optimal strategies based on these results.

[0634] decision support

[0635] The device provides users with real-time insights during board meetings and management conferences. It also improves meeting efficiency by having AI analyze and suggest important agenda items. Users can input new questions as needed and receive instant answers.

[0636] Trend Analysis

[0637] The server integrates and analyzes past decision-making history and industry trend data. Based on this, it suggests topics that should be prioritized for discussion at the next meeting, helping participants to be better prepared.

[0638] For example, if a manufacturer is considering entering a new market, the server can instantly analyze market trend data, customer feedback, and the competitive landscape, and present the user with the optimal timing and strategy for entry via a terminal. In this way, decision-makers at the company can make quick, data-driven, and effective decisions.

[0639] The following describes the processing flow.

[0640] Step 1:

[0641] The server periodically extracts relevant corporate data from the company's internal database and collects various market data from external data sources via APIs. This includes news articles, social media posts, and industry reports.

[0642] Step 2:

[0643] The server cleanses the collected data. Specifically, it imputes missing values ​​and detects and removes outliers. It also standardizes the data format and converts text data into numerical vectors to extract features necessary for AI analysis.

[0644] Step 3:

[0645] The server feeds pre-processed data into an AI model and performs real-time data analysis. Here, important company metrics such as market share and sales trends are instantly visualized.

[0646] Step 4:

[0647] The server performs predictive analysis using machine learning models based on the analysis results. This generates scenarios for future market trends and product demand, creating materials for formulating optimal business strategies.

[0648] Step 5:

[0649] The terminal presents users with analysis results and predictive scenarios during board meetings and management conferences. It responds to user questions in real time and presents data-driven agenda items provided by AI.

[0650] Step 6:

[0651] The server analyzes the latest industry trend data based on past meeting records and decision-making history. This allows it to identify and suggest key topics that should be prioritized for discussion in the next meeting.

[0652] (Example 1)

[0653] 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".

[0654] In modern business management, effective decision-making based on vast amounts of internal and external data is essential. Achieving this requires a system that seamlessly handles data acquisition, preprocessing, analysis, and immediate delivery of results. However, traditional methods fragment these processes, making real-time decision-making support difficult. This hinders quick and accurate judgment, forcing many managers to waste time and resources.

[0655] 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.

[0656] In this invention, the server includes, as a data collection means, a mechanism for acquiring organizational data from an internal database and external data from an external data source; a data processing mechanism for purifying the acquired raw data and converting it into a numerical representation; and a data analysis mechanism for analyzing the processed data and immediately extracting business-related insights. This enables organizations to support real-time, precise data-driven decision-making and enhance their competitiveness.

[0657] A "data collection method" is a mechanism for extracting organizational data from an internal database and acquiring external data from external data sources.

[0658] A "data processing mechanism" is a method for purifying acquired raw data and converting it into a numerical representation.

[0659] A "data analysis mechanism" is a process for analyzing processed data and immediately extracting business-related insights.

[0660] A "predictive mechanism" is a system that uses learning models to predict future market changes and organizational performance, and to provide strategies based on those predictions.

[0661] The "decision-making support mechanism" is a process that presents insights and provides agenda items in real time during a meeting.

[0662] A "trend analysis mechanism" is a method for analyzing past history and providing future agenda items.

[0663] A "display surface" is an interface that provides information in response to user inquiries.

[0664] The present invention is a business intelligence system for supporting organizational decision-making, enabling effective decision-making through data collection, processing, analysis, and prediction. The following describes embodiments for carrying out this invention.

[0665] The system consists of servers, terminals, and users, each performing data processing according to its role. The servers function as data collection tools, periodically extracting financial data, sales information, and customer relationship data from the organization's databases. In addition, information from external data sources, such as news articles and social media, is collected using technologies like APIs and web scraping. This forms a broad information base necessary for decision-making.

[0666] The collected data is cleansed by a data processing mechanism on the server. Specifically, missing values ​​and outliers are removed using libraries such as Pandas and NumPy in the Python language. In addition, natural language processing is performed using NLTK and spaCy to convert text data into numerical representations, creating a dataset that can be analyzed by AI models. This improves data quality and increases the accuracy of the analysis.

