system

Abstract

Provide a system. 【Solution means】 Means for collecting information from a data source via a network, Means for preprocessing, cleaning, and structuring the collected information, Means for analyzing the preprocessed information and generating an analysis result, Means for automatically generating a business strategy based on the analysis result, Means for providing the generated business strategy to a user terminal, Means for generating information to support an investment decision based on the analysis result, Means for providing the generated investment decision information to a user terminal, Means for receiving feedback information from a user and using it for learning and model optimization, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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 venture companies, formulating business plans and raising funds are important issues, and it is required to carry them out efficiently. Also, for investors, making appropriate investment decisions from numerous investment target companies and maximizing investment effects are the top priorities. However, there is a lack of effective tools for selecting important data from a vast amount of information and appropriately analyzing and utilizing it.

Means for Solving the Problems

[0005] This invention provides a system that collects information from diverse data sources via a network and transforms it into useful data through effective preprocessing. This system can analyze the preprocessed information using generative AI and automatically generate business strategies based on that analysis. Similarly, it generates and provides information from the analysis results to support investment decisions. This mechanism assists entrepreneurs in formulating strategic business plans and provides investors with information to guide accurate investment decisions. Furthermore, the AI ​​model can be continuously optimized based on user feedback, further improving the accuracy of future proposals and decisions.

[0006] A "network" is a communication infrastructure that connects to various information sources to acquire and transmit data.

[0007] A "data source" is a source of information that provides a set of publicly available or accessible data that is the subject of information collection.

[0008] "Information" refers to a collection of data gathered for the purpose of formulating business strategies and making investment decisions.

[0009] "Collection" refers to the process of accumulating target data from data sources.

[0010] "Preprocessing" is the process of removing noise from collected information and preparing it in a format that can be analyzed.

[0011] "Cleaning" is the process of removing errors and duplicates from data, ensuring data consistency.

[0012] "Structuring" is the process of transforming raw data into a structured format to facilitate its use in databases and models.

[0013] "Analysis" is the process of analyzing data to derive meaningful patterns and information from it.

[0014] "Analysis results" refer to a collection of conclusions and insights obtained through data analysis.

[0015] "Business strategy" refers to the plans and policies formulated by an enterprise to build a competitive advantage in the market.

[0016] "Automatic generation" refers to the function of a system to create results or outputs using algorithms without human intervention.

[0017] "User terminal" refers to an electronic device through which a user interfaces with a system.

[0018] "Investment decision" refers to an evaluation process by which an investor determines the target and timing for capital investment.

[0019] "Feedback information" refers to data by which a user reports usage results and satisfaction levels to a system.

[0020] "Learning" refers to the operation of a system to adjust its own algorithms based on new data and feedback information for optimization.

[0021] "Model optimization" refers to the process by which an AI model within a system improves its performance through iterative improvement.

Brief Description of Drawings

[0022] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] Note: There seems to be an incorrect symbol "并" in line ID=32 in the original text. It might be a typo. The translation is done as it is presented in the original.It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0023] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

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

[0025] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0026] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0027] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0028] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0029] 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."

[0030] [First Embodiment]

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

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0037] 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.

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

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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".

[0043] This invention relates to a system that collects information from diverse data sources via a network, preprocesses and analyzes it, and automatically generates and provides information useful for business strategy and investment decisions. This system achieves these processes by utilizing generative AI through a specific algorithm.

[0044] First, the server utilizes communication infrastructure to collect information via the internet. For example, it retrieves news articles, social media posts, and publicly available company reports via crawling or APIs. Next, the server verifies the integrity of the retrieved information and preprocesses it to remove noise and unnecessary data.

[0045] The pre-processed information is analyzed by the server using natural language processing and machine learning techniques. The analysis extracts highly relevant business insights, which are then used to formulate business strategies. For example, market trends and competitor analysis are conducted, leading to concrete proposals for new market entry strategies and product lineups.

[0046] Furthermore, for investors, the server generates reports evaluating companies' financial health and growth forecasts based on the analysis results. This provides information to help them determine which companies are worth investing in.

[0047] Users (entrepreneurs or investors) receive these analysis results and suggestions through their devices. For example, if a user is considering launching a new business, they can develop a business plan based on the market strategy presented by the server. If a user is considering investing in a particular startup, they can refer to the server's analysis report to assess the risks and use it to help make an investment decision.

[0048] Furthermore, user feedback is collected by the server and used to improve the AI ​​model. This enhances the accuracy and effectiveness of suggestions, strengthening support for future strategy formulation and investment decisions.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The server accesses data sources via the internet and collects the necessary information. In this process, it uses crawlers to collect data from news sites and social media, as well as to obtain publicly available company information through APIs.

[0052] Step 2:

[0053] The server preprocesses the collected information. In this process, natural language processing techniques are used to normalize the text data and remove noise. The information is also categorized and organized into structured data.

[0054] Step 3:

[0055] The server analyzes pre-processed data. Specifically, it uses machine learning models to conduct market trend and competitor analysis, extracting meaningful business insights. This data is then visualized in statistical metrics and graphs.

[0056] Step 4:

[0057] The server automatically generates business strategies based on the analysis results. In this process, the generating AI creates specific strategic proposals, such as strategies for entering new markets and measures to enhance existing products.

[0058] Step 5:

[0059] The server generates information to support investment decisions and creates company evaluation reports. This includes evaluating financial indicators and forecasting growth.

[0060] Step 6:

[0061] Users (entrepreneurs or investors) view analysis results and suggestions provided by the server from their terminals. Based on this, users develop their own business plans or make investment decisions.

[0062] Step 7:

[0063] Users send feedback on the suggestions and analyses they use to the server via their device. Based on this feedback, the server updates the AI ​​model to improve the accuracy of future suggestions and decisions.

[0064] (Example 1)

[0065] 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."

[0066] Efficiently collecting, integrating, and analyzing vast amounts of diverse information from various data sources, and then quickly and accurately providing business strategies and investment decisions based on that information, is a critical challenge in modern economic activity. This process requires advanced technical skills and efficient methods for information preprocessing, noise reduction, and improving the accuracy of analysis results. Furthermore, methods for effectively utilizing user feedback to continuously improve the accuracy of future proposals are also essential.

[0067] 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.

[0068] In this invention, the server includes means for collecting information from a data set via a network, means for preprocessing and structuring the collected information, and means for analyzing the data using natural language processing and machine learning techniques. This enables the efficient integration of diverse information and the provision of business strategies and investment decisions based on advanced analysis.

[0069] A "network" is a connection infrastructure used by computers and devices to communicate with each other, and is a structure that enables the sending and receiving of information.

[0070] A "data set" refers to a collection of information gathered for a specific purpose, and it may include numbers, characters, symbols, and other elements.

[0071] "Preprocessing" refers to the process of removing unnecessary data from collected information, imputing missing values, and preparing the data in a format that is easy to analyze.

[0072] "Structuring" refers to organizing data according to certain rules to make it easier to handle, thereby enabling efficient analysis.

[0073] "Analysis" is the act of using techniques such as natural language processing and machine learning to derive useful insights and patterns from collected and pre-processed information.

[0074] "Business strategy" refers to long-term plans and policies for corporate activities, which are determined by taking into account market trends and the situation of competitors.

[0075] "Investment decisions" refer to the process of determining which companies or projects should receive capital investment, based on financial data and market analysis.

[0076] "Feedback" refers to evaluations and opinions provided by users, and is information used to improve the system and enhance the accuracy of the model.

[0077] "Natural language processing" is a technology that enables computers to understand, interpret, and generate language that humans use on a daily basis.

[0078] Machine learning is a technology that enables computers to find patterns in data and automatically make predictions and decisions.

[0079] This invention is a data analysis system in which a server, terminal, and user work together to utilize information obtained via a network. The server collects information from multiple data sets and efficiently integrates and analyzes that information to enable business strategies and investment decisions.

[0080] The server collects information in real time using news APIs and social media APIs via the internet. The collected information is converted into a data frame using the Python Pandas library, and preprocessing is performed to impute missing values ​​and filter out noise. Subsequently, the information is analyzed using the NLTK library for natural language processing and generative AI models from TENSORFLOW® and OpenAI® for machine learning.

[0081] The analyzed data is used for business strategies and investment decisions. Business strategies are automatically generated based on market trends and competitive analysis. Specific examples include optimizing the timing of new product launches and reviewing product lineups. Investment decisions are evaluated based on a company's financial health and growth forecasts, contributing to the selection of investment targets.

[0082] Users receive the results of business strategies and investment decisions provided via their devices. By accessing the dashboard, users can visually review the analysis results and decide on necessary actions. For example, if a user is looking for a specific strategy to enter a new market, the server will present specific suggestions based on a prompt such as, "Please propose a strategy for entering a new market. This strategy should be based on recent industry trends and competitive analysis."

[0083] Furthermore, user feedback is collected by the server and used as training data for the generated AI model. This allows for model improvement based on feedback, thereby improving the accuracy of future suggestions.

[0084] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0085] Step 1:

[0086] The server first collects information via the internet. At this stage, it utilizes news APIs and social media APIs to obtain real-time data. The input is raw data obtained from the APIs, and the output is that data in its raw form. This raw data includes information such as the article title, body text, publication date and time, and source. Specifically, the server queries the APIs at regular intervals and executes scripts to retrieve new data.

[0087] Step 2:

[0088] The server performs preprocessing on the collected data. This preprocessing uses the Python Pandas library to convert the data into a data frame and performs missing value imputation and noise filtering. The input is the raw data obtained in step 1, and the output is a clean, prepared dataset. Specifically, the server fills in missing values ​​with the mean or median, and deletes rows that do not meet certain conditions. It also performs text tokenization and stop word removal using NLTK.

[0089] Step 3:

[0090] The server performs analysis on the pre-processed data. This analysis utilizes natural language processing and machine learning techniques, employing TensorFlow and generative AI models. The input is the clean dataset obtained in step 2, and the output is the analysis results, i.e., business insights. Specifically, the AI ​​model is fed context, and topic modeling and sentiment analysis are performed to extract key trends and customer sentiment.

[0091] Step 4:

[0092] The server automatically generates business strategies and investment decisions based on the analysis results. It utilizes a generating AI model to form specific recommended strategies and decision-making information. The input is the analysis results obtained in step 3, and the output is specific strategy proposals and investment reports. Specifically, the generating AI model performs evaluations, automatically generates strategy documents and reports, and customizes them as needed to match user-specified conditions.

[0093] Step 5:

[0094] The server provides the generated business strategies and investment decisions to the user's terminal. This allows the user to review the strategies and take necessary actions. The input is the output generated in step 4, and the output is displayed in a format that is easy for the user to understand. Specifically, the server displays the results on a dashboard via a web browser or a dedicated application.

[0095] Step 6:

[0096] Users provide feedback. They input their opinions and evaluations of the analysis results and suggestions through their terminals. The input is user feedback, and the output is feedback data sent to the server. Specifically, users use a feedback form to input satisfaction ratings and improvement requests.

[0097] Step 7:

[0098] The server receives feedback information from users and uses it to train the AI ​​model. Based on the feedback, it adjusts the model's parameters to improve the accuracy of future strategic suggestions and investment decisions. The input is the feedback data obtained in step 6, and the output is the improved AI model's parameter settings. Specifically, the server feeds the feedback data into the learning algorithm and retrains the model.

[0099] (Application Example 1)

[0100] 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."

[0101] Conventional information analysis systems struggle to effectively collect and analyze large amounts of data, particularly in response to the need for rapid, real-time decision-making regarding business strategies and resource allocation. Furthermore, a lack of clear and visually appealing methods for representing analysis results has prevented users from fully utilizing the information they obtain in their actual work. Additionally, continuous model optimization and incorporation of user feedback to improve the accuracy of generated information are insufficient.

[0102] 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.

[0103] In this invention, the server includes means for collecting data from information sources via a network, means for preprocessing, cleaning, and structuring the collected data, means for analyzing the preprocessed data and generating analysis results, and means for displaying the analysis results using a visual display based on augmented reality technology. This enables users to visually check various types of information in real time and make quick and accurate decisions regarding business strategies and resource allocation.

[0104] "Means of collecting data from information sources via a network" refers to the function of obtaining information from various data sources such as news articles, company reports, and social media via the internet or intranet.

[0105] "Methods for preprocessing, cleaning, and structuring collected data" refers to the process of checking the integrity and quality of acquired data, removing and organizing noise, and converting it into a form that is easy to analyze.

[0106] "Means for analyzing pre-processed data and generating analysis results" refers to a function that uses machine learning and natural language processing techniques to execute algorithms that derive useful business insights and trends from cleaned data.

[0107] "Means of displaying analysis results based on augmented reality technology using visual displays" refers to a function that utilizes augmented reality (AR) to provide users with an easy-to-understand graphical visual representation of analysis results.

[0108] "Business strategy" refers to plans and guidelines that companies and organizations formulate to respond to market trends and competitive situations based on collected and analyzed information.

[0109] "Information that supports resource allocation decisions" refers to data and analytical results that assist in determining which business areas or projects should receive the most resources.

[0110] "User's device" refers to a terminal used to view or operate information provided by the system, such as a smartphone, tablet, or personal computer.

[0111] "Means of receiving evaluation information and using it for learning and model optimization" refers to the process of collecting feedback from users, updating the AI ​​model based on that feedback, and improving the accuracy of future suggestions and analyses.

[0112] The system implementing this invention leverages a network infrastructure that includes cloud-based servers and user equipment. The servers automatically collect data from diverse sources on the internet, such as news articles, company reports, and social media, using advanced data collection programs. This data is preprocessed in real time on streaming platforms such as Apache® Kafka, where noise is removed and the data is formatted. The collected data is then analyzed using natural language processing and machine learning techniques, utilizing Amazon SageMaker and Google® Cloud AI Platform. Generative AI models are used to extract information from the data that supports business insights and resource allocation decisions.

[0113] The user's device has an interface to receive analysis results and present them to the user visually. This utilizes augmented reality (AR) applications and graphical displays implemented with Unity or React Native. As a result, the user can intuitively understand the analysis results and make effective business strategy and resource allocation decisions in real time.

[0114] Specifically, when a user enters prompts such as, "What are the current trends in the renewable energy industry?" or "Show me the growth forecast for technology companies in the next quarter," the server collects and analyzes relevant information and sends the results to the user's device. Based on this information, the user can quickly proceed with the decision-making process. Evaluations and feedback from the user are continuously sent to the server, so the accuracy of the model and the effectiveness of the suggestions continue to improve.

