system

Abstract

We provide the system. [Solution] A data collection means that autonomously collects information related to a specific domain, Information analysis means that analyzes information based on collected data and identifies industry trends, A command management means that generates commands based on the analyzed information and determines their priority, A display generation means that visualizes and generates output results based on prioritized commands, A human interaction interface means for delivering the output results to a terminal, A means of collecting and analyzing real-time information including traffic conditions, road conditions, and weather information, A system that includes this.

Description

Technical Field

[0005]

[0001] The technology of this 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 recent years, it has become an important issue for companies to quickly and efficiently collect and analyze relevant information from data provided by a large number of information sources. However, with the existing technologies, the condition setting for information collection is complicated, and the analysis and reporting of information are often performed manually, making it difficult to make timely decisions. Therefore, there is a demand for a system that automatically collects and analyzes news and trend information in a specific field and reports it quickly and efficiently.

Means for Solving the Problems

[0005] The present invention provides an information gathering means for autonomously collecting data related to a specific field, a data analysis means for analyzing the collected data and identifying industry trends, a task management means for generating tasks based on the analyzed data and determining their priority, an output generation means for visualizing and generating output results based on the prioritized tasks, and a user interface means for delivering the output results to a terminal. By providing this information gathering and reporting, it is possible to automate information gathering and reporting and support a company's marketing activities and rapid decision-making.

[0006] "Data related to a specific field" refers to information related to a particular industry or topic, including news, articles, and social media posts concerning trends and developments in that industry.

[0007] "Information gathering means" refers to technical methods for automatically obtaining relevant data from various information sources on the internet, such as using web crawlers and APIs to collect data.

[0008] "Data analysis methods" refer to technical means used to analyze collected data and derive meaningful insights, and involve processing data using statistical methods and machine learning algorithms.

[0009] "Industry trends" refer to the overall movements and changes within a particular industry, and are used to make future predictions based on them.

[0010] A "task management system" refers to a function that manages the types and volume of generated tasks and automatically determines their priority, thereby supporting the efficient execution of tasks.

[0011] "Output generation means" refers to a function that formats analysis results as visual information and outputs them as reports, graphs, and charts, thereby aiding in the understanding of the information.

[0012] "User interface means" refers to an interface that allows users to access analysis results and outputs and efficiently receive information, and it provides information visually in a dashboard format. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] The present invention is a system whose primary purpose is to autonomously collect and analyze information in a specific field and to rapidly report the results. This system includes information collection means, data analysis means, task management means, output generation means, and user interface means.

[0035] The server automatically collects relevant data from various sources on the internet using web crawlers and APIs as information gathering tools. This includes news sites, social networking platforms, and official company websites. Information gathering is designed to be autonomous and performed regularly.

[0036] The collected data is processed by data analysis tools. The server uses multiple machine learning algorithms to analyze the collected data, deriving insights such as industry trends and the actions of specific companies. In this process, it is possible to identify new trends by comparing them with past data.

[0037] Based on the analysis results, the AI ​​agent generates new tasks using task management tools. Task priorities are determined according to the importance and urgency of the discovered information. For example, information regarding rapid market changes is recognized as a high-priority task.

[0038] In the output generation method, the server generates analysis results as reports and visualized data. This generated output is then presented as graphs and charts, making it visible to the user. This allows the user to quickly understand the information and use it to aid in decision-making.

[0039] Through a user interface, users operating on a terminal can receive these outputs in a dashboard format. Users can customize the dashboard to prioritize the display of information relevant to specific industries or topics. This allows users to quickly obtain the information they need and perform their tasks efficiently.

[0040] In this way, the system of the present invention achieves consistent automation from information collection to analysis and reporting, supporting companies' marketing activities and rapid decision-making.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server launches an information gathering script, using a web crawler and APIs to collect data related to a specific area from news sites and social media on the internet. The collection is performed regularly on an automated schedule, filtering the data based on specified keywords.

[0044] Step 2:

[0045] The server stores the collected data in a temporary database and uses natural language processing techniques to extract relevant information. It then removes noisy and duplicate data to create a clean dataset.

[0046] Step 3:

[0047] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This reveals industry trends and the actions of specific companies, and new insights can be derived by comparing them with past trends.

[0048] Step 4:

[0049] Based on the analysis results, the server generates tasks through an AI agent and determines the priority of those tasks. Information regarding rapid market changes and important events is given the utmost attention when prioritizing.

[0050] Step 5:

[0051] The server uses output generation mechanisms to generate reports and visualized data based on the analysis results. This output is generated in the form of graphs, charts, and sometimes video clips, formatting the information for easy understanding.

[0052] Step 6:

[0053] This final output is delivered to the user interface, where users can view it on a dashboard via their devices. Users can customize the dashboard to their individual needs, quickly access the information they require, and make efficient business decisions.

[0054] (Example 1)

[0055] 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."

[0056] In modern society, a vast amount of information exists on digital networks, but efficiently collecting, analyzing, and obtaining useful information from this data is difficult. Furthermore, appropriately prioritizing information and presenting it visually to users is also a challenge. In particular, in business, there is a need to acquire and analyze relevant information in a timely manner to support rapid decision-making.

[0057] 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.

[0058] In this invention, the server includes data collection means, information processing means, and business management means. This makes it possible to automatically collect large amounts of information, analyze that information to generate tasks, and set priorities as needed. Through this series of processes, users can quickly obtain useful information and perform their tasks efficiently.

[0059] "Data collection means" refers to a device or process for efficiently acquiring necessary information from a digital network.

[0060] "Information processing means" refers to a device or method for analyzing acquired information using an automated calculation model to derive useful insights and trends.

[0061] A "business management tool" is a device or process for generating necessary tasks based on analysis results and appropriately setting their priorities.

[0062] "Result generation means" refers to a device or method for visually representing the results of analyzed information and presenting them in a way that is easy for the user to understand.

[0063] "User connection means" refers to a device or process for providing the generated results to the user via a communication device.

[0064] This invention relates to a system that efficiently collects and analyzes vast amounts of information on a digital network and provides useful information to users. This system includes data collection means, information processing means, and business management means.

[0065] The server collects information from the internet using web crawlers and APIs as data collection tools. Specific software used in this process includes Python's Beautiful Soup and Scrapy. The server retrieves data from news sites and social media platforms based on configured keywords. For example, to collect articles related to a specific industry, it periodically crawls web pages and retrieves their content as text data.

[0066] Next, the server uses information processing tools to analyze the collected data. This analysis utilizes machine learning algorithms to identify data trends and patterns. Specifically, it leverages tools such as Scikit-learn and TENSORFLOW®. The server can compare historical and current data to identify new business trends. For example, it can use sales data to predict new market trends.

[0067] The task management system allows the server to generate new tasks based on analysis results and determine their priority. Tasks can be allocated according to urgency and importance. For example, if the entry of a new competitor is discovered, tasks for further investigation into that competitor may be prioritized and scheduled.

[0068] The output is visually represented through result generation methods and accessible to users on their devices. For example, data can be presented as graphs and charts using visualization tools such as Tableau. This allows users to quickly grasp information and support their decision-making in their work.

[0069] Users can access information through their devices in a dashboard format, obtaining the latest information on specific fields and topics. For example, by entering a prompt such as, "Show me important news related to the latest technology in a dashboard format," predefined information will be organized and displayed. In this way, the system effectively collects and analyzes information, providing users with the information they need in a timely manner.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] The server accesses the digital network and collects data using web crawlers and APIs. Specific keywords or topics are provided as input. For example, to obtain information about art exhibitions or cultural events, the URL of a configured website and the data format to be retrieved are specified. The server uses Beautiful Soup to parse the HTML document and extract text information from the specified elements. The output is the collected raw data.