[0667] The server inputs pre-processed data into an AI model and performs data analysis in real time. This analysis uses learning frameworks such as TensorFlow and PyTorch to clarify market trends and customer segmentation based on features extracted from the data. Subsequently, time series analysis and regression models are used to estimate future sales and market changes using a prediction mechanism. This process has a significant impact on a company's strategy formulation and risk management.

[0668] The terminal acts as a decision support mechanism, providing users with immediate analysis results. This involves using data visualization tools such as Tableau and Power BI to create an environment where users can intuitively view the data. Users can input prompts as needed to elicit responses from the generated AI model.

[0669] For example, if a user enters a prompt such as, "Forecast next quarter's sales and tell me the optimal time to enter a new market," the system can analyze the relevant data and provide appropriate action suggestions. This allows users to make quick, data-driven decisions.

[0670] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0671] Step 1:

[0672] The server accesses internal databases and external data sources for data collection. Inputs include corporate financial information, sales statistics, customer data, and data from external news articles and social media. The server utilizes APIs and scraping techniques to collect this data and outputs it as a standardized dataset. This collection process is performed regularly to ensure the completeness and timeliness of the information.

[0673] Step 2:

[0674] The server performs data preprocessing. It receives the unified formatted dataset output in step 1 as input. Specific actions include cleaning the raw data using Pandas and NumPy. After imputing missing values ​​and removing outliers, the data is converted into a format usable by the AI ​​model (e.g., numerical vectors). As a result, the system outputs the formatted dataset to the next processing step.

[0675] Step 3:

[0676] The server performs real-time data analysis. By using pre-processed data from Step 2 as input, it feeds it into an AI model (using TensorFlow or PyTorch) to instantly extract business-related insights. Specifically, this involves identifying customer segments and understanding market trends. The resulting insights are provided as output, forming the foundation for the next steps.

[0677] Step 4:

[0678] The server performs predictive analytics. Using the insights obtained in Step 3 as input, it uses a learning model to predict future market trends and organizational performance. Here, methods such as time series analysis and linear regression are employed. The output is predicted sales and market trends, which serve as foundational information for strategic planning.

[0679] Step 5:

[0680] The terminal provides decision support to the user. Output data from the server is used as input for visualization in Tableau and Power BI. The user can view this in real time and, if necessary, enter prompts to obtain more detailed analysis results. Specifically, prompts such as "Forecast next quarter's sales and tell me the optimal time for entering new markets" are used. As a result, concrete insights are presented to the user.

[0681] Step 6:

[0682] The server performs trend analysis. It analyzes past decision-making history and industry trend data as input and proposes future agenda items. Here, data mining techniques are used to compare past and present data and automatically suggest priority agenda items for the next meeting. This provides users with the information they need to strategically plan.

[0683] (Application Example 1)

[0684] 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".

[0685] In today's business environment, it is necessary to quickly interpret large amounts of data and utilize it for decision-making, but there is a lack of appropriate support systems for this purpose. Furthermore, there is a demand for real-time information based on individual consumer behavior and market trends, but no system exists that can efficiently achieve this.

[0686] 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.

[0687] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables companies to predict future market trends and provide personalized recommendations and real-time notifications to consumers.

[0688] "Data collection means" refers to a mechanism for obtaining necessary information from internal databases and external data sources.

[0689] "Data preprocessing means" refers to a system that has the function of cleansing collected raw data and converting it into a format suitable for analysis.

[0690] A "real-time data analysis method" is a technology that sequentially analyzes pre-processed data and immediately extracts insights relevant to business operations.

[0691] "Predictive analytics tools" are tools that use machine learning models to predict market trends and organizational performance in the future.

[0692] "Decision-making support tools" are means of supporting the decision-making process by presenting necessary analysis results and agenda items in real time during meetings.

[0693] "Trend analysis tools" are technologies that integrate historical data and market trends to propose future priority issues.