[0115] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0116] Step 1:

[0117] The server collects data from multiple sources via the internet. Specifically, it retrieves news articles, company reports, and social media data using APIs or web crawling technologies. Inputs include target keywords and URLs, and output is the original data.

[0118] Step 2:

[0119] The server preprocesses the acquired data. This process verifies data integrity, removes duplicates and noise, and structures the data. The input is the raw data acquired in step 1, and the output is a clean and organized dataset. Specifically, a text cleaning algorithm is used to remove extraneous symbols and spaces.

[0120] Step 3:

[0121] The server utilizes a generative AI model to analyze the preprocessed data. Through natural language processing algorithms, it extracts useful business insights and patterns from the data. The input is the data cleaned in step 2, and the output is the insights and trends obtained through the analysis. Specifically, a machine learning model operates to identify key features from the dataset.

[0122] Step 4:

[0123] The user's device receives the analysis results sent from the server and displays them visually. This process uses augmented reality technology to present information visually. The input is the analysis results generated in step 3, and the output is a visual display that the user can view. Specifically, the Unity or React Native platform is used, and interactive displays utilizing AR are implemented.

[0124] Step 5:

[0125] The user makes a decision based on the information provided and sends feedback to the server. This user feedback is used for the next model retraining. The input is the user's evaluation and improvement requests, and the output is the feedback data sent to the server. Specifically, the user inputs comments and evaluation scores through the application interface.

[0126] Step 6:

[0127] The server receives feedback from the user and retrains the generated AI model. In this phase, the improved model is used for subsequent analyses. The input is the feedback data received in step 5, and the output is the new model with improved accuracy. Specifically, the server adjusts the model's hyperparameters using the feedback data and then retrains it.

[0128] 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.

[0129] This invention provides a system that improves the accuracy of strategic and investment information by combining a system that collects, preprocesses, and analyzes data via a network and automatically generates business strategies and investment decisions based on that data with an emotion engine that recognizes user emotions.

[0130] First, the server collects information from various data sources via the network as usual, performs noise reduction and information cleaning, and prepares it as structured data. Next, the server analyzes the collected information and extracts business insights. Based on these results, it automatically generates information for business strategy and investment decisions using AI.

[0131] The emotion engine in this system recognizes the user's emotions through voice, facial expressions, text input, and other data while the user is using the device. The server receives this emotion data and customizes business strategies and investment decision information according to the user's emotions. For example, if the user is showing anxiety, the system will enhance strategic suggestions to mitigate risks and prioritize presenting information that provides reassurance.

[0132] As a concrete example, consider a scenario where a user is considering investing in a new business. The server analyzes the collected data to predict market growth and conduct competitive analysis, generating a business strategy. Meanwhile, the emotion engine evaluates how the user feels about the information presented. If the emotion data indicates that the user is overly optimistic, the server will perform a reality check, emphasizing realistic risks to support a balanced decision.

[0133] Thus, systems equipped with an emotion engine provide strategic recommendations and investment information that reflect the user's psychological state, enabling more personalized decision-making support. This approach is crucial for enhancing the influence on user behavior and decisions compared to conventional information delivery methods.

[0134] The following describes the processing flow.

[0135] Step 1:

[0136] The server collects data from news articles, social media, and publicly available corporate data via the network. It uses crawlers and APIs to efficiently retrieve the necessary information.

[0137] Step 2:

[0138] The server preprocesses the collected data. Specifically, it removes noise, normalizes text, and categorizes the data to prepare it as analyzable structured data.

[0139] Step 3:

[0140] The server analyzes the pre-processed data. It applies machine learning algorithms to analyze market trends and competitor activities, extracting business insights. At this stage, the analysis results are formatted as statistical indicators and visual data.

[0141] Step 4:

[0142] The server automatically generates business strategies based on the analysis results. Utilizing the AI-generated strategies, it specifically proposes measures for developing new markets and strengthening existing strategies.

[0143] Step 5:

[0144] Users receive strategic proposals and investment information generated by the server through their devices. At this stage, the information is displayed in a user-friendly interface, making it easy to view.

[0145] Step 6:

[0146] The emotion engine built into the device recognizes the user's emotional state. Through voice recognition, facial expression analysis, and text input analysis, it identifies what emotions the user is experiencing.

[0147] Step 7:

[0148] The server adjusts the input information based on the user's emotional data obtained from the emotion engine. For example, if the user is feeling anxious, the server adjusts the output by emphasizing more detailed explanations to provide reassurance or suggestions to mitigate risks.

[0149] Step 8:

[0150] Users can view personalized, emotion-based suggestions on their devices to aid in business planning and investment decisions. The goal is to improve the quality of decision-making based on the information provided.

[0151] Step 9:

[0152] User feedback is sent to the server via the device. The server uses this information to update the AI ​​model, continuously improving the overall accuracy and effectiveness of the system.

[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 today's diverse business environment, business strategies and investment decisions must not only be based on data analysis but also consider the emotions and psychological states of individual users. However, conventional systems do not adequately provide information that takes user emotions into account, resulting in a lack of accuracy in providing personalized decision support. There is a need to solve this problem and realize more effective decision support.

[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 means for collecting data from information sources via a network, means for preprocessing, cleaning, and structuring the collected data, means for analyzing the preprocessed data and extracting the analysis results, and means for identifying the user's emotions and adjusting business strategy and investment decision information according to the identified emotions. This makes it possible to provide strategies and investment decisions that reflect the user's emotions.

[0158] A "network" refers to a connection between multiple computers or devices built to send and receive data.

[0159] "Information source" refers to the database, online platform, or other data provision infrastructure from which data is obtained.

[0160] "Data collection" refers to the process of gathering information from various sources to achieve a specific purpose.

[0161] "Preprocessing" refers to the process of removing noise and imputing missing values ​​in order to convert raw data into an analyzable format.

[0162] "Data cleanup" refers to the process of deleting or correcting unnecessary or incorrect information in order to improve data quality.

[0163] "Data structuring" refers to the process of organizing collected information into a specific format to make it easier to handle.

[0164] "Analysis" refers to the process of analyzing data to uncover hidden patterns and useful information.

[0165] "Generative AI" refers to a type of artificial intelligence that generates new content such as text and images based on presented data and prompts.

[0166] "Business strategy" refers to the plans and policies that a company or organization aims to achieve in order to accomplish its ultimate goals.

[0167] "Investment decision" refers to the evaluation and selection process used to determine which businesses or projects to allocate capital to.

[0168] "Emotional identification" refers to the process of interpreting a user's psychological state and emotions from their words, facial expressions, and actions.

[0169] "Adjustment" refers to the act of making changes to optimize existing plans and policies as needed or in accordance with the circumstances.

[0170] "Feedback" refers to information and evaluations received regarding actions and results, which are used as a reference for improvement.

[0171] "Learning" refers to the process of acquiring knowledge and skills based on experience and information, and improving one's abilities.

[0172] This invention realizes a system that can provide users with optimized business strategies and investment decisions by utilizing multiple means. Specific embodiments thereof are shown below.

[0173] Data acquisition and preprocessing

[0174] The server first collects data from various sources via the network. Specifically, it uses social media platforms, news websites, and economic databases as sources. The Python requests library is used to retrieve the data. Next, the Python Pandas library is used to clean and structure the collected data. This removes noise and irrelevant information and prepares it in a format suitable for analysis.

[0175] Strategy generation using data analysis and generative AI.

[0176] The server analyzes pre-processed data and extracts business insights. The analysis uses the Scikit-learn library to perform cluster analysis and regression analysis. Furthermore, a generative AI model is used to automatically generate strategies and investment decisions based on the extracted insights. In this process, a large-scale language model is used for the generative AI, and an example of a prompt is, "Please propose an investment strategy for the next quarter based on market trends, but please take into account the concerns expressed by the user."

[0177] Emotion recognition and information customization

[0178] The device uses its camera and microphone to collect facial expressions and voice to recognize the user's emotions. The collected data is processed by an emotion analysis algorithm to evaluate the user's current psychological state. Based on this emotion data, the server customizes strategies and investment information. For example, if the user indicates anxiety, the server strengthens suggestions to mitigate risk.

[0179] Application examples

[0180] As a practical example, consider a user considering investing in a new business. In this case, the server performs market analysis and proposes a strategy based on the competitive landscape and growth forecasts. Meanwhile, the terminal analyzes the user's reactions and provides additional reassuring information if the user is feeling anxious. This allows the user to make a more balanced decision.

[0181] Thus, by combining data analysis and emotion recognition, this invention can provide decision-making support tailored to the individual needs of each user.

[0182] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0183] Step 1:

[0184] The server collects data from information sources via the network. Specifically, the server uses APIs to retrieve text data from social media and news sites. This input data includes posts and articles in text format. The retrieved data is temporarily stored in a database.

[0185] Step 2:

[0186] The server preprocesses the collected raw data. It uses Python's regular expression tools to remove unwanted characters and noise. It also cleans the data and imputes missing values ​​using the Pandas library. This process yields analyzable structured data. The output is formatted text data.

[0187] Step 3:

[0188] The server analyzes preprocessed data using machine learning models. Scikit-learn is used for the analysis, building cluster analysis and regression models. Preprocessed data is provided as input. The output is information about specific patterns and trends, known as extracted business insights.

[0189] Step 4:

[0190] The server inputs prompt messages into the generating AI model and generates strategies and investment decisions based on the analysis results. Specifically, it uses prompt messages such as, "Please propose an investment strategy for the next quarter based on market trends." The output is text-based information regarding strategy proposals and investment decisions.

[0191] Step 5:

[0192] The device uses a camera and microphone to collect voice and facial expression data to identify the user's emotions. The input is real-time data from the user. The acquired emotion data is processed by an emotion analysis algorithm to identify the user's emotional state. This result is output as an emotion score.

[0193] Step 6:

[0194] The server customizes generated strategies and investment decisions based on sentiment data. Specifically, if the user indicates anxiety, it adjusts the information to emphasize suggestions for risk reduction. The output is customized strategic information tailored to the user's emotions.

[0195] Step 7:

[0196] The server transmits customized information to the terminal and presents it to the user. The terminal visually presents the received information to the user through an output device such as a display. This allows the user to review strategic information and use it to aid in decision-making.

[0197] (Application Example 2)

[0198] 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."

[0199] Conventional data analysis systems provide information generated without considering the user's psychological state or emotions, resulting in challenges in personalizing and accurately conveying information that contributes to user decision-making. Furthermore, in e-commerce, appropriate information is often not presented to effectively increase user purchasing intent. In this context, there is a need for strategic proposals and purchase-promoting information that take user emotions into account.

[0200] 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.

[0201] In this invention, the server includes means for collecting information from a data source via a network, means for preprocessing, cleaning, and structuring the collected information, and means for analyzing the preprocessed information and generating analysis results. This makes it possible to recognize the user's emotions, adjust the information based on those emotions, and provide personalized strategic suggestions and purchase promotion information.

[0202] A "network" is a system in which computers and other devices are connected to communicate information.

[0203] A "data source" refers to the place or system from which information is acquired, and it provides data in various formats.

[0204] "Preprocessing" refers to the process of preparing data for analysis, and includes steps such as noise reduction and data organization.

[0205] "Information cleaning" is the process of removing inaccurate or unnecessary parts from data and preparing it to be usable.

[0206] "Structuring" refers to organizing data into a specific format, thereby making it easier to analyze and search.

[0207] "Analysis results" refer to the output obtained after data analysis, including conclusions or insights based on the intended analysis.

[0208] "Business policy" refers to the strategies and plans for achieving business objectives, indicating the direction and activities that a company should adopt.

[0209] A "user terminal" is a device used by a user to receive and process information, and includes smartphones and personal computers.

[0210] "Feedback information" refers to information such as opinions and evaluations obtained from users that contribute to the improvement of a system or process.

[0211] "Learning and model optimization" is the process of adjusting a machine learning model using new data to improve it.

[0212] "User emotions" refers to the mental or psychological state that users exhibit while using the system, and is an element on which information is adjusted.

[0213] "Purchase promotion information" refers to incentives and marketing information provided to increase users' motivation to purchase products or services.

[0214] To implement this invention, the server first collects information from multiple data sources using a network. The collected data undergoes information cleaning and preprocessing and is converted into a structured format. Next, the server analyzes the preprocessed information using data analysis software and outputs the results as business policy and investment decision information using a generating AI model.

[0215] The emotion engine uses smartphones and other user devices to recognize the user's emotions from voice data, text data, and facial expression data. Based on the user's emotion data, the server adaptively adjusts the generated business policies and investment decision information. In particular, if the emotion engine detects an emotion that may influence the user's purchasing decision, the server immediately presents the user with specific purchase promotion information. This system is capable of providing optimal information tailored to emotions in real time.

[0216] As a concrete example, when a user is browsing products in an online shop, the system may detect hesitation in purchasing based on the user's tone of voice and facial expression. In this case, the server provides a promotional message such as, "Special sale today! Please use your 10% discount coupon," to encourage purchase. The prompt is given to the generating AI model as follows:

[0217] "Generate an appropriate incentive offer for a user who is hesitant to purchase. The user's sentiment data is as follows: Text 'Okay, but a little expensive,' Voice tone 'Doubtful,' Facial expression 'Thinking.' What incentive would be effective?"

[0218] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0219] Step 1:

[0220] The server collects information from various data sources via the network. Inputs include site logs, purchase history, and user search behavior data. By receiving this data and temporarily storing it in a database, the server prepares the foundational data necessary for subsequent analysis.

[0221] Step 2:

[0222] The server performs preprocessing and information cleaning on the collected data. It removes noise, standardizes data formats, and outputs structured data. Specifically, it imputes missing data and filters outliers to prepare a well-organized dataset.

[0223] Step 3:

[0224] The server analyzes the organized data and generates analysis results. During this process, machine learning algorithms are used to extract features and perform market analysis and customer trend predictions. It identifies meaningful patterns from the input data and outputs them as business insights.

[0225] Step 4:

[0226] The server uses a generative AI model to automatically generate business policies and investment decision information based on analysis results. By inputting prompts into the machine learning model, appropriate strategies and suggestions are obtained. The output consists of specific action items and investment recommendations.