[0073] Step 2:

[0074] The server utilizes Scikit-learn to begin analyzing the collected data. The input is the raw data collected in the previous step. Specifically, it filters out the necessary information from the data and performs data cleansing. During this process, data preprocessing such as normalization and handling of missing values ​​is performed. The output is an analyzable dataset.

[0075] Step 3:

[0076] The server uses the cleansed data to perform trend analysis using machine learning algorithms. The input for this step is the dataset generated in the previous step. Specifically, it performs regression analysis and clustering to predict new trends and patterns by comparing them with historical data. The output is the results of the trend analysis and the recognized patterns.

[0077] Step 4:

[0078] The server generates new tasks and sets their priorities based on the analysis results. The input utilizes the results of trend analysis. Specifically, it runs a scoring model to identify high-priority tasks. For example, tasks such as detailed investigation and action planning are automatically generated for topics that are rapidly gaining attention. The output is a prioritized list of tasks.

[0079] Step 5:

[0080] The server uses visualization tools such as Tableau to generate a visual report of the analysis results. The input for this process is the task list and analysis results generated in step 4. Specifically, it converts the data into graphs and charts and creates a report in a format that is easy for the user to understand intuitively. The output is a visualized report.

[0081] Step 6:

[0082] The user receives generated reports and task lists through their device. The input for this step is reports generated by a visualization tool. The information is displayed in a dashboard format on the device, and the interface is customized to allow the user to focus on specific data. The output is visualized information to support user decision-making. The user can obtain this information by entering a prompt such as, "Please display important news related to the latest technology in a dashboard format."

[0083] (Application Example 1)

[0084] 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."

[0085] Autonomous vehicles are required to accurately grasp traffic and weather conditions in real time to support safe and efficient driving. However, current systems face the challenge of not being able to effectively collect and analyze this information and feed it back into autonomous driving.

[0086] 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.

[0087] In this invention, the server includes data collection means for autonomously collecting information related to a specific area, information analysis means for analyzing the collected information and identifying industry trends, and means for collecting and analyzing real-time information including traffic conditions, road conditions, and weather information. This enables autonomous vehicles to operate safely and efficiently in real time.

[0088] "Information related to a specific domain" refers to data that affects the operation of autonomous vehicles, such as traffic conditions, road conditions, and weather information.

[0089] "Data collection means" refers to technological means for autonomously acquiring necessary information via online services on the internet or sensors.

[0090] "Information analysis methods" refer to technical means that use machine learning techniques to derive patterns and trends based on collected data, and utilize them to optimize operations.

[0091] A "command management system" is a technical means for generating tasks to be executed based on analysis results and determining their priority according to their importance.

[0092] A "display generation means" is a technical means that outputs analysis results in a visually easy-to-understand format and presents them in a way that is easy for the user to understand.

[0093] A "human interaction interface means" is a communication means in which a user receives information from a system and sends commands as needed.

[0094] An "online service" is a platform that serves as a source of data and information provided via the internet.

[0095] "Machine learning methods" refer to technologies that include algorithms and techniques for performing pattern recognition and prediction based on data.

[0096] "Real-time information" refers to the latest data that is constantly updated and is immediately reflected in the decision-making of autonomous vehicles.

[0097] In this invention, the following configuration is conceivable for realizing an information collection and analysis system for autonomous vehicles. First, the server autonomously collects real-time information such as traffic conditions, road conditions, and weather information using data collection means, utilizing sensors and online services on the internet. Next, the information analysis means analyzes the collected data to identify traffic patterns and potential risks. Machine learning algorithms such as TensorFlow can be used in this process.

[0098] The analysis results are generated as commands on the server and prioritized by the command management system. This information is visualized through the display generation system and delivered to the terminal in real time via the user interface. Users can check the latest information necessary for vehicle operation through the dashboard on their terminal and take action or make decisions as needed.

[0099] As a concrete example, an autonomous vehicle in Tokyo can receive traffic congestion information for its planned route five minutes later and plan the optimal detour based on that information. Examples of prompt messages in this system include:

[0100] "Show me the optimal route from my current location to my destination, taking into account traffic accident information and weather conditions."

[0101] "Analyze the weather changes over the next 15 minutes and how they will affect driving conditions."

[0102] In this way, autonomous vehicles can achieve safer and more efficient operation.

[0103] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0104] Step 1:

[0105] The server collects traffic conditions, road conditions, and weather information from sensors and web APIs. The input consists of data from online services and various sensors, resulting in a clean and consistent dataset. Here, the Scrapy framework is used to retrieve the data and record it in a database.

[0106] Step 2:

[0107] The server analyzes the collected data using TensorFlow. The input is the dataset obtained in step 1, and the output is insights into traffic patterns and potential risks. The analysis process involves comparison with historical data and predictions using machine learning models.

[0108] Step 3:

[0109] The server autonomously generates commands from the analysis results and prioritizes them based on their importance. The input is the insight from step 2, and the output is a list of commands to be executed. A Python script is used to implement the conditional branching and priority algorithms.

[0110] Step 4:

[0111] The server visualizes the information to be displayed based on the instructions and delivers it to the terminal in a dashboard format. The input is the instructions generated in step 3, and the output is graphs and charts for the user. A web application is built using the Flask framework, and the dashboard is displayed using HTML and JavaScript (registered trademark).

[0112] Step 5:

[0113] The user reviews the provided information on the device's dashboard and adjusts the route and settings as needed. The input is the visualization displayed in step 4, and the output is the result of executing commands based on user settings. The user can customize the information and notifications they need by manipulating the dashboard options.

[0114] 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.

[0115] This invention provides a system that enables more adaptive information provision and task management by autonomously collecting data related to a specific field and analyzing it in combination with a function that recognizes user emotions. This system includes information collection means, data analysis means, emotion engine, task management means, output generation means, and user interface means.

[0116] The server utilizes information gathering tools to collect relevant data from news sites, social networking services, and other online platforms on the internet. This data collection is performed regularly, with the aim of providing near real-time information.

[0117] The collected data is sent to data analysis tools and analyzed in detail by machine learning algorithms. This identifies industry trends and the activities of specific companies, and provides insights based on them. This analysis is also supported by an emotion engine, which analyzes user emotions based on user-provided feedback and voice input.

[0118] The emotion engine, for example, recognizes whether a user has positive or negative feelings towards data and provides that information to the task management system. As a result, task priorities are dynamically adjusted based on the user's emotional state.

[0119] The output generation mechanism generates an integrated output combining these analysis results and emotion recognition results. The server creates visualized reports and customized information, providing the data in a format that is easily understandable to the user.

[0120] Users accessing the device receive this information through the user interface. The dashboard displays information optimized based on the user's needs, allowing users to view information and make decisions that align with their own emotions.

[0121] For example, if a user places importance on product launch information and is experiencing stress, the system recognizes this emotion and provides relevant information with greater accuracy and speed than usual to support decision-making. In this way, the system of the present invention achieves flexible and efficient information processing and reporting that takes user emotions into account.

[0122] The following describes the processing flow.

[0123] Step 1:

[0124] The server utilizes information gathering tools, including web crawlers and APIs, to collect data from news sites and social media on the internet. This includes filtering the data using keywords related to specific fields. Collection is performed regularly, ensuring that new information is constantly being added.

[0125] Step 2:

[0126] The server temporarily stores the collected data in a database and extracts relevant information using natural language processing techniques. Data cleansing is also performed here, removing duplicate and noisy data.

[0127] Step 3:

[0128] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This analysis helps to understand industry trends and company movements, and new insights can be gained by comparing them with historical data. The analysis results are stored in a database.

[0129] Step 4:

[0130] When a user accesses the system, the emotion engine is activated and analyzes the user's emotions based on their input (e.g., voice or text). The server receives this analysis and identifies the user's current emotional state. Emotional information, such as positive or negative, influences task management.