[0694] A "recommendation engine" is an algorithm that recommends products and services based on the user's behavior.

[0695] A "push notification method" is a communication method that reflects real-time market information and delivers messages directly to users.

[0696] The business support system implementing the present invention consists of multiple hardware and software components. The server acquires organizational data from internal and external data sources using data acquisition means. This data is cleansed and converted into feature vectors by data preprocessing means.

[0697] Pre-processed data is sequentially analyzed using real-time data analysis tools to extract business insights. This analysis utilizes AI models based on TensorFlow. The server also leverages machine learning models through predictive analytics tools to forecast the organization's future market trends and performance.

[0698] The device visualizes these insights and provides them to the user in real time. Furthermore, recommended products and sales information generated by the server are individually optimized by the recommendation engine and sent to the user via push notifications.

[0699] For example, when a user is online shopping, data on the products they have viewed is collected in real time, and an AI model recommends appropriate products to encourage their next purchase. A specific example is a prompt message generated and sent to the user saying, "Special offers related to items you've recently viewed are available for the upcoming big sale. Check the app for details!"

[0700] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0701] Step 1:

[0702] The server retrieves organizational data from internal databases and external data sources using data collection methods. Input data includes financial data, sales data, and social media posts. Output is a compilation of the collected raw data.

[0703] Step 2:

[0704] The server cleanses the raw data collected by the data preprocessing mechanism and converts it into feature vectors. The raw data obtained as input is then converted into a format suitable for analysis through missing value imputation and outlier removal. The output is a cleansed and feature-enhanced dataset.

[0705] Step 3:

[0706] The server uses real-time data analysis tools to sequentially analyze pre-processed data and extract business-related insights. The input data is analyzed using a TensorFlow-based generative AI model. The output provides insights into customer satisfaction and market share fluctuations.

[0707] Step 4:

[0708] The server leverages machine learning models through predictive analytics to forecast future market trends and performance for an organization. It receives analysis results as input and uses them to build future sales forecasts and product strategies. The output consists of predicted market trends and strategic recommendations.

[0709] Step 5:

[0710] The terminal uses decision support tools to visualize generated insights in real time and provide them to the user during the meeting. Input consists of prediction results and insights sent from the server. Output is visually represented data, allowing for quick identification of important agenda items.

[0711] Step 6:

[0712] The server also uses a recommendation engine to analyze user behavior data and generate personalized product and service information. Input data includes the user's browsing and purchase history, while output is appropriately personalized product recommendations based on that data.

[0713] Step 7:

[0714] The device notifies the user of personalized product recommendations and campaign information via push notifications. The input is product recommendations sent from the server, and the output is a notification message displayed on the user's device.

[0715] 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.

[0716] This invention relates to an AI system with enhanced capabilities to effectively support a company's decision-making process, particularly one that recognizes user emotions and incorporates them into decision-making. The system consists of data collection, data preprocessing, real-time data analysis, predictive analytics, decision support, trend analysis, and emotion recognition.

[0717] Data collection

[0718] The server periodically collects necessary data from the company's internal databases and external data sources. This includes financial data, sales data, news articles, social media posts, and industry reports.

[0719] Data preprocessing

[0720] The server cleanses the collected data, imputing missing values ​​and removing outliers. Furthermore, it transforms the data into features in a format that the model can learn from.

[0721] Real-time data analysis and predictive analytics

[0722] The server analyzes pre-processed data using an AI model, instantly extracts key business metrics, and predicts future market trends using machine learning techniques.

[0723] decision support

[0724] The device presents users with analysis results and predictive scenarios, and also responds to real-time questions during meetings. Furthermore, the AI ​​automatically generates and presents important agenda items to users, supporting efficient decision-making.

[0725] Trend Analysis

[0726] The server analyzes past records and industry trends to suggest priority agenda items for the next meeting. This allows meeting participants to prepare more effectively.

[0727] emotion recognition

[0728] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize emotions in real time. This allows the server to adjust the agenda and approach according to the emotional state. For example, if the user shows anxiety, it will provide more information and different perspectives.