[0227] Step 5:

[0228] The device uses an emotion engine to recognize the user's voice data, text data, and facial expression data. Based on the data acquired through the voice assistant and camera module, it performs emotion analysis and evaluates the user's psychological state.

[0229] Step 6:

[0230] The server analyzes the emotional data output by the emotion engine and adjusts business policies and investment decision information based on the user's emotions. For example, for users who are showing anxiety, it focuses on providing information that mitigates risk.

[0231] Step 7:

[0232] The terminal presents the user with pre-configured information from the server. Through the user interface, emotionally relevant and purchase-promoting information is displayed to effectively support the user's decision-making. Specific examples include discount coupons and information on special sales events.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] [Second Embodiment]

[0237] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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".

[0249] This invention relates to a system that collects information from diverse data sources via a network, preprocesses and analyzes it, and automatically generates and provides information useful for business strategy and investment decisions. This system achieves these processes by utilizing generative AI through a specific algorithm.

[0250] First, the server utilizes communication infrastructure to collect information via the internet. For example, it retrieves news articles, social media posts, and publicly available company reports via crawling or APIs. Next, the server verifies the integrity of the retrieved information and preprocesses it to remove noise and unnecessary data.

[0251] The pre-processed information is analyzed by the server using natural language processing and machine learning techniques. The analysis extracts highly relevant business insights, which are then used to formulate business strategies. For example, market trends and competitor analysis are conducted, leading to concrete proposals for new market entry strategies and product lineups.

[0252] Furthermore, for investors, the server generates reports evaluating companies' financial health and growth forecasts based on the analysis results. This provides information to help them determine which companies are worth investing in.

[0253] Users (entrepreneurs or investors) receive these analysis results and suggestions through their devices. For example, if a user is considering launching a new business, they can develop a business plan based on the market strategy presented by the server. If a user is considering investing in a particular startup, they can refer to the server's analysis report to assess the risks and use it to help make an investment decision.

[0254] Furthermore, user feedback is collected by the server and used to improve the AI ​​model. This enhances the accuracy and effectiveness of suggestions, strengthening support for future strategy formulation and investment decisions.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The server accesses data sources via the internet and collects the necessary information. In this process, it uses crawlers to collect data from news sites and social media, as well as to obtain publicly available company information through APIs.

[0258] Step 2:

[0259] The server preprocesses the collected information. In this process, natural language processing techniques are used to normalize the text data and remove noise. The information is also categorized and organized into structured data.

[0260] Step 3:

[0261] The server analyzes pre-processed data. Specifically, it uses machine learning models to conduct market trend and competitor analysis, extracting meaningful business insights. This data is then visualized in statistical metrics and graphs.

[0262] Step 4:

[0263] The server automatically generates business strategies based on the analysis results. In this process, the generating AI creates specific strategic proposals, such as strategies for entering new markets and measures to enhance existing products.

[0264] Step 5:

[0265] The server generates information to support investment decisions and creates company evaluation reports. This includes evaluating financial indicators and forecasting growth.

[0266] Step 6:

[0267] Users (entrepreneurs or investors) view analysis results and suggestions provided by the server from their terminals. Based on this, users develop their own business plans or make investment decisions.

[0268] Step 7:

[0269] Users send feedback on the suggestions and analyses they use to the server via their device. Based on this feedback, the server updates the AI ​​model to improve the accuracy of future suggestions and decisions.

[0270] (Example 1)

[0271] 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."

[0272] Efficiently collecting, integrating, and analyzing vast amounts of diverse information from various data sources, and then quickly and accurately providing business strategies and investment decisions based on that information, is a critical challenge in modern economic activity. This process requires advanced technical skills and efficient methods for information preprocessing, noise reduction, and improving the accuracy of analysis results. Furthermore, methods for effectively utilizing user feedback to continuously improve the accuracy of future proposals are also essential.

[0273] 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.

[0274] In this invention, the server includes means for collecting information from a data set via a network, means for preprocessing and structuring the collected information, and means for analyzing the data using natural language processing and machine learning techniques. This enables the efficient integration of diverse information and the provision of business strategies and investment decisions based on advanced analysis.

[0275] A "network" is a connection infrastructure used by computers and devices to communicate with each other, and is a structure that enables the sending and receiving of information.

[0276] A "data set" refers to a collection of information gathered for a specific purpose, and it may include numbers, characters, symbols, and other elements.

[0277] "Preprocessing" refers to the process of removing unnecessary data from collected information, imputing missing values, and preparing the data in a format that is easy to analyze.

[0278] "Structuring" refers to organizing data according to certain rules to make it easier to handle, thereby enabling efficient analysis.

[0279] "Analysis" refers to the act of using techniques such as natural language processing and machine learning to derive useful insights and patterns from the collected and preprocessed information.

[0280] "Business strategy" refers to the long-term plans and policies in corporate activities, which are determined considering market trends and the situations of competing companies.

[0281] "Investment judgment" refers to the decision of which companies or projects to invest capital in based on financial data and market analysis.

[0282] "Feedback" refers to the evaluations and opinions provided by users, which are information used for system improvement and model accuracy improvement.

[0283] "Natural language processing" is a technology for computers to understand, interpret, and generate the language that humans use daily.

[0284] "Machine learning" is a technology that enables computers to find patterns from data and perform predictions and decision-making automatically.

[0285] This invention is a data analysis system in which a server, a terminal, and a user operate in cooperation and utilize information obtained via a network. The server collects information from a plurality of data sets and enables business strategies and investment judgments by efficiently integrating and analyzing the information.

[0286] The server collects information in real time by using news APIs and social media APIs through the Internet. The collected information is converted into a data frame using the Pandas library of Python, and preprocessing such as complementing missing values and filtering noise is performed. Thereafter, information analysis is performed using the NLTK library for natural language processing and the generative AI models of TensorFlow and OpenAI for machine learning.

[0287] The analyzed data is used for business strategies and investment decisions. Business strategies are automatically generated based on market trends and competitive analysis. As a specific example, it is utilized for optimizing the market launch timing of new products and reviewing the product lineup. Also, investment decisions evaluate the financial soundness and growth prediction of a company and contribute to the selection of investment destinations.

[0288] Users receive the results of business strategies and investment decisions provided using the terminal. By accessing the dashboard, users can visually confirm the analysis results and determine necessary actions. For example, when a user is searching for a specific strategy to enter a new market, the server presents a specific proposal based on the prompt text "Please propose a strategy for entering a new market. This strategy should be based on recent industry trends and competitive analysis."

[0289] Furthermore, feedback from users is collected by the server and used as training data for the generative AI model. This enables improvement of the model based on the feedback and can enhance the accuracy of future proposals.

[0290] The flow of the specific process in Example 1 will be described using FIG. 11.

[0291] Step 1:

[0292] First, the server collects information via the Internet. At this stage, news APIs and social media APIs are utilized to obtain real-time data. The input is the raw data obtained from the API, and the output is the raw format of that data. This raw data includes information such as the title, text, publication date and time, and source of the article. As a specific operation, the server queries the API at regular intervals and executes a script to obtain new data.

[0293] Step 2:

[0294] The server performs preprocessing on the collected data. This preprocessing uses the Python Pandas library to convert the data into a data frame and performs missing value imputation and noise filtering. The input is the raw data obtained in step 1, and the output is a clean, prepared dataset. Specifically, the server fills in missing values ​​with the mean or median, and deletes rows that do not meet certain conditions. It also performs text tokenization and stop word removal using NLTK.

[0295] Step 3:

[0296] The server performs analysis on the pre-processed data. This analysis utilizes natural language processing and machine learning techniques, employing TensorFlow and generative AI models. The input is the clean dataset obtained in step 2, and the output is the analysis results, i.e., business insights. Specifically, the AI ​​model is fed context, and topic modeling and sentiment analysis are performed to extract key trends and customer sentiment.

[0297] Step 4:

[0298] The server automatically generates business strategies and investment decisions based on the analysis results. It utilizes a generating AI model to form specific recommended strategies and decision-making information. The input is the analysis results obtained in step 3, and the output is specific strategy proposals and investment reports. Specifically, the generating AI model performs evaluations, automatically generates strategy documents and reports, and customizes them as needed to match user-specified conditions.

[0299] Step 5:

[0300] The server provides the generated business strategies and investment decisions to the user's terminal. This allows the user to review the strategies and take necessary actions. The input is the output generated in step 4, and the output is displayed in a format that is easy for the user to understand. Specifically, the server displays the results on a dashboard via a web browser or a dedicated application.

[0301] Step 6:

[0302] Users provide feedback. They input their opinions and evaluations of the analysis results and suggestions through their terminals. The input is user feedback, and the output is feedback data sent to the server. Specifically, users use a feedback form to input satisfaction ratings and improvement requests.

[0303] Step 7:

[0304] The server receives feedback information from users and uses it to train the AI ​​model. Based on the feedback, it adjusts the model's parameters to improve the accuracy of future strategic suggestions and investment decisions. The input is the feedback data obtained in step 6, and the output is the improved AI model's parameter settings. Specifically, the server feeds the feedback data into the learning algorithm and retrains the model.

[0305] (Application Example 1)

[0306] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0307] In conventional information analysis systems, it is difficult to effectively collect and analyze large amounts of data, and there is a particular need to quickly make judgments regarding real-time business strategies and resource allocation. In addition, since there is a lack of methods for visually presenting analysis results in an easy-to-understand manner, there has been a problem that users cannot fully utilize the information obtained in actual business. Furthermore, continuous model optimization and reflection of user feedback to improve the accuracy of the generated information are not sufficient.

[0308] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0309] In this invention, the server includes means for collecting data from an information source via a network, means for preprocessing and cleaning the collected data to structure it, means for analyzing the preprocessed data to generate an analysis result, and means for displaying the analysis result using visual display based on augmented reality technology. As a result, the user can visually confirm various information in real time and can quickly and accurately make judgments regarding business strategies and resource allocation.

[0310] The "means for collecting data from an information source via a network" is a function for obtaining information from various data sources such as news articles, corporate reports, and social media through the Internet or an intranet.

[0311] The "means for preprocessing, cleaning, and structuring the collected data" is a process of checking the consistency and quality of the acquired data, removing and organizing noise, and converting it into a form that is easy to analyze.

[0312] The "means for analyzing the preprocessed data to generate an analysis result" is a function for executing an algorithm that derives useful business insights and trends from the cleaned data using techniques of machine learning and natural language processing.

[0313] "Means of displaying analysis results based on augmented reality technology using visual displays" refers to a function that utilizes augmented reality (AR) to provide users with an easy-to-understand graphical visual representation of analysis results.

[0314] "Business strategy" refers to plans and guidelines that companies and organizations formulate to respond to market trends and competitive situations based on collected and analyzed information.

[0315] "Information that supports resource allocation decisions" refers to data and analytical results that assist in determining which business areas or projects should receive the most resources.

[0316] "User's device" refers to a terminal used to view or operate information provided by the system, such as a smartphone, tablet, or personal computer.

[0317] "Means of receiving evaluation information and using it for learning and model optimization" refers to the process of collecting feedback from users, updating the AI ​​model based on that feedback, and improving the accuracy of future suggestions and analyses.

[0318] The system implementing this invention leverages a network infrastructure that includes cloud-based servers and user equipment. The servers automatically collect data from diverse sources on the internet, such as news articles, company reports, and social media, using advanced data collection programs. This data is preprocessed in real time on streaming platforms such as Apache Kafka, where noise is removed and the data is formatted. The collected data is then analyzed using natural language processing and machine learning techniques, utilizing Amazon SageMaker and Google Cloud AI Platform. Generative AI models are used to extract information from the data that supports business insights and resource allocation decisions.

[0319] The user's device has an interface to receive analysis results and present them to the user visually. This utilizes augmented reality (AR) applications and graphical displays implemented with Unity or React Native. As a result, the user can intuitively understand the analysis results and make effective business strategy and resource allocation decisions in real time.

[0320] Specifically, when a user enters prompts such as, "What are the current trends in the renewable energy industry?" or "Show me the growth forecast for technology companies in the next quarter," the server collects and analyzes relevant information and sends the results to the user's device. Based on this information, the user can quickly proceed with the decision-making process. Evaluations and feedback from the user are continuously sent to the server, so the accuracy of the model and the effectiveness of the suggestions continue to improve.

[0321] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0322] Step 1:

[0323] The server collects data from multiple sources via the internet. Specifically, it retrieves news articles, company reports, and social media data using APIs or web crawling technologies. Inputs include target keywords and URLs, and output is the original data.

[0324] Step 2:

[0325] The server preprocesses the acquired data. This process verifies data integrity, removes duplicates and noise, and structures the data. The input is the raw data acquired in step 1, and the output is a clean and organized dataset. Specifically, a text cleaning algorithm is used to remove extraneous symbols and spaces.

[0326] Step 3:

[0327] The server utilizes a generative AI model to analyze the preprocessed data. Through natural language processing algorithms, it extracts useful business insights and patterns from the data. The input is the data cleaned in step 2, and the output is the insights and trends obtained through the analysis. Specifically, a machine learning model operates to identify key features from the dataset.

[0328] Step 4:

[0329] The user's device receives the analysis results sent from the server and displays them visually. This process uses augmented reality technology to present information visually. The input is the analysis results generated in step 3, and the output is a visual display that the user can view. Specifically, the Unity or React Native platform is used, and interactive displays utilizing AR are implemented.

[0330] Step 5:

[0331] The user makes a decision based on the information provided and sends feedback to the server. This user feedback is used for the next model retraining. The input is the user's evaluation and improvement requests, and the output is the feedback data sent to the server. Specifically, the user inputs comments and evaluation scores through the application interface.

[0332] Step 6:

[0333] The server receives feedback from the user and retrains the generated AI model. In this phase, the improved model is used for subsequent analyses. The input is the feedback data received in step 5, and the output is the new model with improved accuracy. Specifically, the server adjusts the model's hyperparameters using the feedback data and then retrains it.

[0334] 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.

[0335] This invention provides a system that improves the accuracy of strategic and investment information by combining a system that collects, preprocesses, and analyzes data via a network and automatically generates business strategies and investment decisions based on that data with an emotion engine that recognizes user emotions.

[0336] First, the server collects information from various data sources via the network as usual, performs noise reduction and information cleaning, and prepares it as structured data. Next, the server analyzes the collected information and extracts business insights. Based on these results, it automatically generates information for business strategy and investment decisions using AI.