[0131] Step 5:

[0132] The server generates tasks through an AI agent based on information obtained from the emotion engine and determines task priorities. It is designed to prioritize the delivery of particularly important information when the user is experiencing stress.

[0133] Step 6:

[0134] The server uses output generation mechanisms to create visualized reports and customized information. This generates output that is easy for users to understand. The generated output is provided as graphs, charts, or custom messages.

[0135] Step 7:

[0136] From a user interface running on the device, users receive generated output in a dashboard format. Users can customize the dashboard and prioritize viewing information according to their specific needs and emotions. This allows users to make decisions efficiently.

[0137] (Example 2)

[0138] 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".

[0139] Conventional information delivery systems did not adequately consider the emotional state of users when providing information or managing tasks. As a result, users found it difficult to obtain information that was always appropriate to their emotions and circumstances quickly and accurately, which forced them into inefficient decision-making.

[0140] 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.

[0141] In this invention, the server includes means for autonomously collecting data related to a specific field, means for analyzing the collected data and identifying industry trends, and means for analyzing emotions based on feedback input from users. This enables highly adaptive information provision and efficient task management that takes into account the emotional state of the user.

[0142] "Information gathering means" refers to a means for autonomously collecting data related to a specific field, and has the function of acquiring necessary data from electronic information providers.

[0143] "Data analysis methods" refer to methods of analyzing data using knowledge-based models in order to identify industry trends based on collected data.

[0144] An "emotion analysis tool" is a means of analyzing emotions based on feedback entered by the user and understanding the user's emotional state.

[0145] A "task management system" is a means of generating tasks based on analyzed data and determining their priority.

[0146] An "output generation means" is a means of visualizing and generating output results based on a prioritized task.

[0147] A "user interface means" is a means for delivering the generated output results to a terminal, and has the function of presenting the information in a format that is easy for the user to receive.

[0148] This system can autonomously collect data from various digital sources and provide information that takes user sentiment into consideration. Specifically, the server periodically retrieves data from multiple online platforms on the internet using various data collection methods. This data collection process aims to analyze information in near real-time, utilizing web scraping tools and APIs. For example, the latest articles can be retrieved from news sites using the Python BeautifulSoup library.

[0149] The server analyzes the collected data in more detail using data analysis tools. Machine learning algorithms such as knowledge-based models like TensorFlow and Scikit-learn are used. These analysis tools allow for the identification of industry trends and the activities of specific companies, thereby gaining meaningful insights.

[0150] Furthermore, the server uses sentiment analysis tools to analyze emotions based on user feedback and voice input. This analysis employs natural language processing technology, such as the Google® Cloud Natural Language API, to identify the sentiment of the input text.

[0151] Users receive information provided by the server via their terminal. For display, visualized reports and customized information generated by the output generation system are presented through the user interface. This allows users to view information in a way that suits their emotional state and needs, supporting efficient decision-making.

[0152] For example, if a user is interested in reviews of a new gadget, the server collects the latest relevant review information and provides the analysis results to the device. At this time, considering the user's past emotional tendencies, the server prioritizes displaying information that better matches the user's preferences. An example of a prompt to the generative AI model would be to instruct the server to "collect information about the launch of a new smartphone and suggest countermeasures if the user's emotional reaction to that information is negative." This allows the server to provide information that more accurately meets the user's needs.

[0153] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0154] Step 1:

[0155] The server periodically retrieves data from news sites, social media, and other online sources using various information gathering methods. It uses URLs and API keys of online platforms as input. Specifically, it employs the Python BeautifulSoup library to extract necessary text data using scraping techniques and convert it into a structured format. As a result, the latest information is accumulated on the server in real time.

[0156] Step 2:

[0157] The server sends the collected data to a data analysis system to analyze industry trends. A knowledge-based model is used for data analysis, taking the previously acquired text data as input. Specifically, a neural network model using TensorFlow is used to classify the data and identify trends. The output is generated as statistical information and graphs showing industry trends based on the analysis results.

[0158] Step 3:

[0159] The server uses sentiment analysis techniques with user feedback as input. It collects feedback and voice data provided by the user through their device and analyzes their emotions using natural language processing technology. Specifically, it uses the Google Cloud Natural Language API to classify emotions from text and assign labels such as positive, negative, or neutral. As a result, the user's emotional state is output in a quantitative format.

[0160] Step 4:

[0161] The server determines task priorities using a task management system based on sentiment analysis results. It uses analyzed sentiment data and industry trend data as input. Specifically, it adjusts task content and deadlines, and then determines priorities. The output is a task list with clearly defined priorities.

[0162] Step 5:

[0163] The server generates customized information for the user using output generation methods. Inputs include analyzed data and sentiment data. Specifically, it uses D3.js to create visualized reports and graphs. The output is a report converted into an easy-to-understand format.

[0164] Step 6:

[0165] The terminal presents visualized reports output from the server to the user through a user interface. It receives customized report data as input. Specifically, it displays necessary information on the dashboard, allowing the user to intuitively understand the information. As a result, users can view information and make decisions based on their own emotions.

[0166] (Application Example 2)

[0167] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0168] Providing personalized information that takes user emotions into account has been difficult with conventional systems. In particular, dynamically adjusting the priority of information based on user emotions and providing more appropriate content required an advanced system that was linked to emotion recognition technology.

[0169] 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.

[0170] In this invention, the server includes information gathering means for autonomously collecting information related to a specific target area, information analysis means for analyzing the collected information and identifying trends, and emotion recognition means for recognizing the user's emotions and dynamically adjusting accordingly. This enables the provision of personalized information in accordance with the user's emotions.

[0171] "Information gathering means" refers to devices or software that have the function of collecting information related to a specific subject area.

[0172] "Information analysis means" refers to processes or algorithms that have the function of analyzing collected information and identifying trends within related categories.

[0173] "Behavioral management means" refers to a system or control device that executes a process of generating actions based on analyzed information and determining their priority.

[0174] An "emotion recognition tool" is a module or software that has the function of identifying and analyzing the user's emotional state and dynamically adjusting the system's operation.

[0175] "Result generation means" refers to a system or interface for generating and presenting process-based results in a visual or other manner.

[0176] "User interface means" refers to a terminal or application that displays the results of the system to the user and allows them to operate it.

[0177] In this embodiment of the invention, the server first automatically collects information related to a specific area using information collection means. The information is mainly obtained from a communication network, and real-time information updates are possible. This allows analysis to always be performed based on the latest information.

[0178] Next, the server utilizes information analysis tools to analyze the collected information and identify trends. This analysis can use machine learning models such as Google's TensorFlow to precisely identify and analyze information trends.

[0179] Furthermore, the system includes emotion recognition capabilities, using Microsoft's Azure® Emotion API to identify the user's emotions. The user's emotion data is analyzed based on data acquired through the device's camera and microphone. This functionality enables flexible information delivery tailored to the user's emotions.

[0180] The result generation mechanism, which integrates analysis results and emotion recognition results, uses React Native to provide a user interface for visually presenting information to the user. Through this interface, the user can receive information adapted to their own emotional state.

[0181] For example, if the system detects that a user is experiencing excessive stress, it will prioritize recommending relaxation music or soothing videos. This allows users to enjoy an emotionally sensitive experience.

[0182] An example of input to the generative AI model would be a prompt sentence like, "Recommend the best music or video content for a user who is feeling stressed."

[0183] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0184] Step 1:

[0185] The server uses information gathering tools to collect information related to a specific area from communication networks. Inputs include specific keywords and categories, and data is retrieved from news sites and social media. The output is a collection of the retrieved raw data. The server performs this process periodically to keep the information up-to-date.

[0186] Step 2:

[0187] The server analyzes the collected raw data using information analysis tools. The input is the raw data collected in step 1, and data patterns and trends are extracted through a machine learning model (e.g., TensorFlow). The output is an analysis result showing specific patterns or trends. The specific operation here is the process of preprocessing the data, inputting it into the analysis model, and obtaining the results.