[0729] For example, when discussing the market launch of a new product during a board meeting, the server analyzes market data and suggests the optimal strategy. The terminal also monitors the user's emotional state, recommending a challenging strategy if optimistic feelings are present, and a more conservative approach if concerns are expressed. This allows for the integration of user emotions into data-driven decision-making, leading to more balanced conclusions.

[0730] The following describes the processing flow.

[0731] Step 1:

[0732] The server collects various corporate data from the company's internal database and retrieves market data, news articles, and social media posts from external data sources via external APIs. This creates a comprehensive dataset.

[0733] Step 2:

[0734] The server performs data cleansing on the acquired data, imputing missing values ​​and detecting and removing outliers. It converts the data format to a standard format usable by the AI ​​model and prepares it for extracting necessary features.

[0735] Step 3:

[0736] The server processes pre-processed data through an AI model to extract business insights in real time. Market share and trend analysis are performed at this stage.

[0737] Step 4:

[0738] The server uses machine learning models to predict future market trends and company performance, and generates strategic scenarios based on the results.

[0739] Step 5:

[0740] The terminal displays real-time insights and predictive scenarios from the server during various meetings and provides immediate answers to user questions. It also dynamically suggests agenda items based on AI analysis to support meeting progress.

[0741] Step 6:

[0742] The device uses an emotion engine to analyze the user's facial expressions, tone of voice, and text input to recognize their emotional state in real time. This allows the system to reflect the user's emotions and perform appropriate agenda adjustments.

[0743] Step 7:

[0744] The server analyzes sentiment data and past decision-making history to suggest agenda items that should be prioritized in the next meeting. These suggestions are made in conjunction with trend data to help users select the most relevant agenda items.

[0745] (Example 2)

[0746] 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".

[0747] In corporate decision-making processes, it is necessary not only to conduct data-driven analysis but also to reflect the emotions of decision-makers. Current systems face the challenge of automatically and efficiently carrying out decision-making processes that take emotions into account. Furthermore, they lack the functionality to answer questions in real time during meetings and to automatically generate and present important agenda items.

[0748] 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.

[0749] In this invention, the server includes data collection means, data preprocessing means, and real-time data analysis means. This enables efficient extraction of insights from vast amounts of data and flexible responses that reflect user emotions in the decision-making process.

[0750] "Data collection means" refers to methods for obtaining company-related information and external information from internal information recording media and external information sources.

[0751] "Data preprocessing means" refers to the process of purifying collected raw data and converting it into characteristic numerical values.

[0752] "Immediate data analysis methods" refer to methods for quickly deriving business-related insights using prepared data.

[0753] "Predictive analytics" refers to technologies that utilize machine learning models to predict future market trends and company performance, and then propose concrete solutions.

[0754] A "decision-making support tool" is a tool that has the function of presenting information in real time during a meeting and automatically generating and proposing new agenda items.

[0755] "Trend analysis methods" are analytical techniques that propose future priority issues based on past records and industry trends.

[0756] "Emotion recognition means" refers to technologies that understand a user's emotions and take those emotions into consideration in the decision-making process.

[0757] This invention is an AI system for supporting corporate decision-making processes, and in particular, it has the function of recognizing user emotions and reflecting them in decision-making. This system is mainly composed of a server and terminals.

[0758] The server is equipped with data collection means to collect corporate-related and external information from internal information storage media and external information sources. This includes information retrieval using APIs and database access using SQL queries. The collected data is pre-processed using software such as Pandas and Scikit-learn to purify the data and convert it into characteristic values.

[0759] The server also uses machine learning libraries such as TensorFlow and PyTorch to gain business-related insights through immediate data analysis. Furthermore, it utilizes predictive analytics to forecast future market trends and company performance based on this data, generating concrete proposals.

[0760] The terminal has an interface for presenting analysis results to the user in real time and is equipped with decision support means for asking questions and providing agenda items during meetings. This interface allows the user to freely input prompts to the generated AI model. For example, by inputting a question such as "What will the sales forecast for the next quarter be?", a direct answer can be obtained.