[0337] The emotion engine in this system recognizes the user's emotions through voice, facial expressions, text input, and other data while the user is using the device. The server receives this emotion data and customizes business strategies and investment decision information according to the user's emotions. For example, if the user is showing anxiety, the system will enhance strategic suggestions to mitigate risks and prioritize presenting information that provides reassurance.

[0338] As a concrete example, consider a scenario where a user is considering investing in a new business. The server analyzes the collected data to predict market growth and conduct competitive analysis, generating a business strategy. Meanwhile, the emotion engine evaluates how the user feels about the information presented. If the emotion data indicates that the user is overly optimistic, the server will perform a reality check, emphasizing realistic risks to support a balanced decision.

[0339] Thus, systems equipped with an emotion engine provide strategic recommendations and investment information that reflect the user's psychological state, enabling more personalized decision-making support. This approach is crucial for enhancing the influence on user behavior and decisions compared to conventional information delivery methods.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The server collects data from news articles, social media, and publicly available corporate data via the network. It uses crawlers and APIs to efficiently retrieve the necessary information.

[0343] Step 2:

[0344] The server preprocesses the collected data. Specifically, it removes noise, normalizes text, and categorizes the data to prepare it as analyzable structured data.

[0345] Step 3:

[0346] The server analyzes the pre-processed data. It applies machine learning algorithms to analyze market trends and competitor activities, extracting business insights. At this stage, the analysis results are formatted as statistical indicators and visual data.

[0347] Step 4:

[0348] The server automatically generates business strategies based on the analysis results. Utilizing the AI-generated strategies, it specifically proposes measures for developing new markets and strengthening existing strategies.

[0349] Step 5:

[0350] Users receive strategic proposals and investment information generated by the server through their devices. At this stage, the information is displayed in a user-friendly interface, making it easy to view.

[0351] Step 6:

[0352] The emotion engine built into the device recognizes the user's emotional state. Through voice recognition, facial expression analysis, and text input analysis, it identifies what emotions the user is experiencing.

[0353] Step 7:

[0354] The server adjusts the input information based on the user's emotional data obtained from the emotion engine. For example, if the user is feeling anxious, the server adjusts the output by emphasizing more detailed explanations to provide reassurance or suggestions to mitigate risks.

[0355] Step 8:

[0356] Users can view personalized, emotion-based suggestions on their devices to aid in business planning and investment decisions. The goal is to improve the quality of decision-making based on the information provided.

[0357] Step 9:

[0358] User feedback is sent to the server via the device. The server uses this information to update the AI ​​model, continuously improving the overall accuracy and effectiveness of the system.

[0359] (Example 2)

[0360] 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".

[0361] In today's diverse business environment, business strategies and investment decisions must not only be based on data analysis but also consider the emotions and psychological states of individual users. However, conventional systems do not adequately provide information that takes user emotions into account, resulting in a lack of accuracy in providing personalized decision support. There is a need to solve this problem and realize more effective decision support.

[0362] 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.

[0363] In this invention, the server includes means for collecting data from information sources via a network, means for preprocessing, cleaning, and structuring the collected data, means for analyzing the preprocessed data and extracting the analysis results, and means for identifying the user's emotions and adjusting business strategy and investment decision information according to the identified emotions. This makes it possible to provide strategies and investment decisions that reflect the user's emotions.

[0364] A "network" refers to a connection between multiple computers or devices built to send and receive data.

[0365] "Information source" refers to the database, online platform, or other data provision infrastructure from which data is obtained.

[0366] "Data collection" refers to the process of gathering information from various sources to achieve a specific purpose.

[0367] "Preprocessing" refers to the process of removing noise and imputing missing values ​​in order to convert raw data into an analyzable format.

[0368] "Data cleanup" refers to the process of deleting or correcting unnecessary or incorrect information in order to improve data quality.

[0369] "Data structuring" refers to the process of organizing collected information into a specific format to make it easier to handle.

[0370] "Analysis" refers to the process of analyzing data to uncover hidden patterns and useful information.

[0371] "Generative AI" refers to a type of artificial intelligence that generates new content such as text and images based on presented data and prompts.

[0372] "Business strategy" refers to the plans and policies that a company or organization aims to achieve in order to accomplish its ultimate goals.

[0373] "Investment decision" refers to the evaluation and selection process used to determine which businesses or projects to allocate capital to.

[0374] "Emotional identification" refers to the process of interpreting a user's psychological state and emotions from their words, facial expressions, and actions.

[0375] "Adjustment" refers to the act of making changes to optimize existing plans and policies as needed or in accordance with the circumstances.

[0376] "Feedback" refers to information and evaluations received regarding actions and results, which are used as a reference for improvement.

[0377] "Learning" refers to the process of acquiring knowledge and skills based on experience and information, and improving one's abilities.

[0378] This invention realizes a system that can provide users with optimized business strategies and investment decisions by utilizing multiple means. Specific embodiments thereof are shown below.

[0379] Data acquisition and preprocessing

[0380] The server first collects data from various sources via the network. Specifically, it uses social media platforms, news websites, and economic databases as sources. The Python requests library is used to retrieve the data. Next, the Python Pandas library is used to clean and structure the collected data. This removes noise and irrelevant information and prepares it in a format suitable for analysis.

[0381] Strategy generation using data analysis and generative AI.

[0382] The server analyzes pre-processed data and extracts business insights. The analysis uses the Scikit-learn library to perform cluster analysis and regression analysis. Furthermore, a generative AI model is used to automatically generate strategies and investment decisions based on the extracted insights. In this process, a large-scale language model is used for the generative AI, and an example of a prompt is, "Please propose an investment strategy for the next quarter based on market trends, but please take into account the concerns expressed by the user."

[0383] Emotion recognition and information customization

[0384] The device uses its camera and microphone to collect facial expressions and voice to recognize the user's emotions. The collected data is processed by an emotion analysis algorithm to evaluate the user's current psychological state. Based on this emotion data, the server customizes strategies and investment information. For example, if the user indicates anxiety, the server strengthens suggestions to mitigate risk.

[0385] Application examples

[0386] As a practical example, consider a user considering investing in a new business. In this case, the server performs market analysis and proposes a strategy based on the competitive landscape and growth forecasts. Meanwhile, the terminal analyzes the user's reactions and provides additional reassuring information if the user is feeling anxious. This allows the user to make a more balanced decision.

[0387] Thus, by combining data analysis and emotion recognition, this invention can provide decision-making support tailored to the individual needs of each user.

[0388] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0389] Step 1:

[0390] The server collects data from information sources via the network. Specifically, the server uses APIs to retrieve text data from social media and news sites. This input data includes posts and articles in text format. The retrieved data is temporarily stored in a database.

[0391] Step 2:

[0392] The server preprocesses the collected raw data. It uses Python's regular expression tools to remove unwanted characters and noise. It also cleans the data and imputes missing values ​​using the Pandas library. This process yields analyzable structured data. The output is formatted text data.

[0393] Step 3:

[0394] The server analyzes preprocessed data using machine learning models. Scikit-learn is used for the analysis, building cluster analysis and regression models. Preprocessed data is provided as input. The output is information about specific patterns and trends, known as extracted business insights.

[0395] Step 4:

[0396] The server inputs prompt messages into the generating AI model and generates strategies and investment decisions based on the analysis results. Specifically, it uses prompt messages such as, "Please propose an investment strategy for the next quarter based on market trends." The output is text-based information regarding strategy proposals and investment decisions.

[0397] Step 5:

[0398] The device uses a camera and microphone to collect voice and facial expression data to identify the user's emotions. The input is real-time data from the user. The acquired emotion data is processed by an emotion analysis algorithm to identify the user's emotional state. This result is output as an emotion score.

[0399] Step 6:

[0400] The server customizes generated strategies and investment decisions based on sentiment data. Specifically, if the user indicates anxiety, it adjusts the information to emphasize suggestions for risk reduction. The output is customized strategic information tailored to the user's emotions.

[0401] Step 7:

[0402] The server transmits customized information to the terminal and presents it to the user. The terminal visually presents the received information to the user through an output device such as a display. This allows the user to review strategic information and use it to aid in decision-making.

[0403] (Application Example 2)

[0404] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0405] Conventional data analysis systems provide information generated without considering the user's psychological state or emotions, resulting in challenges in personalizing and accurately conveying information that contributes to user decision-making. Furthermore, in e-commerce, appropriate information is often not presented to effectively increase user purchasing intent. In this context, there is a need for strategic proposals and purchase-promoting information that take user emotions into account.

[0406] 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.

[0407] In this invention, the server includes means for collecting information from a data source via a network, means for preprocessing, cleaning, and structuring the collected information, and means for analyzing the preprocessed information and generating analysis results. This makes it possible to recognize the user's emotions, adjust the information based on those emotions, and provide personalized strategic suggestions and purchase promotion information.

[0408] A "network" is a system in which computers and other devices are connected to communicate information.

[0409] A "data source" refers to the place or system from which information is acquired, and it provides data in various formats.

[0410] "Preprocessing" refers to the process of preparing data for analysis, and includes steps such as noise reduction and data organization.

[0411] "Information cleaning" is the process of removing inaccurate or unnecessary parts from data and preparing it to be usable.

[0412] "Structuring" refers to organizing data into a specific format, thereby making it easier to analyze and search.

[0413] "Analysis results" refer to the output obtained after data analysis, including conclusions or insights based on the intended analysis.

[0414] "Business policy" refers to the strategies and plans for achieving business objectives, indicating the direction and activities that a company should adopt.

[0415] A "user terminal" is a device used by a user to receive and process information, and includes smartphones and personal computers.

[0416] "Feedback information" refers to information such as opinions and evaluations obtained from users that contribute to the improvement of a system or process.

[0417] "Learning and model optimization" is the process of adjusting a machine learning model using new data to improve it.

[0418] "User emotions" refers to the mental or psychological state that users exhibit while using the system, and is an element on which information is adjusted.

[0419] "Purchase promotion information" refers to incentives and marketing information provided to increase users' motivation to purchase products or services.

[0420] To implement this invention, the server first collects information from multiple data sources using a network. The collected data undergoes information cleaning and preprocessing and is converted into a structured format. Next, the server analyzes the preprocessed information using data analysis software and outputs the results as business policy and investment decision information using a generating AI model.

[0421] The emotion engine uses smartphones and other user devices to recognize the user's emotions from voice data, text data, and facial expression data. Based on the user's emotion data, the server adaptively adjusts the generated business policies and investment decision information. In particular, if the emotion engine detects an emotion that may influence the user's purchasing decision, the server immediately presents the user with specific purchase promotion information. This system is capable of providing optimal information tailored to emotions in real time.

[0422] As a concrete example, when a user is browsing products in an online shop, the system may detect hesitation in purchasing based on the user's tone of voice and facial expression. In this case, the server provides a promotional message such as, "Special sale today! Please use your 10% discount coupon," to encourage purchase. The prompt is given to the generating AI model as follows:

[0423] "Generate an appropriate incentive offer for a user who is hesitant to purchase. The user's sentiment data is as follows: Text 'Okay, but a little expensive,' Voice tone 'Doubtful,' Facial expression 'Thinking.' What incentive would be effective?"

[0424] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0425] Step 1:

[0426] The server collects information from various data sources via the network. Inputs include site logs, purchase history, and user search behavior data. By receiving this data and temporarily storing it in a database, the server prepares the foundational data necessary for subsequent analysis.

[0427] Step 2:

[0428] The server performs preprocessing and information cleaning on the collected data. It removes noise, standardizes data formats, and outputs structured data. Specifically, it imputes missing data and filters outliers to prepare a well-organized dataset.

[0429] Step 3:

[0430] The server analyzes the organized data and generates analysis results. During this process, machine learning algorithms are used to extract features and perform market analysis and customer trend predictions. It identifies meaningful patterns from the input data and outputs them as business insights.

[0431] Step 4:

[0432] The server uses a generative AI model to automatically generate business policies and investment decision information based on analysis results. By inputting prompts into the machine learning model, appropriate strategies and suggestions are obtained. The output consists of specific action items and investment recommendations.

[0433] Step 5:

[0434] The device uses an emotion engine to recognize the user's voice data, text data, and facial expression data. Based on the data acquired through the voice assistant and camera module, it performs emotion analysis and evaluates the user's psychological state.

[0435] Step 6:

[0436] The server analyzes the emotional data output by the emotion engine and adjusts business policies and investment decision information based on the user's emotions. For example, for users who are showing anxiety, it focuses on providing information that mitigates risk.

[0437] Step 7:

[0438] The terminal presents the user with pre-configured information from the server. Through the user interface, emotionally relevant and purchase-promoting information is displayed to effectively support the user's decision-making. Specific examples include discount coupons and information on special sales events.

[0439] 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.

[0440] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0441] 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.

[0442] [Third Embodiment]

[0443] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0444] 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.

[0445] 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).

[0446] 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.

[0447] 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.

[0448] 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).

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] 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".

[0455] This invention relates to a system that collects information from diverse data sources via a network, preprocesses and analyzes it, and automatically generates and provides information useful for business strategy and investment decisions. This system achieves these processes by utilizing generative AI through a specific algorithm.

[0456] First, the server utilizes communication infrastructure to collect information via the internet. For example, it retrieves news articles, social media posts, and publicly available company reports via crawling or APIs. Next, the server verifies the integrity of the retrieved information and preprocesses it to remove noise and unnecessary data.

[0457] The pre-processed information is analyzed by the server using natural language processing and machine learning techniques. The analysis extracts highly relevant business insights, which are then used to formulate business strategies. For example, market trends and competitor analysis are conducted, leading to concrete proposals for new market entry strategies and product lineups.

[0458] Furthermore, for investors, the server generates reports evaluating companies' financial health and growth forecasts based on the analysis results. This provides information to help them determine which companies are worth investing in.

[0459] Users (entrepreneurs or investors) receive these analysis results and suggestions through their devices. For example, if a user is considering launching a new business, they can develop a business plan based on the market strategy presented by the server. If a user is considering investing in a particular startup, they can refer to the server's analysis report to assess the risks and use it to help make an investment decision.

[0460] Furthermore, user feedback is collected by the server and used to improve the AI ​​model. This enhances the accuracy and effectiveness of suggestions, strengthening support for future strategy formulation and investment decisions.