[0188] Step 3:

[0189] The server activates emotion recognition based on the analyzed data to identify the user's emotional state. It uses video and audio data acquired from the user's device as input. Using the Emotion API, it performs emotion analysis and outputs emotion labels such as positive or negative. The actual operation includes real-time evaluation of the captured user's facial expressions and voice.

[0190] Step 4:

[0191] The server integrates the results of emotion recognition and analysis, and uses a result generation mechanism to select appropriate content. The input consists of the emotional state and analysis results, and the server performs calculations to determine content priority based on these. The output is a list of content tailored to the user's emotions. Data processing is performed dynamically by a priority engine and is constantly optimized.

[0192] Step 5:

[0193] The terminal presents the content obtained from the result generation means to the user through the user interface means. The input is the content list created in step 4, and the output is the interface behavior displayed to the user. The user can intuitively manipulate and select information through this interface. Specific examples of this behavior include visualization and navigation functionality provided by React Native.

[0194] 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.

[0195] Data generation model 58 is a type of 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.

[0196] 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.

[0197] [Second Embodiment]

[0198] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0199] 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.

[0200] 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).

[0201] 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.

[0202] 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.

[0203] 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).

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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".

[0210] The present invention is a system whose primary purpose is to autonomously collect and analyze information in a specific field and to rapidly report the results. This system includes information collection means, data analysis means, task management means, output generation means, and user interface means.

[0211] The server automatically collects relevant data from various sources on the internet using web crawlers and APIs as information gathering tools. This includes news sites, social networking platforms, and official company websites. Information gathering is designed to be autonomous and performed regularly.

[0212] The collected data is processed by data analysis tools. The server uses multiple machine learning algorithms to analyze the collected data, deriving insights such as industry trends and the actions of specific companies. In this process, it is possible to identify new trends by comparing them with past data.

[0213] Based on the analysis results, the AI ​​agent generates new tasks using task management tools. Task priorities are determined according to the importance and urgency of the discovered information. For example, information regarding rapid market changes is recognized as a high-priority task.

[0214] In the output generation method, the server generates analysis results as reports and visualized data. This generated output is then presented as graphs and charts, making it visible to the user. This allows the user to quickly understand the information and use it to aid in decision-making.

[0215] Through a user interface, users operating on a terminal can receive these outputs in a dashboard format. Users can customize the dashboard to prioritize the display of information relevant to specific industries or topics. This allows users to quickly obtain the information they need and perform their tasks efficiently.

[0216] In this way, the system of the present invention achieves consistent automation from information collection to analysis and reporting, supporting companies' marketing activities and rapid decision-making.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The server launches an information gathering script, using a web crawler and APIs to collect data related to a specific area from news sites and social media on the internet. The collection is performed regularly on an automated schedule, filtering the data based on specified keywords.

[0220] Step 2:

[0221] The server stores the collected data in a temporary database and uses natural language processing techniques to extract relevant information. It then removes noisy and duplicate data to create a clean dataset.

[0222] Step 3:

[0223] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This reveals industry trends and the actions of specific companies, and new insights can be derived by comparing them with past trends.

[0224] Step 4:

[0225] Based on the analysis results, the server generates tasks through an AI agent and determines the priority of those tasks. Information regarding rapid market changes and important events is given the utmost attention when prioritizing.

[0226] Step 5:

[0227] The server uses output generation mechanisms to generate reports and visualized data based on the analysis results. This output is generated in the form of graphs, charts, and sometimes video clips, formatting the information in an easy-to-understand manner.

[0228] Step 6:

[0229] This final output is delivered to the user interface, where users can view it on a dashboard via their devices. Users can customize the dashboard to their individual needs, quickly access the information they require, and make efficient business decisions.

[0230] (Example 1)

[0231] 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".

[0232] In modern society, a vast amount of information exists on digital networks, but efficiently collecting, analyzing, and obtaining useful information from this data is difficult. Furthermore, appropriately prioritizing information and presenting it visually to users is also a challenge. In particular, in business, there is a need to acquire and analyze relevant information in a timely manner to support rapid decision-making.

[0233] 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.

[0234] In this invention, the server includes data collection means, information processing means, and business management means. This makes it possible to automatically collect large amounts of information, analyze that information to generate tasks, and set priorities as needed. Through this series of processes, users can quickly obtain useful information and perform their tasks efficiently.

[0235] "Data collection means" refers to a device or process for efficiently acquiring necessary information from a digital network.

[0236] "Information processing means" refers to a device or method for analyzing acquired information using an automated calculation model to derive useful insights and trends.

[0237] A "business management tool" is a device or process for generating necessary tasks based on analysis results and appropriately setting their priorities.

[0238] "Result generation means" refers to a device or method for visually representing the results of analyzed information and presenting them in a way that is easy for the user to understand.

[0239] "User connection means" refers to a device or process for providing the generated results to the user via a communication device.

[0240] This invention relates to a system that efficiently collects and analyzes vast amounts of information on a digital network and provides useful information to users. This system includes data collection means, information processing means, and business management means.

[0241] The server collects information from the internet using web crawlers and APIs as data collection tools. Specific software used in this process includes Python's Beautiful Soup and Scrapy. The server retrieves data from news sites and social media platforms based on configured keywords. For example, to collect articles related to a specific industry, it periodically crawls web pages and retrieves their content as text data.

[0242] Next, the server uses information processing tools to analyze the collected data. This analysis utilizes machine learning algorithms to identify data trends and patterns. Specifically, it leverages tools such as Scikit-learn and TensorFlow. The server can compare historical and current data to identify new business trends. For example, it can use sales data to predict new market trends.

[0243] The task management system allows the server to generate new tasks based on analysis results and determine their priority. Tasks can be allocated according to urgency and importance. For example, if the entry of a new competitor is discovered, tasks for further investigation into that competitor may be prioritized and scheduled.

[0244] The output is visually represented through result generation methods and accessible to users on their devices. For example, data can be presented as graphs and charts using visualization tools such as Tableau. This allows users to quickly grasp information and support their decision-making in their work.

[0245] Users can access information through their devices in a dashboard format, obtaining the latest information on specific fields and topics. For example, by entering a prompt such as, "Show me important news related to the latest technology in a dashboard format," predefined information will be organized and displayed. In this way, the system effectively collects and analyzes information, providing users with the information they need in a timely manner.

[0246] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0247] Step 1:

[0248] The server accesses the digital network and collects data using web crawlers and APIs. Specific keywords or topics are provided as input. For example, to obtain information about art exhibitions or cultural events, the URL of a configured website and the data format to be retrieved are specified. The server uses Beautiful Soup to parse the HTML document and extract text information from the specified elements. The output is the collected raw data.

[0249] Step 2:

[0250] The server utilizes Scikit-learn to begin analyzing the collected data. The input is the raw data collected in the previous step. Specifically, it filters out the necessary information from the data and performs data cleansing. During this process, data preprocessing such as normalization and handling of missing values ​​is performed. The output is an analyzable dataset.

[0251] Step 3:

[0252] The server uses the cleansed data to perform trend analysis using machine learning algorithms. The input for this step is the dataset generated in the previous step. Specifically, it performs regression analysis and clustering to predict new trends and patterns by comparing them with historical data. The output is the results of the trend analysis and the recognized patterns.

[0253] Step 4:

[0254] The server generates new tasks and sets their priorities based on the analysis results. The input utilizes the results of trend analysis. Specifically, it runs a scoring model to identify high-priority tasks. For example, tasks such as detailed investigation and action planning are automatically generated for topics that are rapidly gaining attention. The output is a prioritized list of tasks.