[0761] The emotion recognition system built into the device collects and analyzes the user's facial expressions and tone of voice to recognize the emotions the user is expressing in real time. This includes data acquisition using a webcam and microphone. Based on this emotion information, the server optimizes decision-making according to the user's emotions, for example, by providing supplementary information if the user shows anxiety.

[0762] An example of a prompt using a generative AI model is: "When launching a new product, please suggest the optimal strategy that takes into account current trends and user sentiment."

[0763] Thus, the present invention is a system that can efficiently utilize large amounts of data and provide complete decision-making support, including the user's emotions.

[0764] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0765] Step 1:

[0766] The server collects information from internal information storage media and external information sources. It receives company-related information and external information as input and retrieves data using APIs. As output, it stores the collected data in raw data format.

[0767] Step 2:

[0768] The server preprocesses the collected raw data through cleansing and feature transformation. It accepts raw data as input and uses Pandas and Scikit-learn to remove outliers, impute missing values, and perform numerical transformations on the data. As output, it generates a preprocessed and analyzable dataset.

[0769] Step 3:

[0770] The server performs immediate data analysis using pre-processed data. It uses pre-processed data as input and performs analysis using TensorFlow or PyTorch to extract business-related insights. The output provides key business metrics.

[0771] Step 4:

[0772] The server performs predictive analysis based on the analysis results. It receives the results of data analysis as input and uses a machine learning model to predict future market trends and company performance. As output, it generates predictive data to propose specific scenarios.

[0773] Step 5:

[0774] The terminal presents analysis results and prediction scenarios to the user in real time. It receives prediction data sent from the server as input and displays answers to prompts in the user interface. Users can dynamically view results by entering questions through the terminal. The output provides information to support the user's decision-making.

[0775] Step 6:

[0776] The device analyzes the user's emotions through emotion recognition. It receives data from a webcam and microphone as input, and uses an emotion engine to analyze facial expressions and voice tone. As output, it sends the recognized emotion data to a server to help adjust decision-making in real time.

[0777] (Application Example 2)

[0778] 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".

[0779] In face-to-face services such as brick-and-mortar stores, it is difficult to recognize customer emotions in real time and propose appropriate services. Therefore, providing optimal services that meet customer needs and emotions is challenging, limiting the potential for improving customer satisfaction. Solving this problem and improving service quality is essential.

[0780] 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.

[0781] In this invention, the server includes, as a data collection means, means for collecting organizational data from an internal information storage device and external information from an external information source; data preprocessing means for cleansing the collected raw data and converting it into feature quantities; and emotion recognition means for analyzing the user's facial expressions and voice to recognize emotions and dynamically adjust the service provided. This makes it possible to provide services that reflect the customer's emotions in real time.

[0782] "Data collection means" refers to the function of collecting organizational data from internal information storage devices and collecting external information from external information sources.

[0783] "Data preprocessing means" refers to the process of cleansing collected raw data and converting it into features that can be easily handled by machine learning models.

[0784] A "real-time data analysis method" is a method for immediately analyzing pre-processed data and extracting important insights related to the activity.

[0785] "Predictive analytics" refers to technologies that use machine learning models to predict future market trends and organizational performance, and to propose appropriate scenarios.

[0786] A "decision-making support tool" is a system that facilitates decision-making by providing real-time opinions and proposing agenda items during a meeting.

[0787] "Trend analysis methods" are techniques for analyzing past records and effectively prioritizing future agenda items.

[0788] An "emotion recognition system" is a system that identifies emotions by analyzing the user's facial expressions and voice, and dynamically adjusts services and suggestions based on that state.

[0789] This invention realizes a system that recognizes customer emotions in a physical store and dynamically adjusts service content based on those emotions. The system utilizes smart glasses as its main hardware, collects data through various means, and performs emotion recognition after processing.