[0461] The following describes the processing flow.

[0462] Step 1:

[0463] The server accesses data sources via the internet and collects the necessary information. In this process, it uses crawlers to collect data from news sites and social media, as well as to obtain publicly available company information through APIs.

[0464] Step 2:

[0465] The server preprocesses the collected information. In this process, natural language processing techniques are used to normalize the text data and remove noise. The information is also categorized and organized into structured data.

[0466] Step 3:

[0467] The server analyzes pre-processed data. Specifically, it uses machine learning models to conduct market trend and competitor analysis, extracting meaningful business insights. This data is then visualized in statistical metrics and graphs.

[0468] Step 4:

[0469] The server automatically generates business strategies based on the analysis results. In this process, the generating AI creates specific strategic proposals, such as strategies for entering new markets and measures to enhance existing products.

[0470] Step 5:

[0471] The server generates information to support investment decisions and creates company evaluation reports. This includes evaluating financial indicators and forecasting growth.

[0472] Step 6:

[0473] Users (entrepreneurs or investors) view analysis results and suggestions provided by the server from their terminals. Based on this, users develop their own business plans or make investment decisions.

[0474] Step 7:

[0475] Users send feedback on the suggestions and analyses they use to the server via their device. Based on this feedback, the server updates the AI ​​model to improve the accuracy of future suggestions and decisions.

[0476] (Example 1)

[0477] 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."

[0478] Efficiently collecting, integrating, and analyzing vast amounts of diverse information from various data sources, and then quickly and accurately providing business strategies and investment decisions based on that information, is a critical challenge in modern economic activity. This process requires advanced technical skills and efficient methods for information preprocessing, noise reduction, and improving the accuracy of analysis results. Furthermore, methods for effectively utilizing user feedback to continuously improve the accuracy of future proposals are also essential.

[0479] 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.

[0480] In this invention, the server includes means for collecting information from a data set via a network, means for preprocessing and structuring the collected information, and means for analyzing the data using natural language processing and machine learning techniques. This enables the efficient integration of diverse information and the provision of business strategies and investment decisions based on advanced analysis.

[0481] A "network" is a connection infrastructure used by computers and devices to communicate with each other, and is a structure that enables the sending and receiving of information.

[0482] A "data set" refers to a collection of information gathered for a specific purpose, and it may include numbers, characters, symbols, and other elements.

[0483] "Preprocessing" refers to the process of removing unnecessary data from collected information, imputing missing values, and preparing the data in a format that is easy to analyze.

[0484] "Structuring" refers to organizing data according to certain rules to make it easier to handle, thereby enabling efficient analysis.

[0485] "Analysis" is the act of using techniques such as natural language processing and machine learning to derive useful insights and patterns from collected and pre-processed information.

[0486] "Business strategy" refers to long-term plans and policies for corporate activities, which are determined by taking into account market trends and the situation of competitors.

[0487] "Investment decisions" refer to the process of determining which companies or projects should receive capital investment, based on financial data and market analysis.

[0488] "Feedback" refers to evaluations and opinions provided by users, and is information used to improve the system and enhance the accuracy of the model.

[0489] "Natural language processing" is a technology that enables computers to understand, interpret, and generate language that humans use on a daily basis.

[0490] Machine learning is a technology that enables computers to find patterns in data and automatically make predictions and decisions.

[0491] This invention is a data analysis system in which a server, terminal, and user work together to utilize information obtained via a network. The server collects information from multiple data sets and efficiently integrates and analyzes that information to enable business strategies and investment decisions.

[0492] The server collects information in real time using news APIs and social media APIs via the internet. The collected information is converted into a data frame using the Python Pandas library, and preprocessing is performed to impute missing values ​​and filter out noise. Subsequently, the information is analyzed using the NLTK library for natural language processing and generative AI models from TensorFlow and OpenAI for machine learning.

[0493] The analyzed data is used for business strategies and investment decisions. Business strategies are automatically generated based on market trends and competitive analysis. Specific examples include optimizing the timing of new product launches and reviewing product lineups. Investment decisions are evaluated based on a company's financial health and growth forecasts, contributing to the selection of investment targets.

[0494] Users receive the results of business strategies and investment decisions provided via their devices. By accessing the dashboard, users can visually review the analysis results and decide on necessary actions. For example, if a user is looking for a specific strategy to enter a new market, the server will present specific suggestions based on a prompt such as, "Please propose a strategy for entering a new market. This strategy should be based on recent industry trends and competitive analysis."

[0495] Furthermore, user feedback is collected by the server and used as training data for the generated AI model. This allows for model improvement based on feedback, thereby improving the accuracy of future suggestions.

[0496] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0497] Step 1:

[0498] The server first collects information via the internet. At this stage, it utilizes news APIs and social media APIs to obtain real-time data. The input is raw data obtained from the APIs, and the output is that data in its raw form. This raw data includes information such as the article title, body text, publication date and time, and source. Specifically, the server queries the APIs at regular intervals and executes scripts to retrieve new data.

[0499] Step 2:

[0500] The server performs preprocessing on the collected data. This preprocessing uses the Python Pandas library to convert the data into a data frame and performs missing value imputation and noise filtering. The input is the raw data obtained in step 1, and the output is a clean, prepared dataset. Specifically, the server fills in missing values ​​with the mean or median, and deletes rows that do not meet certain conditions. It also performs text tokenization and stop word removal using NLTK.

[0501] Step 3:

[0502] The server performs analysis on the pre-processed data. This analysis utilizes natural language processing and machine learning techniques, employing TensorFlow and generative AI models. The input is the clean dataset obtained in step 2, and the output is the analysis results, i.e., business insights. Specifically, the AI ​​model is fed context, and topic modeling and sentiment analysis are performed to extract key trends and customer sentiment.

[0503] Step 4:

[0504] The server automatically generates business strategies and investment decisions based on the analysis results. It utilizes a generating AI model to form specific recommended strategies and decision-making information. The input is the analysis results obtained in step 3, and the output is specific strategy proposals and investment reports. Specifically, the generating AI model performs evaluations, automatically generates strategy documents and reports, and customizes them as needed to match user-specified conditions.

[0505] Step 5:

[0506] The server provides the generated business strategies and investment decisions to the user's terminal. This allows the user to review the strategies and take necessary actions. The input is the output generated in step 4, and the output is displayed in a format that is easy for the user to understand. Specifically, the server displays the results on a dashboard via a web browser or a dedicated application.

[0507] Step 6:

[0508] Users provide feedback. They input their opinions and evaluations of the analysis results and suggestions through their terminals. The input is user feedback, and the output is feedback data sent to the server. Specifically, users use a feedback form to input satisfaction ratings and improvement requests.

[0509] Step 7:

[0510] The server receives feedback information from users and uses it to train the AI ​​model. Based on the feedback, it adjusts the model's parameters to improve the accuracy of future strategic suggestions and investment decisions. The input is the feedback data obtained in step 6, and the output is the improved AI model's parameter settings. Specifically, the server feeds the feedback data into the learning algorithm and retrains the model.

[0511] (Application Example 1)

[0512] 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."

[0513] Conventional information analysis systems struggle to effectively collect and analyze large amounts of data, particularly in response to the need for rapid, real-time decision-making regarding business strategies and resource allocation. Furthermore, a lack of clear and visually appealing methods for representing analysis results has prevented users from fully utilizing the information they obtain in their actual work. Additionally, continuous model optimization and incorporation of user feedback to improve the accuracy of generated information are insufficient.

[0514] 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.

[0515] In this invention, the server includes means for collecting data from information sources via a network, means for preprocessing, cleaning, and structuring the collected data, means for analyzing the preprocessed data and generating analysis results, and means for displaying the analysis results using a visual display based on augmented reality technology. This enables users to visually check various types of information in real time and make quick and accurate decisions regarding business strategies and resource allocation.

[0516] "Means of collecting data from information sources via a network" refers to the function of obtaining information from various data sources such as news articles, company reports, and social media via the internet or intranet.

[0517] "Methods for preprocessing, cleaning, and structuring collected data" refers to the process of checking the integrity and quality of acquired data, removing and organizing noise, and converting it into a form that is easy to analyze.

[0518] "Means for analyzing pre-processed data and generating analysis results" refers to a function that uses machine learning and natural language processing techniques to execute algorithms that derive useful business insights and trends from cleaned data.

[0519] "Means of displaying analysis results based on augmented reality technology using visual displays" refers to a function that utilizes augmented reality (AR) to provide users with an easy-to-understand graphical visual representation of analysis results.

[0520] "Business strategy" refers to plans and guidelines that companies and organizations formulate to respond to market trends and competitive situations based on collected and analyzed information.

[0521] "Information that supports resource allocation decisions" refers to data and analytical results that assist in determining which business areas or projects should receive the most resources.

[0522] "User's device" refers to a terminal used to view or operate information provided by the system, such as a smartphone, tablet, or personal computer.

[0523] "Means of receiving evaluation information and using it for learning and model optimization" refers to the process of collecting feedback from users, updating the AI ​​model based on that feedback, and improving the accuracy of future suggestions and analyses.

[0524] The system implementing this invention leverages a network infrastructure that includes cloud-based servers and user equipment. The servers automatically collect data from diverse sources on the internet, such as news articles, company reports, and social media, using advanced data collection programs. This data is preprocessed in real time on streaming platforms such as Apache Kafka, where noise is removed and the data is formatted. The collected data is then analyzed using natural language processing and machine learning techniques, utilizing Amazon SageMaker and Google Cloud AI Platform. Generative AI models are used to extract information from the data that supports business insights and resource allocation decisions.

[0525] The user's device has an interface to receive analysis results and present them to the user visually. This utilizes augmented reality (AR) applications and graphical displays implemented with Unity or React Native. As a result, the user can intuitively understand the analysis results and make effective business strategy and resource allocation decisions in real time.

[0526] Specifically, when a user enters prompts such as, "What are the current trends in the renewable energy industry?" or "Show me the growth forecast for technology companies in the next quarter," the server collects and analyzes relevant information and sends the results to the user's device. Based on this information, the user can quickly proceed with the decision-making process. Evaluations and feedback from the user are continuously sent to the server, so the accuracy of the model and the effectiveness of the suggestions continue to improve.

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

[0528] Step 1:

[0529] The server collects data from multiple sources via the internet. Specifically, it retrieves news articles, company reports, and social media data using APIs or web crawling technologies. Inputs include target keywords and URLs, and output is the original data.

[0530] Step 2:

[0531] The server preprocesses the acquired data. This process verifies data integrity, removes duplicates and noise, and structures the data. The input is the raw data acquired in step 1, and the output is a clean and organized dataset. Specifically, a text cleaning algorithm is used to remove extraneous symbols and spaces.

[0532] Step 3:

[0533] The server utilizes a generative AI model to analyze the preprocessed data. Through natural language processing algorithms, it extracts useful business insights and patterns from the data. The input is the data cleaned in step 2, and the output is the insights and trends obtained through the analysis. Specifically, a machine learning model operates to identify key features from the dataset.

[0534] Step 4:

[0535] The user's device receives the analysis results sent from the server and displays them visually. This process uses augmented reality technology to present information visually. The input is the analysis results generated in step 3, and the output is a visual display that the user can view. Specifically, the Unity or React Native platform is used, and interactive displays utilizing AR are implemented.

[0536] Step 5:

[0537] The user makes a decision based on the information provided and sends feedback to the server. This user feedback is used for the next model retraining. The input is the user's evaluation and improvement requests, and the output is the feedback data sent to the server. Specifically, the user inputs comments and evaluation scores through the application interface.

[0538] Step 6:

[0539] The server receives feedback from the user and retrains the generated AI model. In this phase, the improved model is used for subsequent analyses. The input is the feedback data received in step 5, and the output is the new model with improved accuracy. Specifically, the server adjusts the model's hyperparameters using the feedback data and then retrains it.

[0540] 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.

[0541] This invention provides a system that improves the accuracy of strategic and investment information by combining a system that collects, preprocesses, and analyzes data via a network and automatically generates business strategies and investment decisions based on that data with an emotion engine that recognizes user emotions.

[0542] First, the server collects information from various data sources via the network as usual, performs noise reduction and information cleaning, and prepares it as structured data. Next, the server analyzes the collected information and extracts business insights. Based on these results, it automatically generates information for business strategy and investment decisions using AI.

[0543] The emotion engine in this system recognizes the user's emotions through voice, facial expressions, text input, and other data while the user is using the device. The server receives this emotion data and customizes business strategies and investment decision information according to the user's emotions. For example, if the user is showing anxiety, the system will enhance strategic suggestions to mitigate risks and prioritize presenting information that provides reassurance.

[0544] As a concrete example, consider a scenario where a user is considering investing in a new business. The server analyzes the collected data to predict market growth and conduct competitive analysis, generating a business strategy. Meanwhile, the emotion engine evaluates how the user feels about the information presented. If the emotion data indicates that the user is overly optimistic, the server will perform a reality check, emphasizing realistic risks to support a balanced decision.

[0545] Thus, systems equipped with an emotion engine provide strategic recommendations and investment information that reflect the user's psychological state, enabling more personalized decision-making support. This approach is crucial for enhancing the influence on user behavior and decisions compared to conventional information delivery methods.

[0546] The following describes the processing flow.

[0547] Step 1:

[0548] The server collects data from news articles, social media, and publicly available corporate data via the network. It uses crawlers and APIs to efficiently retrieve the necessary information.

[0549] Step 2:

[0550] The server preprocesses the collected data. Specifically, it removes noise, normalizes text, and categorizes the data to prepare it as analyzable structured data.

[0551] Step 3:

[0552] The server analyzes the pre-processed data. It applies machine learning algorithms to analyze market trends and competitor activities, extracting business insights. At this stage, the analysis results are formatted as statistical indicators and visual data.

[0553] Step 4:

[0554] The server automatically generates business strategies based on the analysis results. Utilizing the AI-generated strategies, it specifically proposes measures for developing new markets and strengthening existing strategies.

[0555] Step 5:

[0556] Users receive strategic proposals and investment information generated by the server through their devices. At this stage, the information is displayed in a user-friendly interface, making it easy to view.

[0557] Step 6:

[0558] The emotion engine built into the device recognizes the user's emotional state. Through voice recognition, facial expression analysis, and text input analysis, it identifies what emotions the user is experiencing.