[0255] Step 5:

[0256] The server uses visualization tools such as Tableau to generate a visual report of the analysis results. The input for this process is the task list and analysis results generated in step 4. Specifically, it converts the data into graphs and charts and creates a report in a format that is easy for the user to understand intuitively. The output is a visualized report.

[0257] Step 6:

[0258] The user receives generated reports and task lists through their device. The input for this step is reports generated by a visualization tool. The information is displayed in a dashboard format on the device, and the interface is customized to allow the user to focus on specific data. The output is visualized information to support user decision-making. The user can obtain this information by entering a prompt such as, "Please display important news related to the latest technology in a dashboard format."

[0259] (Application Example 1)

[0260] 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."

[0261] Autonomous vehicles are required to accurately grasp traffic and weather conditions in real time to support safe and efficient driving. However, current systems face the challenge of not being able to effectively collect and analyze this information and feed it back into autonomous driving.

[0262] 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.

[0263] In this invention, the server includes data collection means for autonomously collecting information related to a specific area, information analysis means for analyzing the collected information and identifying industry trends, and means for collecting and analyzing real-time information including traffic conditions, road conditions, and weather information. This enables autonomous vehicles to operate safely and efficiently in real time.

[0264] "Information related to a specific domain" refers to data that affects the operation of autonomous vehicles, such as traffic conditions, road conditions, and weather information.

[0265] "Data collection means" refers to technological means for autonomously acquiring necessary information via online services on the internet or sensors.

[0266] "Information analysis methods" refer to technical means that use machine learning techniques to derive patterns and trends based on collected data, and utilize them to optimize operations.

[0267] A "command management system" is a technical means for generating tasks to be executed based on analysis results and determining their priority according to their importance.

[0268] A "display generation means" is a technical means that outputs analysis results in a visually easy-to-understand format and presents them in a way that is easy for the user to understand.

[0269] A "human interaction interface means" is a communication means in which a user receives information from a system and sends commands as needed.

[0270] An "online service" is a platform that serves as a source of data and information provided via the internet.

[0271] "Machine learning methods" refer to technologies that include algorithms and techniques for performing pattern recognition and prediction based on data.

[0272] "Real-time information" refers to the latest data that is constantly updated and is immediately reflected in the decision-making of autonomous vehicles.

[0273] In this invention, the following configuration is conceivable for realizing an information collection and analysis system for autonomous vehicles. First, the server autonomously collects real-time information such as traffic conditions, road conditions, and weather information using data collection means, utilizing sensors and online services on the internet. Next, the information analysis means analyzes the collected data to identify traffic patterns and potential risks. Machine learning algorithms such as TensorFlow can be used in this process.

[0274] The analysis results are generated as commands on the server and prioritized by the command management system. This information is visualized through the display generation system and delivered to the terminal in real time via the user interface. Users can check the latest information necessary for vehicle operation through the dashboard on their terminal and take action or make decisions as needed.

[0275] As a concrete example, an autonomous vehicle in Tokyo can receive traffic congestion information for its planned route five minutes later and plan the optimal detour based on that information. Examples of prompts in this system include:

[0276] "Show me the optimal route from my current location to my destination, taking into account traffic accident information and weather conditions."

[0277] "Analyze the weather changes over the next 15 minutes and how they will affect driving conditions."

[0278] In this way, autonomous vehicles can achieve safer and more efficient operation.

[0279] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0280] Step 1:

[0281] The server collects traffic conditions, road conditions, and weather information from sensors and Web APIs. The inputs are data from online services and various sensors, and the output is a clean and consistent dataset. Here, the Scrapy framework is used to obtain data and record it in the database.

[0282] Step 2:

[0283] The server analyzes the collected data using TensorFlow. The input is the dataset obtained in Step 1, and the output is insights regarding traffic patterns and potential risks. In the analysis process, comparisons with past data and predictions using machine learning models are performed.

[0284] Step 3:

[0285] The server autonomously generates commands from the analysis results and sets priorities based on the importance of the commands. The input is the insights from Step 2, and the output is a list of commands to be executed. A Python script is used to implement conditional branching and priority algorithms.

[0286] Step 4:

[0287] The server visualizes the information to be displayed based on the commands and distributes it to the terminal in the form of a dashboard. The input is the commands generated in Step 3, and the output is graphs and charts for the user. A Flask framework is used to build a web application and display the dashboard with HTML and JavaScript.

[0288] Step 5:

[0289] The user checks the provided information on the dashboard of the terminal and adjusts the running route and settings as needed. The input is the visualization information displayed in Step 4, and the output is the execution result of the command based on the user settings. The user operates the options of the dashboard to customize the necessary information and notifications.

[0290] 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.

[0291] This invention provides a system that enables more adaptive information provision and task management by autonomously collecting data related to a specific field and analyzing it in combination with a function that recognizes user emotions. This system includes information collection means, data analysis means, emotion engine, task management means, output generation means, and user interface means.

[0292] The server utilizes information gathering tools to collect relevant data from news sites, social networking services, and other online platforms on the internet. This data collection is performed regularly, with the aim of providing near real-time information.

[0293] The collected data is sent to data analysis tools and analyzed in detail by machine learning algorithms. This identifies industry trends and the activities of specific companies, and provides insights based on them. This analysis is also supported by an emotion engine, which analyzes user emotions based on user-provided feedback and voice input.

[0294] The emotion engine, for example, recognizes whether a user has positive or negative feelings towards data and provides that information to the task management system. As a result, task priorities are dynamically adjusted based on the user's emotional state.

[0295] The output generation mechanism generates an integrated output combining these analysis results and emotion recognition results. The server creates visualized reports and customized information, providing the data in a format that is easily understandable to the user.

[0296] Users accessing the device receive this information through the user interface. The dashboard displays information optimized based on the user's needs, allowing users to view information and make decisions that align with their own emotions.

[0297] For example, if a user places importance on product launch information and is experiencing stress, the system recognizes this emotion and provides relevant information with greater accuracy and speed than usual to support decision-making. In this way, the system of the present invention achieves flexible and efficient information processing and reporting that takes user emotions into account.

[0298] The following describes the processing flow.

[0299] Step 1:

[0300] The server utilizes information gathering tools, including web crawlers and APIs, to collect data from news sites and social media on the internet. This includes filtering the data using keywords related to specific fields. Collection is performed regularly, ensuring that new information is constantly being added.

[0301] Step 2:

[0302] The server temporarily stores the collected data in a database and extracts relevant information using natural language processing techniques. Data cleansing is also performed here, removing duplicate and noisy data.

[0303] Step 3:

[0304] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This analysis helps to understand industry trends and company movements, and new insights can be gained by comparing them with historical data. The analysis results are stored in a database.

[0305] Step 4:

[0306] When the user accesses the system, the emotion engine is activated, and emotions are analyzed based on the user's input (such as voice or text). The server receives this analysis result and identifies the user's current emotional state. Emotional information such as positive or negative affects task management.

[0307] Step 5:

[0308] Based on the information obtained from the emotion engine, the server generates tasks through the AI agent and determines the priority of the tasks. When the user is feeling stressed, it is designed to provide particularly important information preferentially.

[0309] Step 6:

[0310] The server uses output generation means to create a visualized report or customized information. As a result, an output that allows the user to easily understand the information is generated. The product is provided as a graph, chart, or custom message.

[0311] Step 7:

[0312] From the user interface operating on the terminal, the user receives the generated output in dashboard form. The user can customize the dashboard and preferentially view information according to specific needs or emotions. As a result, the user can make decisions efficiently.

[0313] (Example 2)

[0314] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] Conventional information delivery systems did not adequately consider the emotional state of users when providing information or managing tasks. As a result, users found it difficult to obtain information that was always appropriate to their emotions and circumstances quickly and accurately, which forced them into inefficient decision-making.

[0316] 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.