[0790] The server collects necessary data from information storage devices and external information sources. For example, it incorporates past customer purchase history and industry trends to form the foundational data for service provision. The collected data is cleansed using data preprocessing means and converted into analyzable features. The preprocessed data is quickly analyzed by real-time data analysis means, and valuable insights are provided to the user.

[0791] The smart glasses, which serve as the terminal, capture and analyze the customer's facial expressions and voice in real time as a means of emotion recognition. The software used is a deep learning framework such as TensorFlow or PyTorch. This allows the service content to be determined based on the customer's emotions. For example, if the customer is smiling, it would be appropriate to provide more detailed product information.

[0792] The generative AI model dynamically adjusts the service suggestions based on the input provided by the user. An example of a prompt is, "Infer the customer's purchase intent from their facial expressions and suggest actions that will lead to sales promotion." This prompt allows the AI ​​model to uncover the customer's latent needs and generate the optimal customer service approach.

[0793] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0794] Step 1:

[0795] The server collects organizational data from internal storage devices and external information from external information sources. The input at this stage consists of data obtained from both internal storage devices and external information sources. The server aggregates this data and outputs it as raw data.

[0796] Step 2:

[0797] The server cleanses the raw data and converts it into features. The input is the raw data from step 1, which is then cleansed to remove noise and processed to extract the necessary information. The output is clean feature data suitable for analysis.

[0798] Step 3:

[0799] The server analyzes feature data in real time and extracts key insights. The input is the feature data obtained in step 2, and data calculations are performed using machine learning algorithms. The output is business-related insights.

[0800] Step 4:

[0801] The smart glasses, which act as the terminal, capture the customer's facial expressions and voice and perform emotion recognition. The input is real-time customer data from the camera and microphone. Emotion recognition software analyzes this data and performs data calculations to identify the emotional state. The output is the customer's emotional state.

[0802] Step 5:

[0803] The server generates adaptive service suggestions based on the emotional state. The inputs are the emotional state from step 4 and the business insights from step 3. The generating AI model processes the data according to the prompts and outputs specific service suggestions.

[0804] Step 6:

[0805] The user, acting as a store employee, presents the customer with the most suitable service suggestions through the display of smart glasses. The input is the service suggestion from step 5, which the user applies and uses to approach the customer. The output is the customer's service satisfaction.

[0806] 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.

[0807] 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.

[0808] 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 robot 414.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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."

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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 as being incorporated by reference.

[0827] The following is further disclosed regarding the embodiments described above.

[0828] (Claim 1)

[0829] As a means of data collection, it includes means for collecting corporate data from an internal database and external data from external data sources.

[0830] A data preprocessing means for cleansing collected raw data and converting it into features,

[0831] A real-time data analysis method that analyzes pre-processed data and extracts business-related insights,

[0832] A predictive analytics tool that uses machine learning models to forecast future market trends and company performance, and proposes scenarios.

[0833] A decision-making support tool that presents real-time insights and proposes agenda items during meetings,

[0834] A trend analysis tool that analyzes past records and proposes future agenda items,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, characterized in that the decision support means has an interface that presents information in response to a user's question.

[0838] (Claim 3)

[0839] The system according to claim 1, characterized in that the trend analysis means preferentially proposes the agenda for the next meeting based on past decision-making history and industry trend data.

[0840] "Example 1"

[0841] (Claim 1)

[0842] As a means of data collection, a mechanism for acquiring organizational data from an internal database and external data from an external data source,

[0843] A data processing mechanism that purifies the acquired raw data and converts it into a numerical representation,

[0844] A data analysis mechanism that analyzes processed data and immediately extracts business-related insights,

[0845] A forecasting mechanism that uses learning models to predict future market changes and organizational performance, and provides strategies.

[0846] A decision-making support mechanism that provides immediate insights and agenda items during the meeting,

[0847] A trend analysis organization that analyzes past history and provides future agenda items,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, characterized in that the decision support mechanism has a display surface that provides information in response to a user's question.

[0851] (Claim 3)

[0852] The system according to claim 1, characterized in that the trend analysis mechanism preferentially proposes the agenda for the next meeting based on past decision history and industry trend data.