[0559] Step 7:

[0560] The server adjusts the input information based on the user's emotional data obtained from the emotion engine. For example, if the user is feeling anxious, the server adjusts the output by emphasizing more detailed explanations to provide reassurance or suggestions to mitigate risks.

[0561] Step 8:

[0562] Users can view personalized, emotion-based suggestions on their devices to aid in business planning and investment decisions. The goal is to improve the quality of decision-making based on the information provided.

[0563] Step 9:

[0564] User feedback is sent to the server via the device. The server uses this information to update the AI ​​model, continuously improving the overall accuracy and effectiveness of the system.

[0565] (Example 2)

[0566] 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."

[0567] In today's diverse business environment, business strategies and investment decisions must not only be based on data analysis but also consider the emotions and psychological states of individual users. However, conventional systems do not adequately provide information that takes user emotions into account, resulting in a lack of accuracy in providing personalized decision support. There is a need to solve this problem and realize more effective decision support.

[0568] 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.

[0569] In this invention, the server includes means for collecting data from information sources via a network, means for preprocessing, cleaning, and structuring the collected data, means for analyzing the preprocessed data and extracting the analysis results, and means for identifying the user's emotions and adjusting business strategy and investment decision information according to the identified emotions. This makes it possible to provide strategies and investment decisions that reflect the user's emotions.

[0570] A "network" refers to a connection between multiple computers or devices built to send and receive data.

[0571] "Information source" refers to the database, online platform, or other data provision infrastructure from which data is obtained.

[0572] "Data collection" refers to the process of gathering information from various sources to achieve a specific purpose.

[0573] "Preprocessing" refers to the process of removing noise and imputing missing values ​​in order to convert raw data into an analyzable format.

[0574] "Data cleanup" refers to the process of deleting or correcting unnecessary or incorrect information in order to improve data quality.

[0575] "Data structuring" refers to the process of organizing collected information into a specific format to make it easier to handle.

[0576] "Analysis" refers to the process of analyzing data to uncover hidden patterns and useful information.

[0577] "Generative AI" refers to a type of artificial intelligence that generates new content such as text and images based on presented data and prompts.

[0578] "Business strategy" refers to the plans and policies that a company or organization aims to achieve in order to accomplish its ultimate goals.

[0579] "Investment decision" refers to the evaluation and selection process used to determine which businesses or projects to allocate capital to.

[0580] "Emotional identification" refers to the process of interpreting a user's psychological state and emotions from their words, facial expressions, and actions.

[0581] "Adjustment" refers to the act of making changes to optimize existing plans and policies as needed or in accordance with the circumstances.

[0582] "Feedback" refers to information and evaluations received regarding actions and results, which are used as a reference for improvement.

[0583] "Learning" refers to the process of acquiring knowledge and skills based on experience and information, and improving one's abilities.

[0584] This invention realizes a system that can provide users with optimized business strategies and investment decisions by utilizing multiple means. Specific embodiments thereof are shown below.

[0585] Data acquisition and preprocessing

[0586] The server first collects data from various sources via the network. Specifically, it uses social media platforms, news websites, and economic databases as sources. The Python requests library is used to retrieve the data. Next, the Python Pandas library is used to clean and structure the collected data. This removes noise and irrelevant information and prepares it in a format suitable for analysis.

[0587] Strategy generation using data analysis and generative AI.

[0588] The server analyzes pre-processed data and extracts business insights. The analysis uses the Scikit-learn library to perform cluster analysis and regression analysis. Furthermore, a generative AI model is used to automatically generate strategies and investment decisions based on the extracted insights. In this process, a large-scale language model is used for the generative AI, and an example of a prompt is, "Please propose an investment strategy for the next quarter based on market trends, but please take into account the concerns expressed by the user."

[0589] Emotion recognition and information customization

[0590] The device uses its camera and microphone to collect facial expressions and voice to recognize the user's emotions. The collected data is processed by an emotion analysis algorithm to evaluate the user's current psychological state. Based on this emotion data, the server customizes strategies and investment information. For example, if the user indicates anxiety, the server strengthens suggestions to mitigate risk.

[0591] Application examples

[0592] As a practical example, consider a user considering investing in a new business. In this case, the server performs market analysis and proposes a strategy based on the competitive landscape and growth forecasts. Meanwhile, the terminal analyzes the user's reactions and provides additional reassuring information if the user is feeling anxious. This allows the user to make a more balanced decision.

[0593] Thus, by combining data analysis and emotion recognition, this invention can provide decision-making support tailored to the individual needs of each user.

[0594] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0595] Step 1:

[0596] The server collects data from information sources via the network. Specifically, the server uses APIs to retrieve text data from social media and news sites. This input data includes posts and articles in text format. The retrieved data is temporarily stored in a database.

[0597] Step 2:

[0598] The server preprocesses the collected raw data. It uses Python's regular expression tools to remove unwanted characters and noise. It also cleans the data and imputes missing values ​​using the Pandas library. This process yields analyzable structured data. The output is formatted text data.

[0599] Step 3:

[0600] The server analyzes preprocessed data using machine learning models. Scikit-learn is used for the analysis, building cluster analysis and regression models. Preprocessed data is provided as input. The output is information about specific patterns and trends, known as extracted business insights.

[0601] Step 4:

[0602] The server inputs prompt messages into the generating AI model and generates strategies and investment decisions based on the analysis results. Specifically, it uses prompt messages such as, "Please propose an investment strategy for the next quarter based on market trends." The output is text-based information regarding strategy proposals and investment decisions.

[0603] Step 5:

[0604] The device uses a camera and microphone to collect voice and facial expression data to identify the user's emotions. The input is real-time data from the user. The acquired emotion data is processed by an emotion analysis algorithm to identify the user's emotional state. This result is output as an emotion score.

[0605] Step 6:

[0606] The server customizes generated strategies and investment decisions based on sentiment data. Specifically, if the user indicates anxiety, it adjusts the information to emphasize suggestions for risk reduction. The output is customized strategic information tailored to the user's emotions.

[0607] Step 7:

[0608] The server transmits customized information to the terminal and presents it to the user. The terminal visually presents the received information to the user through an output device such as a display. This allows the user to review strategic information and use it to aid in decision-making.

[0609] (Application Example 2)

[0610] 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."

[0611] Conventional data analysis systems provide information generated without considering the user's psychological state or emotions, resulting in challenges in personalizing and accurately conveying information that contributes to user decision-making. Furthermore, in e-commerce, appropriate information is often not presented to effectively increase user purchasing intent. In this context, there is a need for strategic proposals and purchase-promoting information that take user emotions into account.

[0612] 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.

[0613] In this invention, the server includes means for collecting information from a data source via a network, means for preprocessing, cleaning, and structuring the collected information, and means for analyzing the preprocessed information and generating analysis results. This makes it possible to recognize the user's emotions, adjust the information based on those emotions, and provide personalized strategic suggestions and purchase promotion information.

[0614] A "network" is a system in which computers and other devices are connected to communicate information.

[0615] A "data source" refers to the place or system from which information is acquired, and it provides data in various formats.

[0616] "Preprocessing" refers to the process of preparing data for analysis, and includes steps such as noise reduction and data organization.

[0617] "Information cleaning" is the process of removing inaccurate or unnecessary parts from data and preparing it to be usable.

[0618] "Structuring" refers to organizing data into a specific format, thereby making it easier to analyze and search.

[0619] "Analysis results" refer to the output obtained after data analysis, including conclusions or insights based on the intended analysis.

[0620] "Business policy" refers to the strategies and plans for achieving business objectives, indicating the direction and activities that a company should adopt.

[0621] A "user terminal" is a device used by a user to receive and process information, and includes smartphones and personal computers.

[0622] "Feedback information" refers to information such as opinions and evaluations obtained from users that contribute to the improvement of a system or process.

[0623] "Learning and model optimization" is the process of adjusting a machine learning model using new data to improve it.

[0624] "User emotions" refers to the mental or psychological state that users exhibit while using the system, and is an element on which information is adjusted.

[0625] "Purchase promotion information" refers to incentives and marketing information provided to increase users' motivation to purchase products or services.

[0626] To implement this invention, the server first collects information from multiple data sources using a network. The collected data undergoes information cleaning and preprocessing and is converted into a structured format. Next, the server analyzes the preprocessed information using data analysis software and outputs the results as business policy and investment decision information using a generating AI model.

[0627] The emotion engine uses smartphones and other user devices to recognize the user's emotions from voice data, text data, and facial expression data. Based on the user's emotion data, the server adaptively adjusts the generated business policies and investment decision information. In particular, if the emotion engine detects an emotion that may influence the user's purchasing decision, the server immediately presents the user with specific purchase promotion information. This system is capable of providing optimal information tailored to emotions in real time.

[0628] As a concrete example, when a user is browsing products in an online shop, the system may detect hesitation in purchasing based on the user's tone of voice and facial expression. In this case, the server provides a promotional message such as, "Special sale today! Please use your 10% discount coupon," to encourage purchase. The prompt is given to the generating AI model as follows:

[0629] "Generate an appropriate incentive offer for a user who is hesitant to purchase. The user's sentiment data is as follows: Text 'Okay, but a little expensive,' Voice tone 'Doubtful,' Facial expression 'Thinking.' What incentive would be effective?"

[0630] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0631] Step 1:

[0632] The server collects information from various data sources via the network. Inputs include site logs, purchase history, and user search behavior data. By receiving this data and temporarily storing it in a database, the server prepares the foundational data necessary for subsequent analysis.

[0633] Step 2:

[0634] The server performs preprocessing and information cleaning on the collected data. It removes noise, standardizes data formats, and outputs structured data. Specifically, it imputes missing data and filters outliers to prepare a well-organized dataset.

[0635] Step 3:

[0636] The server analyzes the organized data and generates analysis results. During this process, machine learning algorithms are used to extract features and perform market analysis and customer trend predictions. It identifies meaningful patterns from the input data and outputs them as business insights.

[0637] Step 4:

[0638] The server uses a generative AI model to automatically generate business policies and investment decision information based on analysis results. By inputting prompts into the machine learning model, appropriate strategies and suggestions are obtained. The output consists of specific action items and investment recommendations.

[0639] Step 5:

[0640] The device uses an emotion engine to recognize the user's voice data, text data, and facial expression data. Based on the data acquired through the voice assistant and camera module, it performs emotion analysis and evaluates the user's psychological state.

[0641] Step 6:

[0642] The server analyzes the emotional data output by the emotion engine and adjusts business policies and investment decision information based on the user's emotions. For example, for users who are showing anxiety, it focuses on providing information that mitigates risk.

[0643] Step 7:

[0644] The terminal presents the user with pre-configured information from the server. Through the user interface, emotionally relevant and purchase-promoting information is displayed to effectively support the user's decision-making. Specific examples include discount coupons and information on special sales events.

[0645] 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.

[0646] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0647] 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.

[0648] [Fourth Embodiment]

[0649] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0650] 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.

[0651] 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).

[0652] 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.

[0653] 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.

[0654] 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).

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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".

[0662] This invention relates to a system that collects information from diverse data sources via a network, preprocesses and analyzes it, and automatically generates and provides information useful for business strategy and investment decisions. This system achieves these processes by utilizing generative AI through a specific algorithm.

[0663] First, the server utilizes communication infrastructure to collect information via the internet. For example, it retrieves news articles, social media posts, and publicly available company reports via crawling or APIs. Next, the server verifies the integrity of the retrieved information and preprocesses it to remove noise and unnecessary data.

[0664] The pre-processed information is analyzed by the server using natural language processing and machine learning techniques. The analysis extracts highly relevant business insights, which are then used to formulate business strategies. For example, market trends and competitor analysis are conducted, leading to concrete proposals for new market entry strategies and product lineups.

[0665] Furthermore, for investors, the server generates reports evaluating companies' financial health and growth forecasts based on the analysis results. This provides information to help them determine which companies are worth investing in.

[0666] Users (entrepreneurs or investors) receive these analysis results and suggestions through their devices. For example, if a user is considering launching a new business, they can develop a business plan based on the market strategy presented by the server. If a user is considering investing in a particular startup, they can refer to the server's analysis report to assess the risks and use it to help make an investment decision.

[0667] Furthermore, user feedback is collected by the server and used to improve the AI ​​model. This enhances the accuracy and effectiveness of suggestions, strengthening support for future strategy formulation and investment decisions.

[0668] The following describes the processing flow.

[0669] Step 1:

[0670] The server accesses data sources via the internet and collects the necessary information. In this process, it uses crawlers to collect data from news sites and social media, as well as to obtain publicly available company information through APIs.

[0671] Step 2:

[0672] The server preprocesses the collected information. In this process, natural language processing techniques are used to normalize the text data and remove noise. The information is also categorized and organized into structured data.

[0673] Step 3:

[0674] The server analyzes pre-processed data. Specifically, it uses machine learning models to conduct market trend and competitor analysis, extracting meaningful business insights. This data is then visualized in statistical metrics and graphs.

[0675] Step 4:

[0676] The server automatically generates business strategies based on the analysis results. In this process, the generating AI creates specific strategic proposals, such as strategies for entering new markets and measures to enhance existing products.

[0677] Step 5:

[0678] The server generates information to support investment decisions and creates company evaluation reports. This includes evaluating financial indicators and forecasting growth.

[0679] Step 6:

[0680] Users (entrepreneurs or investors) view analysis results and suggestions provided by the server from their terminals. Based on this, users develop their own business plans or make investment decisions.

[0681] Step 7:

[0682] Users send feedback on the suggestions and analyses they use to the server via their device. Based on this feedback, the server updates the AI ​​model to improve the accuracy of future suggestions and decisions.

[0683] (Example 1)

[0684] 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".

[0685] Efficiently collecting, integrating, and analyzing vast amounts of diverse information from various data sources, and then quickly and accurately providing business strategies and investment decisions based on that information, is a critical challenge in modern economic activity. This process requires advanced technical skills and efficient methods for information preprocessing, noise reduction, and improving the accuracy of analysis results. Furthermore, methods for effectively utilizing user feedback to continuously improve the accuracy of future proposals are also essential.

[0686] 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.

[0687] In this invention, the server includes means for collecting information from a data set via a network, means for preprocessing and structuring the collected information, and means for analyzing the data using natural language processing and machine learning techniques. This enables the efficient integration of diverse information and the provision of business strategies and investment decisions based on advanced analysis.