[0317] In this invention, the server includes means for autonomously collecting data related to a specific field, means for analyzing the collected data and identifying industry trends, and means for analyzing emotions based on feedback input from users. This enables highly adaptive information provision and efficient task management that takes into account the emotional state of the user.

[0318] "Information gathering means" refers to a means for autonomously collecting data related to a specific field, and has the function of acquiring necessary data from electronic information providers.

[0319] "Data analysis methods" refer to methods of analyzing data using knowledge-based models in order to identify industry trends based on collected data.

[0320] An "emotion analysis tool" is a means of analyzing emotions based on feedback entered by the user and understanding the user's emotional state.

[0321] A "task management system" is a means of generating tasks based on analyzed data and determining their priority.

[0322] An "output generation means" is a means of visualizing and generating output results based on a prioritized task.

[0323] A "user interface means" is a means for delivering the generated output results to a terminal, and has the function of presenting the information in a format that is easy for the user to receive.

[0324] This system can autonomously collect data from various digital sources and provide information that takes user sentiment into consideration. Specifically, the server periodically retrieves data from multiple online platforms on the internet using various data collection methods. This data collection process aims to analyze information in near real-time, utilizing web scraping tools and APIs. For example, the latest articles can be retrieved from news sites using the Python BeautifulSoup library.

[0325] The server analyzes the collected data in more detail using data analysis tools. Machine learning algorithms such as knowledge-based models like TensorFlow and Scikit-learn are used. These analysis tools allow for the identification of industry trends and the activities of specific companies, thereby gaining meaningful insights.

[0326] Furthermore, the server uses sentiment analysis tools to analyze user emotions based on their feedback and voice input. This analysis employs natural language processing techniques, such as using the Google Cloud Natural Language API to identify the sentiment of the input text.

[0327] Users receive information provided by the server via their terminal. For display, visualized reports and customized information generated by the output generation system are presented through the user interface. This allows users to view information in a way that suits their emotional state and needs, supporting efficient decision-making.

[0328] For example, if a user is interested in reviews of a new gadget, the server collects the latest relevant review information and provides the analysis results to the device. At this time, considering the user's past emotional tendencies, the server prioritizes displaying information that better matches the user's preferences. An example of a prompt to the generative AI model would be to instruct the server to "collect information about the launch of a new smartphone and suggest countermeasures if the user's emotional reaction to that information is negative." This allows the server to provide information that more accurately meets the user's needs.

[0329] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0330] Step 1:

[0331] The server periodically retrieves data from news sites, social media, and other online sources using various information gathering methods. It uses URLs and API keys of online platforms as input. Specifically, it employs the Python BeautifulSoup library to extract necessary text data using scraping techniques and convert it into a structured format. As a result, the latest information is accumulated on the server in real time.

[0332] Step 2:

[0333] The server sends the collected data to a data analysis system to analyze industry trends. A knowledge-based model is used for data analysis, taking the previously acquired text data as input. Specifically, a neural network model using TensorFlow is used to classify the data and identify trends. The output is generated as statistical information and graphs showing industry trends based on the analysis results.

[0334] Step 3:

[0335] The server uses sentiment analysis techniques with user feedback as input. It collects feedback and voice data provided by the user through their device and analyzes their emotions using natural language processing technology. Specifically, it uses the Google Cloud Natural Language API to classify emotions from text and assign labels such as positive, negative, or neutral. As a result, the user's emotional state is output in a quantitative format.

[0336] Step 4:

[0337] The server determines task priorities using a task management system based on sentiment analysis results. It uses analyzed sentiment data and industry trend data as input. Specifically, it adjusts task content and deadlines, and then determines priorities. The output is a task list with clearly defined priorities.

[0338] Step 5:

[0339] The server generates customized information for the user using output generation methods. Inputs include analyzed data and sentiment data. Specifically, it uses D3.js to create visualized reports and graphs. The output is a report converted into an easy-to-understand format.

[0340] Step 6:

[0341] The terminal presents visualized reports output from the server to the user through a user interface. It receives customized report data as input. Specifically, it displays necessary information on the dashboard, allowing the user to intuitively understand the information. As a result, users can view information and make decisions based on their own emotions.

[0342] (Application Example 2)

[0343] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0344] Providing personalized information that takes user emotions into account has been difficult with conventional systems. In particular, dynamically adjusting the priority of information based on user emotions and providing more appropriate content required an advanced system that was linked to emotion recognition technology.

[0345] 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.

[0346] In this invention, the server includes information gathering means for autonomously collecting information related to a specific target area, information analysis means for analyzing the collected information and identifying trends, and emotion recognition means for recognizing the user's emotions and dynamically adjusting accordingly. This enables the provision of personalized information in accordance with the user's emotions.

[0347] "Information gathering means" refers to devices or software that have the function of collecting information related to a specific subject area.

[0348] "Information analysis means" refers to processes or algorithms that have the function of analyzing collected information and identifying trends within related categories.

[0349] "Behavioral management means" refers to a system or control device that executes a process of generating actions based on analyzed information and determining their priority.

[0350] An "emotion recognition tool" is a module or software that has the function of identifying and analyzing the user's emotional state and dynamically adjusting the system's operation.

[0351] "Result generation means" refers to a system or interface for generating and presenting process-based results in a visual or other manner.

[0352] "User interface means" refers to a terminal or application that displays the results of the system to the user and allows them to operate it.

[0353] In this embodiment of the invention, the server first automatically collects information related to a specific area using information collection means. The information is mainly obtained from a communication network, and real-time information updates are possible. This allows analysis to always be performed based on the latest information.

[0354] Next, the server utilizes information analysis tools to analyze the collected information and identify trends. This analysis can use machine learning models such as Google's TensorFlow to precisely identify and analyze information trends.

[0355] Furthermore, the system includes emotion recognition capabilities, using Microsoft Azure's Emotion API to identify the user's emotions. The user's emotion data is analyzed based on data acquired through the device's camera and microphone. This functionality enables flexible information delivery tailored to the user's emotions.

[0356] The result generation mechanism, which integrates analysis results and emotion recognition results, uses React Native to provide a user interface for visually presenting information to the user. Through this interface, the user can receive information adapted to their own emotional state.

[0357] For example, if the system detects that a user is experiencing excessive stress, it will prioritize recommending relaxation music or soothing videos. This allows users to enjoy an emotionally sensitive experience.

[0358] An example of input to the generative AI model would be a prompt sentence like, "Recommend the best music or video content for a user who is feeling stressed."

[0359] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0360] Step 1:

[0361] The server uses information gathering tools to collect information related to a specific area from communication networks. Inputs include specific keywords and categories, and data is retrieved from news sites and social media. The output is a collection of the retrieved raw data. The server performs this process periodically to keep the information up-to-date.

[0362] Step 2:

[0363] The server analyzes the collected raw data using information analysis tools. The input is the raw data collected in step 1, and data patterns and trends are extracted through a machine learning model (e.g., TensorFlow). The output is an analysis result showing specific patterns or trends. The specific operation here is the process of preprocessing the data, inputting it into the analysis model, and obtaining the results.

[0364] Step 3:

[0365] The server activates emotion recognition based on the analyzed data to identify the user's emotional state. It uses video and audio data acquired from the user's device as input. Using the Emotion API, it performs emotion analysis and outputs emotion labels such as positive or negative. The actual operation includes real-time evaluation of the captured user's facial expressions and voice.

[0366] Step 4:

[0367] The server integrates the results of emotion recognition and analysis, and uses a result generation mechanism to select appropriate content. The input consists of the emotional state and analysis results, and the server performs calculations to determine content priority based on these. The output is a list of content tailored to the user's emotions. Data processing is performed dynamically by a priority engine and is constantly optimized.

[0368] Step 5:

[0369] The terminal presents the content obtained from the result generation means to the user through the user interface means. The input is the content list created in step 4, and the output is the interface behavior displayed to the user. The user can intuitively manipulate and select information through this interface. Specific examples of this behavior include visualization and navigation functionality provided by React Native.