[0853] "Application Example 1"

[0854] (Claim 1)

[0855] The data collection means include a means for collecting organizational data from an internal database and external data from an external data source.

[0856] A data preprocessing means for cleansing collected raw data and converting it into a feature vector,

[0857] A real-time data analysis method that analyzes pre-processed data and extracts business-related insights,

[0858] A predictive analytics tool that uses machine learning models to forecast future market trends and organizational performance, and proposes options.

[0859] A decision-making support tool that presents real-time insights and proposes agenda items during meetings,

[0860] A trend analysis tool that analyzes past records and proposes future agenda items,

[0861] A recommendation engine that provides individually optimized products and sales information based on user behavior data,

[0862] A push notification method for sending notifications that reflect real-time market trends,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, characterized in that the decision support means has an interface that presents information in response to a user's question.

[0866] (Claim 3)

[0867] The system according to claim 1, characterized in that the trend analysis means preferentially proposes the agenda for the next meeting based on past decision-making history and industry trend data.

[0868] "Example 2 of combining an emotion engine"

[0869] (Claim 1)

[0870] As a means of data collection, it includes means for collecting company-related information from an internal information recording medium and external information from an external information source.

[0871] A data preprocessing means for purifying the collected raw data and converting it into characteristic numerical values,

[0872] An immediate data analysis method that analyzes pre-processed data and extracts business-related insights,

[0873] A predictive analytics tool that uses machine learning models to forecast future market trends and corporate performance, and proposes solutions.

[0874] A decision-making support tool that presents insights in real time during meetings and proposes agenda items,

[0875] A trend analysis method that analyzes records over time and proposes future agenda items,

[0876] An emotion recognition means that recognizes the user's emotions and optimizes decision-making based on those emotions,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, characterized in that the decision support means has an interface that presents information in response to user questions, and also automatically generates and presents important agenda items.

[0880] (Claim 3)

[0881] The system according to claim 1, characterized in that the trend analysis means prioritizes proposing the next meeting agenda based on past decision-making history and industry trend data, and adjusts it while taking into account the user's feelings.

[0882] "Application example 2 of combining emotional engines"

[0883] (Claim 1)

[0884] The data collection means includes means for collecting organizational data from internal information storage devices and external information from external information sources.

[0885] A data preprocessing means for cleansing collected raw data and converting it into features,

[0886] A real-time data analysis means for analyzing pre-processed data and extracting insights related to the activity,

[0887] A predictive analytics tool that uses machine learning models to forecast future market trends and organizational outcomes, and proposes scenarios.

[0888] A decision-making support tool that presents views in real time during meetings and proposes agenda items,

[0889] A trend analysis tool that analyzes past records and proposes future agenda items,

[0890] An emotion recognition means that analyzes the user's facial expressions and voice to recognize emotions and dynamically adjust the content of the service provided,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, characterized in that the decision support means has an interface that presents information in response to a user's question and adaptively changes the proposed content based on the user's emotional state obtained by the emotion recognition means.

[0894] (Claim 3)

[0895] The system according to claim 1, characterized in that the trend analysis means and emotion recognition means preferentially suggest the agenda for the next meeting based on past decision-making history, industry trend data, and the user's emotion history. [Explanation of Symbols]

[0896] 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. As a means of data collection, it includes means for collecting corporate data from an internal database and external data from external data sources. A data preprocessing means for cleansing collected raw data and converting it into features, A real-time data analysis method that analyzes pre-processed data and extracts business-related insights, A predictive analytics tool that uses machine learning models to forecast future market trends and company performance, and proposes scenarios. A decision-making support tool that presents real-time insights and proposes agenda items during meetings, A trend analysis tool that analyzes past records and proposes future agenda items, A system that includes this.

2. The system according to claim 1, characterized in that the decision support means has an interface that presents information in response to a user's question.

3. The system according to claim 1, characterized in that the trend analysis means preferentially proposes the agenda for the next meeting based on past decision-making history and industry trend data.

Images