[0688] A "network" is a connection infrastructure used by computers and devices to communicate with each other, and is a structure that enables the sending and receiving of information.

[0689] A "data set" refers to a collection of information gathered for a specific purpose, and it may include numbers, characters, symbols, and other elements.

[0690] "Preprocessing" refers to the process of removing unnecessary data from collected information, imputing missing values, and preparing the data in a format that is easy to analyze.

[0691] "Structuring" refers to organizing data according to certain rules to make it easier to handle, thereby enabling efficient analysis.

[0692] "Analysis" is the act of using techniques such as natural language processing and machine learning to derive useful insights and patterns from collected and pre-processed information.

[0693] "Business strategy" refers to long-term plans and policies for corporate activities, which are determined by taking into account market trends and the situation of competitors.

[0694] "Investment decisions" refer to the process of determining which companies or projects should receive capital investment, based on financial data and market analysis.

[0695] "Feedback" refers to evaluations and opinions provided by users, and is information used to improve the system and enhance the accuracy of the model.

[0696] "Natural language processing" is a technology that enables computers to understand, interpret, and generate language that humans use on a daily basis.

[0697] Machine learning is a technology that enables computers to find patterns in data and automatically make predictions and decisions.

[0698] This invention is a data analysis system in which a server, terminal, and user work together to utilize information obtained via a network. The server collects information from multiple data sets and efficiently integrates and analyzes that information to enable business strategies and investment decisions.

[0699] The server collects information in real time using news APIs and social media APIs via the internet. The collected information is converted into a data frame using the Python Pandas library, and preprocessing is performed to impute missing values ​​and filter out noise. Subsequently, the information is analyzed using the NLTK library for natural language processing and generative AI models from TensorFlow and OpenAI for machine learning.

[0700] The analyzed data is used for business strategies and investment decisions. Business strategies are automatically generated based on market trends and competitive analysis. Specific examples include optimizing the timing of new product launches and reviewing product lineups. Investment decisions are evaluated based on a company's financial health and growth forecasts, contributing to the selection of investment targets.

[0701] Users receive the results of business strategies and investment decisions provided via their devices. By accessing the dashboard, users can visually review the analysis results and decide on necessary actions. For example, if a user is looking for a specific strategy to enter a new market, the server will present specific suggestions based on a prompt such as, "Please propose a strategy for entering a new market. This strategy should be based on recent industry trends and competitive analysis."

[0702] Furthermore, user feedback is collected by the server and used as training data for the generated AI model. This allows for model improvement based on feedback, thereby improving the accuracy of future suggestions.

[0703] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0704] Step 1:

[0705] The server first collects information via the internet. At this stage, it utilizes news APIs and social media APIs to obtain real-time data. The input is raw data obtained from the APIs, and the output is that data in its raw form. This raw data includes information such as the article title, body text, publication date and time, and source. Specifically, the server queries the APIs at regular intervals and executes scripts to retrieve new data.

[0706] Step 2:

[0707] The server performs preprocessing on the collected data. This preprocessing uses the Python Pandas library to convert the data into a data frame and performs missing value imputation and noise filtering. The input is the raw data obtained in step 1, and the output is a clean, prepared dataset. Specifically, the server fills in missing values ​​with the mean or median, and deletes rows that do not meet certain conditions. It also performs text tokenization and stop word removal using NLTK.

[0708] Step 3:

[0709] The server performs analysis on the pre-processed data. This analysis utilizes natural language processing and machine learning techniques, employing TensorFlow and generative AI models. The input is the clean dataset obtained in step 2, and the output is the analysis results, i.e., business insights. Specifically, the AI ​​model is fed context, and topic modeling and sentiment analysis are performed to extract key trends and customer sentiment.

[0710] Step 4:

[0711] The server automatically generates business strategies and investment decisions based on the analysis results. It utilizes a generating AI model to form specific recommended strategies and decision-making information. The input is the analysis results obtained in step 3, and the output is specific strategy proposals and investment reports. Specifically, the generating AI model performs evaluations, automatically generates strategy documents and reports, and customizes them as needed to match user-specified conditions.

[0712] Step 5:

[0713] The server provides the generated business strategies and investment decisions to the user's terminal. This allows the user to review the strategies and take necessary actions. The input is the output generated in step 4, and the output is displayed in a format that is easy for the user to understand. Specifically, the server displays the results on a dashboard via a web browser or a dedicated application.

[0714] Step 6:

[0715] Users provide feedback. They input their opinions and evaluations of the analysis results and suggestions through their terminals. The input is user feedback, and the output is feedback data sent to the server. Specifically, users use a feedback form to input satisfaction ratings and improvement requests.

[0716] Step 7:

[0717] The server receives feedback information from users and uses it to train the AI ​​model. Based on the feedback, it adjusts the model's parameters to improve the accuracy of future strategic suggestions and investment decisions. The input is the feedback data obtained in step 6, and the output is the improved AI model's parameter settings. Specifically, the server feeds the feedback data into the learning algorithm and retrains the model.

[0718] (Application Example 1)

[0719] 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".

[0720] Conventional information analysis systems struggle to effectively collect and analyze large amounts of data, particularly in response to the need for rapid, real-time decision-making regarding business strategies and resource allocation. Furthermore, a lack of clear and visually appealing methods for representing analysis results has prevented users from fully utilizing the information they obtain in their actual work. Additionally, continuous model optimization and incorporation of user feedback to improve the accuracy of generated information are insufficient.

[0721] 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.

[0722] In this invention, the server includes means for collecting data from information sources via a network, means for preprocessing, cleaning, and structuring the collected data, means for analyzing the preprocessed data and generating analysis results, and means for displaying the analysis results using a visual display based on augmented reality technology. This enables users to visually check various types of information in real time and make quick and accurate decisions regarding business strategies and resource allocation.

[0723] "Means of collecting data from information sources via a network" refers to the function of obtaining information from various data sources such as news articles, company reports, and social media via the internet or intranet.

[0724] "Methods for preprocessing, cleaning, and structuring collected data" refers to the process of checking the integrity and quality of acquired data, removing and organizing noise, and converting it into a form that is easy to analyze.

[0725] "Means for analyzing pre-processed data and generating analysis results" refers to a function that uses machine learning and natural language processing techniques to execute algorithms that derive useful business insights and trends from cleaned data.

[0726] "Means of displaying analysis results based on augmented reality technology using visual displays" refers to a function that utilizes augmented reality (AR) to provide users with an easy-to-understand graphical visual representation of analysis results.

[0727] "Business strategy" refers to plans and guidelines that companies and organizations formulate to respond to market trends and competitive situations based on collected and analyzed information.

[0728] "Information that supports resource allocation decisions" refers to data and analytical results that assist in determining which business areas or projects should receive the most resources.

[0729] "User's device" refers to a terminal used to view or operate information provided by the system, such as a smartphone, tablet, or personal computer.

[0730] "Means of receiving evaluation information and using it for learning and model optimization" refers to the process of collecting feedback from users, updating the AI ​​model based on that feedback, and improving the accuracy of future suggestions and analyses.

[0731] The system implementing this invention leverages a network infrastructure that includes cloud-based servers and user equipment. The servers automatically collect data from diverse sources on the internet, such as news articles, company reports, and social media, using advanced data collection programs. This data is preprocessed in real time on streaming platforms such as Apache Kafka, where noise is removed and the data is formatted. The collected data is then analyzed using natural language processing and machine learning techniques, utilizing Amazon SageMaker and Google Cloud AI Platform. Generative AI models are used to extract information from the data that supports business insights and resource allocation decisions.

[0732] The user's device has an interface to receive analysis results and present them to the user visually. This utilizes augmented reality (AR) applications and graphical displays implemented with Unity or React Native. As a result, the user can intuitively understand the analysis results and make effective business strategy and resource allocation decisions in real time.

[0733] Specifically, when a user enters prompts such as, "What are the current trends in the renewable energy industry?" or "Show me the growth forecast for technology companies in the next quarter," the server collects and analyzes relevant information and sends the results to the user's device. Based on this information, the user can quickly proceed with the decision-making process. Evaluations and feedback from the user are continuously sent to the server, so the accuracy of the model and the effectiveness of the suggestions continue to improve.

[0734] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0735] Step 1:

[0736] The server collects data from multiple sources via the internet. Specifically, it retrieves news articles, company reports, and social media data using APIs or web crawling technologies. Inputs include target keywords and URLs, and output is the original data.

[0737] Step 2:

[0738] The server preprocesses the acquired data. This process verifies data integrity, removes duplicates and noise, and structures the data. The input is the raw data acquired in step 1, and the output is a clean and organized dataset. Specifically, a text cleaning algorithm is used to remove extraneous symbols and spaces.

[0739] Step 3:

[0740] The server utilizes a generative AI model to analyze the preprocessed data. Through natural language processing algorithms, it extracts useful business insights and patterns from the data. The input is the data cleaned in step 2, and the output is the insights and trends obtained through the analysis. Specifically, a machine learning model operates to identify key features from the dataset.

[0741] Step 4:

[0742] The user's device receives the analysis results sent from the server and displays them visually. This process uses augmented reality technology to present information visually. The input is the analysis results generated in step 3, and the output is a visual display that the user can view. Specifically, the Unity or React Native platform is used, and interactive displays utilizing AR are implemented.

[0743] Step 5:

[0744] The user makes a decision based on the information provided and sends feedback to the server. This user feedback is used for the next model retraining. The input is the user's evaluation and improvement requests, and the output is the feedback data sent to the server. Specifically, the user inputs comments and evaluation scores through the application interface.

[0745] Step 6:

[0746] The server receives feedback from the user and retrains the generated AI model. In this phase, the improved model is used for subsequent analyses. The input is the feedback data received in step 5, and the output is the new model with improved accuracy. Specifically, the server adjusts the model's hyperparameters using the feedback data and then retrains it.

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

[0748] This invention provides a system that improves the accuracy of strategic and investment information by combining a system that collects, preprocesses, and analyzes data via a network and automatically generates business strategies and investment decisions based on that data with an emotion engine that recognizes user emotions.

[0749] First, the server collects information from various data sources via the network as usual, performs noise reduction and information cleaning, and prepares it as structured data. Next, the server analyzes the collected information and extracts business insights. Based on these results, it automatically generates information for business strategy and investment decisions using AI.

[0750] The emotion engine in this system recognizes the user's emotions through voice, facial expressions, text input, and other data while the user is using the device. The server receives this emotion data and customizes business strategies and investment decision information according to the user's emotions. For example, if the user is showing anxiety, the system will enhance strategic suggestions to mitigate risks and prioritize presenting information that provides reassurance.

[0751] As a concrete example, consider a scenario where a user is considering investing in a new business. The server analyzes the collected data to predict market growth and conduct competitive analysis, generating a business strategy. Meanwhile, the emotion engine evaluates how the user feels about the information presented. If the emotion data indicates that the user is overly optimistic, the server will perform a reality check, emphasizing realistic risks to support a balanced decision.

[0752] Thus, systems equipped with an emotion engine provide strategic recommendations and investment information that reflect the user's psychological state, enabling more personalized decision-making support. This approach is crucial for enhancing the influence on user behavior and decisions compared to conventional information delivery methods.

[0753] The following describes the processing flow.

[0754] Step 1:

[0755] The server collects data from news articles, social media, and publicly available corporate data via the network. It uses crawlers and APIs to efficiently retrieve the necessary information.

[0756] Step 2:

[0757] The server preprocesses the collected data. Specifically, it removes noise, normalizes text, and categorizes the data to prepare it as analyzable structured data.

[0758] Step 3:

[0759] The server analyzes the pre-processed data. It applies machine learning algorithms to analyze market trends and competitor activities, extracting business insights. At this stage, the analysis results are formatted as statistical indicators and visual data.

[0760] Step 4:

[0761] The server automatically generates business strategies based on the analysis results. Utilizing the AI-generated strategies, it specifically proposes measures for developing new markets and strengthening existing strategies.

[0762] Step 5:

[0763] Users receive strategic proposals and investment information generated by the server through their devices. At this stage, the information is displayed in a user-friendly interface, making it easy to view.

[0764] Step 6:

[0765] The emotion engine built into the device recognizes the user's emotional state. Through voice recognition, facial expression analysis, and text input analysis, it identifies what emotions the user is experiencing.

[0766] Step 7:

[0767] The server adjusts the input information based on the user's emotional data obtained from the emotion engine. For example, if the user is feeling anxious, the server adjusts the output by emphasizing more detailed explanations to provide reassurance or suggestions to mitigate risks.

[0768] Step 8:

[0769] Users can view personalized, emotion-based suggestions on their devices to aid in business planning and investment decisions. The goal is to improve the quality of decision-making based on the information provided.

[0770] Step 9:

[0771] User feedback is sent to the server via the device. The server uses this information to update the AI ​​model, continuously improving the overall accuracy and effectiveness of the system.

[0772] (Example 2)

[0773] 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".

[0774] In today's diverse business environment, business strategies and investment decisions must not only be based on data analysis but also consider the emotions and psychological states of individual users. However, conventional systems do not adequately provide information that takes user emotions into account, resulting in a lack of accuracy in providing personalized decision support. There is a need to solve this problem and realize more effective decision support.

[0775] 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.

[0776] In this invention, the server includes means for collecting data from information sources via a network, means for preprocessing, cleaning, and structuring the collected data, means for analyzing the preprocessed data and extracting the analysis results, and means for identifying the user's emotions and adjusting business strategy and investment decision information according to the identified emotions. This makes it possible to provide strategies and investment decisions that reflect the user's emotions.

[0777] A "network" refers to a connection between multiple computers or devices built to send and receive data.

[0778] "Information source" refers to the database, online platform, or other data provision infrastructure from which data is obtained.

[0779] "Data collection" refers to the process of gathering information from various sources to achieve a specific purpose.

[0780] "Preprocessing" refers to the process of removing noise and imputing missing values ​​in order to convert raw data into an analyzable format.

[0781] "Data cleanup" refers to the process of deleting or correcting unnecessary or incorrect information in order to improve data quality.

[0782] "Data structuring" refers to the process of organizing collected information into a specific format to make it easier to handle.

[0783] "Analysis" refers to the process of analyzing data to uncover hidden patterns and useful information.

[0784] "Generative AI" refers to a type of artificial intelligence that generates new content such as text and images based on presented data and prompts.