[0370] 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.

[0371] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0372] 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.

[0373] [Third Embodiment]

[0374] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0375] 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.

[0376] 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).

[0377] 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.

[0378] 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.

[0379] 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).

[0380] 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.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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".

[0386] The present invention is a system whose primary purpose is to autonomously collect and analyze information in a specific field and to rapidly report the results. This system includes information collection means, data analysis means, task management means, output generation means, and user interface means.

[0387] The server automatically collects relevant data from various sources on the internet using web crawlers and APIs as information gathering tools. This includes news sites, social networking platforms, and official company websites. Information gathering is designed to be autonomous and performed regularly.

[0388] The collected data is processed by data analysis tools. The server uses multiple machine learning algorithms to analyze the collected data, deriving insights such as industry trends and the actions of specific companies. In this process, it is possible to identify new trends by comparing them with past data.

[0389] Based on the analysis results, the AI ​​agent generates new tasks using task management tools. Task priorities are determined according to the importance and urgency of the discovered information. For example, information regarding rapid market changes is recognized as a high-priority task.

[0390] In the output generation method, the server generates analysis results as reports and visualized data. This generated output is then presented as graphs and charts, making it visible to the user. This allows the user to quickly understand the information and use it to aid in decision-making.

[0391] Through a user interface, users operating on a terminal can receive these outputs in a dashboard format. Users can customize the dashboard to prioritize the display of information relevant to specific industries or topics. This allows users to quickly obtain the information they need and perform their tasks efficiently.

[0392] In this way, the system of the present invention achieves consistent automation from information collection to analysis and reporting, supporting companies' marketing activities and rapid decision-making.

[0393] The following describes the processing flow.

[0394] Step 1:

[0395] The server launches an information gathering script, using a web crawler and APIs to collect data related to a specific area from news sites and social media on the internet. The collection is performed regularly on an automated schedule, filtering the data based on specified keywords.

[0396] Step 2:

[0397] The server stores the collected data in a temporary database and uses natural language processing techniques to extract relevant information. It then removes noisy and duplicate data to create a clean dataset.

[0398] Step 3:

[0399] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This reveals industry trends and the actions of specific companies, and new insights can be derived by comparing them with past trends.

[0400] Step 4:

[0401] Based on the analysis results, the server generates tasks through an AI agent and determines the priority of those tasks. Information regarding rapid market changes and important events is given the utmost attention when prioritizing.

[0402] Step 5:

[0403] The server uses output generation mechanisms to generate reports and visualized data based on the analysis results. This output is generated in the form of graphs, charts, and sometimes video clips, formatting the information in an easy-to-understand manner.

[0404] Step 6:

[0405] This final output is delivered to the user interface, where users can view it on a dashboard via their devices. Users can customize the dashboard to their individual needs, quickly access the information they require, and make efficient business decisions.

[0406] (Example 1)

[0407] 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."

[0408] In modern society, a vast amount of information exists on digital networks, but efficiently collecting, analyzing, and obtaining useful information from this data is difficult. Furthermore, appropriately prioritizing information and presenting it visually to users is also a challenge. In particular, in business, there is a need to acquire and analyze relevant information in a timely manner to support rapid decision-making.

[0409] 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.

[0410] In this invention, the server includes data collection means, information processing means, and business management means. This makes it possible to automatically collect large amounts of information, analyze that information to generate tasks, and set priorities as needed. Through this series of processes, users can quickly obtain useful information and perform their tasks efficiently.

[0411] "Data collection means" refers to a device or process for efficiently acquiring necessary information from a digital network.

[0412] "Information processing means" refers to a device or method for analyzing acquired information using an automated calculation model to derive useful insights and trends.

[0413] A "business management tool" is a device or process for generating necessary tasks based on analysis results and appropriately setting their priorities.

[0414] "Result generation means" refers to a device or method for visually representing the results of analyzed information and presenting them in a way that is easy for the user to understand.

[0415] "User connection means" refers to a device or process for providing the generated results to the user via a communication device.

[0416] This invention relates to a system that efficiently collects and analyzes vast amounts of information on a digital network and provides useful information to users. This system includes data collection means, information processing means, and business management means.

[0417] The server collects information from the internet using web crawlers and APIs as data collection tools. Specific software used in this process includes Python's Beautiful Soup and Scrapy. The server retrieves data from news sites and social media platforms based on configured keywords. For example, to collect articles related to a specific industry, it periodically crawls web pages and retrieves their content as text data.

[0418] Next, the server uses information processing tools to analyze the collected data. This analysis utilizes machine learning algorithms to identify data trends and patterns. Specifically, it leverages tools such as Scikit-learn and TensorFlow. The server can compare historical and current data to identify new business trends. For example, it can use sales data to predict new market trends.

[0419] The task management system allows the server to generate new tasks based on analysis results and determine their priority. Tasks can be allocated according to urgency and importance. For example, if the entry of a new competitor is discovered, tasks for further investigation into that competitor may be prioritized and scheduled.

[0420] The output is visually represented through result generation methods and accessible to users on their devices. For example, data can be presented as graphs and charts using visualization tools such as Tableau. This allows users to quickly grasp information and support their decision-making in their work.

[0421] Users can access information through their devices in a dashboard format, obtaining the latest information on specific fields and topics. For example, by entering a prompt such as, "Show me important news related to the latest technology in a dashboard format," predefined information will be organized and displayed. In this way, the system effectively collects and analyzes information, providing users with the information they need in a timely manner.

[0422] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0423] Step 1:

[0424] The server accesses the digital network and collects data using web crawlers and APIs. Specific keywords or topics are provided as input. For example, to obtain information about art exhibitions or cultural events, the URL of a configured website and the data format to be retrieved are specified. The server uses Beautiful Soup to parse the HTML document and extract text information from the specified elements. The output is the collected raw data.

[0425] Step 2:

[0426] The server utilizes Scikit-learn to begin analyzing the collected data. The input is the raw data collected in the previous step. Specifically, it filters out the necessary information from the data and performs data cleansing. During this process, data preprocessing such as normalization and handling of missing values ​​is performed. The output is an analyzable dataset.

[0427] Step 3:

[0428] The server uses the cleansed data to perform trend analysis using machine learning algorithms. The input for this step is the dataset generated in the previous step. Specifically, it performs regression analysis and clustering to predict new trends and patterns by comparing them with historical data. The output is the results of the trend analysis and the recognized patterns.

[0429] Step 4:

[0430] The server generates new tasks and sets their priorities based on the analysis results. The input utilizes the results of trend analysis. Specifically, it runs a scoring model to identify high-priority tasks. For example, tasks such as detailed investigation and action planning are automatically generated for topics that are rapidly gaining attention. The output is a prioritized list of tasks.

[0431] Step 5:

[0432] The server uses visualization tools such as Tableau to generate a visual report of the analysis results. The input for this process is the task list and analysis results generated in step 4. Specifically, it converts the data into graphs and charts and creates a report in a format that is easy for the user to understand intuitively. The output is a visualized report.

[0433] Step 6:

[0434] The user receives generated reports and task lists through their device. The input for this step is reports generated by a visualization tool. The information is displayed in a dashboard format on the device, and the interface is customized to allow the user to focus on specific data. The output is visualized information to support user decision-making. The user can obtain this information by entering a prompt such as, "Please display important news related to the latest technology in a dashboard format."

[0435] (Application Example 1)

[0436] 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."

[0437] Autonomous vehicles are required to accurately grasp traffic and weather conditions in real time to support safe and efficient driving. However, current systems face the challenge of not being able to effectively collect and analyze this information and feed it back into autonomous driving.

[0438] 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.