[0785] "Business strategy" refers to the plans and policies that a company or organization aims to achieve in order to accomplish its ultimate goals.

[0786] "Investment decision" refers to the evaluation and selection process used to determine which businesses or projects to allocate capital to.

[0787] "Emotional identification" refers to the process of interpreting a user's psychological state and emotions from their words, facial expressions, and actions.

[0788] "Adjustment" refers to the act of making changes to optimize existing plans and policies as needed or in accordance with the circumstances.

[0789] "Feedback" refers to information and evaluations received regarding actions and results, which are used as a reference for improvement.

[0790] "Learning" refers to the process of acquiring knowledge and skills based on experience and information, and improving one's abilities.

[0791] This invention realizes a system that can provide users with optimized business strategies and investment decisions by utilizing multiple means. Specific embodiments thereof are shown below.

[0792] Data acquisition and preprocessing

[0793] The server first collects data from various sources via the network. Specifically, it uses social media platforms, news websites, and economic databases as sources. The Python requests library is used to retrieve the data. Next, the Python Pandas library is used to clean and structure the collected data. This removes noise and irrelevant information and prepares it in a format suitable for analysis.

[0794] Strategy generation using data analysis and generative AI.

[0795] The server analyzes pre-processed data and extracts business insights. The analysis uses the Scikit-learn library to perform cluster analysis and regression analysis. Furthermore, a generative AI model is used to automatically generate strategies and investment decisions based on the extracted insights. In this process, a large-scale language model is used for the generative AI, and an example of a prompt is, "Please propose an investment strategy for the next quarter based on market trends, but please take into account the concerns expressed by the user."

[0796] Emotion recognition and information customization

[0797] The device uses its camera and microphone to collect facial expressions and voice to recognize the user's emotions. The collected data is processed by an emotion analysis algorithm to evaluate the user's current psychological state. Based on this emotion data, the server customizes strategies and investment information. For example, if the user indicates anxiety, the server strengthens suggestions to mitigate risk.

[0798] Application examples

[0799] As a practical example, consider a user considering investing in a new business. In this case, the server performs market analysis and proposes a strategy based on the competitive landscape and growth forecasts. Meanwhile, the terminal analyzes the user's reactions and provides additional reassuring information if the user is feeling anxious. This allows the user to make a more balanced decision.

[0800] Thus, by combining data analysis and emotion recognition, this invention can provide decision-making support tailored to the individual needs of each user.

[0801] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0802] Step 1:

[0803] The server collects data from information sources via the network. Specifically, the server uses APIs to retrieve text data from social media and news sites. This input data includes posts and articles in text format. The retrieved data is temporarily stored in a database.

[0804] Step 2:

[0805] The server preprocesses the collected raw data. It uses Python's regular expression tools to remove unwanted characters and noise. It also cleans the data and imputes missing values ​​using the Pandas library. This process yields analyzable structured data. The output is formatted text data.

[0806] Step 3:

[0807] The server analyzes preprocessed data using machine learning models. Scikit-learn is used for the analysis, building cluster analysis and regression models. Preprocessed data is provided as input. The output is information about specific patterns and trends, known as extracted business insights.

[0808] Step 4:

[0809] The server inputs prompt messages into the generating AI model and generates strategies and investment decisions based on the analysis results. Specifically, it uses prompt messages such as, "Please propose an investment strategy for the next quarter based on market trends." The output is text-based information regarding strategy proposals and investment decisions.

[0810] Step 5:

[0811] The device uses a camera and microphone to collect voice and facial expression data to identify the user's emotions. The input is real-time data from the user. The acquired emotion data is processed by an emotion analysis algorithm to identify the user's emotional state. This result is output as an emotion score.

[0812] Step 6:

[0813] The server customizes generated strategies and investment decisions based on sentiment data. Specifically, if the user indicates anxiety, it adjusts the information to emphasize suggestions for risk reduction. The output is customized strategic information tailored to the user's emotions.

[0814] Step 7:

[0815] The server transmits customized information to the terminal and presents it to the user. The terminal visually presents the received information to the user through an output device such as a display. This allows the user to review strategic information and use it to aid in decision-making.

[0816] (Application Example 2)

[0817] 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".

[0818] Conventional data analysis systems provide information generated without considering the user's psychological state or emotions, resulting in challenges in personalizing and accurately conveying information that contributes to user decision-making. Furthermore, in e-commerce, appropriate information is often not presented to effectively increase user purchasing intent. In this context, there is a need for strategic proposals and purchase-promoting information that take user emotions into account.

[0819] 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.

[0820] In this invention, the server includes means for collecting information from a data source via a network, means for preprocessing, cleaning, and structuring the collected information, and means for analyzing the preprocessed information and generating analysis results. This makes it possible to recognize the user's emotions, adjust the information based on those emotions, and provide personalized strategic suggestions and purchase promotion information.

[0821] A "network" is a system in which computers and other devices are connected to communicate information.

[0822] A "data source" refers to the place or system from which information is acquired, and it provides data in various formats.

[0823] "Preprocessing" refers to the process of preparing data for analysis, and includes steps such as noise reduction and data organization.

[0824] "Information cleaning" is the process of removing inaccurate or unnecessary parts from data and preparing it to be usable.

[0825] "Structuring" refers to organizing data into a specific format, thereby making it easier to analyze and search.

[0826] "Analysis results" refer to the output obtained after data analysis, including conclusions or insights based on the intended analysis.

[0827] "Business policy" refers to the strategies and plans for achieving business objectives, indicating the direction and activities that a company should adopt.

[0828] A "user terminal" is a device used by a user to receive and process information, and includes smartphones and personal computers.

[0829] "Feedback information" refers to information such as opinions and evaluations obtained from users that contribute to the improvement of a system or process.

[0830] "Learning and model optimization" is the process of adjusting a machine learning model using new data to improve it.

[0831] "User emotions" refers to the mental or psychological state that users exhibit while using the system, and is an element on which information is adjusted.

[0832] "Purchase promotion information" refers to incentives and marketing information provided to increase users' motivation to purchase products or services.

[0833] To implement this invention, the server first collects information from multiple data sources using a network. The collected data undergoes information cleaning and preprocessing and is converted into a structured format. Next, the server analyzes the preprocessed information using data analysis software and outputs the results as business policy and investment decision information using a generating AI model.

[0834] The emotion engine uses smartphones and other user devices to recognize the user's emotions from voice data, text data, and facial expression data. Based on the user's emotion data, the server adaptively adjusts the generated business policies and investment decision information. In particular, if the emotion engine detects an emotion that may influence the user's purchasing decision, the server immediately presents the user with specific purchase promotion information. This system is capable of providing optimal information tailored to emotions in real time.

[0835] As a concrete example, when a user is browsing products in an online shop, the system may detect hesitation in purchasing based on the user's tone of voice and facial expression. In this case, the server provides a promotional message such as, "Special sale today! Please use your 10% discount coupon," to encourage purchase. The prompt is given to the generating AI model as follows:

[0836] "Generate an appropriate incentive offer for a user who is hesitant to purchase. The user's sentiment data is as follows: Text 'Okay, but a little expensive,' Voice tone 'Doubtful,' Facial expression 'Thinking.' What incentive would be effective?"

[0837] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0838] Step 1:

[0839] The server collects information from various data sources via the network. Inputs include site logs, purchase history, and user search behavior data. By receiving this data and temporarily storing it in a database, the server prepares the foundational data necessary for subsequent analysis.

[0840] Step 2:

[0841] The server performs preprocessing and information cleaning on the collected data. It removes noise, standardizes data formats, and outputs structured data. Specifically, it imputes missing data and filters outliers to prepare a well-organized dataset.

[0842] Step 3:

[0843] The server analyzes the organized data and generates analysis results. During this process, machine learning algorithms are used to extract features and perform market analysis and customer trend predictions. It identifies meaningful patterns from the input data and outputs them as business insights.

[0844] Step 4:

[0845] The server uses a generative AI model to automatically generate business policies and investment decision information based on analysis results. By inputting prompts into the machine learning model, appropriate strategies and suggestions are obtained. The output consists of specific action items and investment recommendations.

[0846] Step 5:

[0847] The device uses an emotion engine to recognize the user's voice data, text data, and facial expression data. Based on the data acquired through the voice assistant and camera module, it performs emotion analysis and evaluates the user's psychological state.

[0848] Step 6:

[0849] The server analyzes the emotional data output by the emotion engine and adjusts business policies and investment decision information based on the user's emotions. For example, for users who are showing anxiety, it focuses on providing information that mitigates risk.

[0850] Step 7:

[0851] The terminal presents the user with pre-configured information from the server. Through the user interface, emotionally relevant and purchase-promoting information is displayed to effectively support the user's decision-making. Specific examples include discount coupons and information on special sales events.

[0852] 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.

[0853] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0854] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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."

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0873] The following is further disclosed regarding the embodiments described above.

[0874] (Claim 1)

[0875] Means for collecting information from data sources via a network,

[0876] A means of preprocessing, cleaning, and structuring the collected information,

[0877] A means for analyzing pre-processed information and generating analysis results,

[0878] A means of automatically generating business strategies based on analysis results,

[0879] A means of providing the generated business strategy to the user terminal,

[0880] A means for generating information to support investment decisions based on analysis results,

[0881] A means for providing the generated investment decision information to the user terminal,

[0882] A means of receiving user feedback information and using it for training and model optimization,

[0883] A system that includes this.

[0884] (Claim 2)

[0885] The system according to claim 1, comprising means for optimizing business strategies based on analysis results using generative AI.

[0886] (Claim 3)

[0887] The system according to claim 1, comprising means for updating the AI ​​model based on feedback information to improve the accuracy of future strategic proposals and investment decisions.

[0888] "Example 1"

[0889] (Claim 1)

[0890] A means of collecting information from a data set via a network,

[0891] A means of preprocessing and structuring the collected information,

[0892] A means for analyzing pre-processed information and deriving analysis results,

[0893] A means of automatically generating business strategies based on analysis results,

[0894] A means of presenting the generated business strategy to the user device,

[0895] A means of forming information to support investment decisions based on analysis results,

[0896] Means for providing the generated investment decision information to the user device,

[0897] A means of receiving user feedback and using it to improve training and models,

[0898] A means to impute missing values ​​in the collected information and filter out noise,

[0899] A means of analyzing data using natural language processing and machine learning techniques,

[0900] A system that includes this.

[0901] (Claim 2)

[0902] The system according to claim 1, comprising means for optimizing business strategies based on analysis results using generative AI.

[0903] (Claim 3)

[0904] The system according to claim 1, comprising means for updating the AI ​​model based on feedback to improve the accuracy of future strategic proposals and investment decisions.

[0905] "Application Example 1"

[0906] (Claim 1)

[0907] Means for collecting data from information sources via a network,

[0908] A means of preprocessing, cleaning, and structuring the collected data,

[0909] A means for analyzing pre-processed data and generating analysis results,

[0910] A means of automatically generating business strategies based on analysis results,

[0911] A means of providing the generated business strategy to the user's device,

[0912] A means for generating information that supports resource allocation decisions based on analysis results,

[0913] A means for providing the generated resource allocation information to the user's device,

[0914] A means of receiving evaluation information from users and using it for learning and model optimization,

[0915] A means of displaying analysis results using visual representations based on augmented reality technology,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, comprising means for optimizing business strategies based on analysis results using generative artificial intelligence.

[0919] (Claim 3)

[0920] The system according to claim 1, comprising means for updating an artificial intelligence model based on evaluation information to improve the accuracy of strategic proposals and resource allocation decisions for subsequent times.

[0921] "Example 2 of combining an emotion engine"

[0922] (Claim 1)

[0923] Means for collecting data from information sources via a network,

[0924] A means of preprocessing, cleaning, and structuring the collected data,

[0925] A means for analyzing preprocessed data and extracting the analysis results,

[0926] A means of automatically generating business strategies using AI based on analysis results,

[0927] A means of providing the generated business strategy to the user's terminal,

[0928] A means for generating information to support investment decisions based on analysis results,

[0929] A means for providing the generated investment decision information to the user's terminal,

[0930] A means for identifying user emotions and adjusting business strategies and investment decision information according to the identified emotions,

[0931] A means of customizing the information suggested based on user sentiment data,

[0932] A means of receiving feedback information from users and using it for learning and model optimization,

[0933] A system that includes this.

[0934] (Claim 2)

[0935] The system according to claim 1, comprising means for individualizing and optimizing business strategies and investment decisions based on analysis results using generative AI.

[0936] (Claim 3)

[0937] The system according to claim 1, comprising means for updating the AI ​​model based on feedback and sentiment data to improve the accuracy of future strategic proposals and investment decisions.

[0938] "Application example 2 when combining with an emotional engine"

[0939] (Claim 1)

[0940] A means of collecting information from a data source via a network,

[0941] A means of preprocessing, cleaning, and structuring the collected information,

[0942] A means for analyzing pre-processed information and generating analysis results,

[0943] A means of automatically generating business policies based on analysis results,

[0944] A means of providing the generated business policy to the user's terminal,

[0945] A means for generating information to support investment decisions based on analysis results,

[0946] A means for providing the generated investment decision information to the user's terminal,

[0947] A means of receiving user feedback information and using it for learning and model optimization,

[0948] A means of recognizing the emotions of users and adjusting the business policies and investment decision information provided based on those emotions,

[0949] A means of presenting purchase promotion information in response to changes in user sentiment,

[0950] A system that includes this.

[0951] (Claim 2)

[0952] The system according to claim 1, comprising means for optimizing business policies based on analysis results using generating AI.

[0953] (Claim 3)

[0954] The system according to claim 1, comprising means for updating a machine learning model based on feedback information to improve the accuracy of future policy proposals and investment decisions. [Explanation of Symbols]

[0955] 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. Means for collecting information from data sources via a network, A means of preprocessing, cleaning, and structuring the collected information, A means for analyzing pre-processed information and generating analysis results, A means of automatically generating business strategies based on analysis results, A means of providing the generated business strategy to the user terminal, A means for generating information to support investment decisions based on analysis results, A means for providing the generated investment decision information to the user terminal, A means of receiving user feedback information and using it for training and model optimization, A system that includes this.

2. The system according to claim 1, comprising means for optimizing business strategies based on analysis results using generative AI.

3. The system according to claim 1, comprising means for updating the AI ​​model based on feedback information to improve the accuracy of future strategic proposals and investment decisions.

Images