[0439] In this invention, the server includes data collection means for autonomously collecting information related to a specific area, information analysis means for analyzing the collected information and identifying industry trends, and means for collecting and analyzing real-time information including traffic conditions, road conditions, and weather information. This enables autonomous vehicles to operate safely and efficiently in real time.

[0440] "Information related to a specific domain" refers to data that affects the operation of autonomous vehicles, such as traffic conditions, road conditions, and weather information.

[0441] "Data collection means" refers to technological means for autonomously acquiring necessary information via online services on the internet or sensors.

[0442] "Information analysis methods" refer to technical means that use machine learning techniques to derive patterns and trends based on collected data, and utilize them to optimize operations.

[0443] A "command management system" is a technical means for generating tasks to be executed based on analysis results and determining their priority according to their importance.

[0444] A "display generation means" is a technical means that outputs analysis results in a visually easy-to-understand format and presents them in a way that is easy for the user to understand.

[0445] A "human interaction interface means" is a communication means in which a user receives information from a system and sends commands as needed.

[0446] An "online service" is a platform that serves as a source of data and information provided via the internet.

[0447] "Machine learning methods" refer to technologies that include algorithms and techniques for performing pattern recognition and prediction based on data.

[0448] "Real-time information" refers to the latest data that is constantly updated and is immediately reflected in the decision-making of autonomous vehicles.

[0449] In this invention, the following configuration is conceivable for realizing an information collection and analysis system for autonomous vehicles. First, the server autonomously collects real-time information such as traffic conditions, road conditions, and weather information using data collection means, utilizing sensors and online services on the internet. Next, the information analysis means analyzes the collected data to identify traffic patterns and potential risks. Machine learning algorithms such as TensorFlow can be used in this process.

[0450] The analysis results are generated as commands on the server and prioritized by the command management system. This information is visualized through the display generation system and delivered to the terminal in real time via the user interface. Users can check the latest information necessary for vehicle operation through the dashboard on their terminal and take action or make decisions as needed.

[0451] As a concrete example, an autonomous vehicle in Tokyo can receive traffic congestion information for its planned route five minutes later and plan the optimal detour based on that information. Examples of prompts in this system include:

[0452] "Show me the optimal route from my current location to my destination, taking into account traffic accident information and weather conditions."

[0453] "Analyze the weather changes over the next 15 minutes and how they will affect driving conditions."

[0454] In this way, autonomous vehicles can achieve safer and more efficient operation.

[0455] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0456] Step 1:

[0457] The server collects traffic conditions, road conditions, and weather information from sensors and web APIs. The input consists of data from online services and various sensors, resulting in a clean and consistent dataset. Here, the Scrapy framework is used to retrieve the data and record it in a database.

[0458] Step 2:

[0459] The server analyzes the collected data using TensorFlow. The input is the dataset obtained in step 1, and the output is insights into traffic patterns and potential risks. The analysis process involves comparison with historical data and predictions using machine learning models.

[0460] Step 3:

[0461] The server autonomously generates commands from the analysis results and prioritizes them based on their importance. The input is the insight from step 2, and the output is a list of commands to be executed. A Python script is used to implement the conditional branching and priority algorithms.

[0462] Step 4:

[0463] The server visualizes the information to be displayed based on the instructions and delivers it to the terminal in a dashboard format. The input is the instructions generated in step 3, and the output is graphs and charts for the user. A web application is built using the Flask framework, and the dashboard is displayed using HTML and JavaScript.

[0464] Step 5:

[0465] The user reviews the provided information on the device's dashboard and adjusts the route and settings as needed. The input is the visualization displayed in step 4, and the output is the result of executing commands based on user settings. The user can customize the information and notifications they need by manipulating the dashboard options.

[0466] 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.

[0467] This invention provides a system that enables more adaptive information provision and task management by autonomously collecting data related to a specific field and analyzing it in combination with a function that recognizes user emotions. This system includes information collection means, data analysis means, emotion engine, task management means, output generation means, and user interface means.

[0468] The server utilizes information gathering tools to collect relevant data from news sites, social networking services, and other online platforms on the internet. This data collection is performed regularly, with the aim of providing near real-time information.

[0469] The collected data is sent to data analysis tools and analyzed in detail by machine learning algorithms. This identifies industry trends and the activities of specific companies, and provides insights based on them. This analysis is also supported by an emotion engine, which analyzes user emotions based on user-provided feedback and voice input.

[0470] The emotion engine, for example, recognizes whether a user has positive or negative feelings towards data and provides that information to the task management system. As a result, task priorities are dynamically adjusted based on the user's emotional state.

[0471] The output generation mechanism generates an integrated output combining these analysis results and emotion recognition results. The server creates visualized reports and customized information, providing the data in a format that is easily understandable to the user.

[0472] Users accessing the device receive this information through the user interface. The dashboard displays information optimized based on the user's needs, allowing users to view information and make decisions that align with their own emotions.

[0473] For example, if a user places importance on product launch information and is experiencing stress, the system recognizes this emotion and provides relevant information with greater accuracy and speed than usual to support decision-making. In this way, the system of the present invention achieves flexible and efficient information processing and reporting that takes user emotions into account.

[0474] The following describes the processing flow.

[0475] Step 1:

[0476] The server utilizes information gathering tools, including web crawlers and APIs, to collect data from news sites and social media on the internet. This includes filtering the data using keywords related to specific fields. Collection is performed regularly, ensuring that new information is constantly being added.

[0477] Step 2:

[0478] The server temporarily stores the collected data in a database and extracts relevant information using natural language processing techniques. Data cleansing is also performed here, removing duplicate and noisy data.

[0479] Step 3:

[0480] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This analysis helps to understand industry trends and company movements, and new insights can be gained by comparing them with historical data. The analysis results are stored in a database.

[0481] Step 4:

[0482] When a user accesses the system, the emotion engine is activated and analyzes the user's emotions based on their input (e.g., voice or text). The server receives this analysis and identifies the user's current emotional state. Emotional information, such as positive or negative, influences task management.

[0483] Step 5:

[0484] The server generates tasks through an AI agent based on information obtained from the emotion engine and determines task priorities. It is designed to prioritize the delivery of particularly important information when the user is experiencing stress.

[0485] Step 6:

[0486] The server uses output generation mechanisms to create visualized reports and customized information. This generates output that is easy for users to understand. The generated output is provided as graphs, charts, or custom messages.

[0487] Step 7:

[0488] From a user interface running on the device, users receive generated output in a dashboard format. Users can customize the dashboard and prioritize viewing information according to their specific needs and emotions. This allows users to make decisions efficiently.

[0489] (Example 2)

[0490] 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."

[0491] Conventional information delivery systems did not adequately consider the emotional state of users when providing information or managing tasks. As a result, users found it difficult to obtain information that was always appropriate to their emotions and circumstances quickly and accurately, which forced them into inefficient decision-making.

[0492] 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.

[0493] In this invention, the server includes means for autonomously collecting data related to a specific field, means for analyzing the collected data and identifying industry trends, and means for analyzing emotions based on feedback input from users. This enables highly adaptive information provision and efficient task management that takes into account the emotional state of the user.

[0494] "Information gathering means" refers to a means for autonomously collecting data related to a specific field, and has the function of acquiring necessary data from electronic information providers.

[0495] "Data analysis methods" refer to methods of analyzing data using knowledge-based models in order to identify industry trends based on collected data.

[0496] An "emotion analysis tool" is a means of analyzing emotions based on feedback entered by the user and understanding the user's emotional state.

[0497] A "task management system" is a means of generating tasks based on analyzed data and determining their priority.

[0498] An "output generation means" is a means of visualizing and generating output results based on a prioritized task.

[0499] A "user interface means" is a means for delivering the generated output results to a terminal, and has the function of presenting the information in a format that is easy for the user to receive.

[0500] This system can autonomously collect data from various digital sources and provide information that takes user sentiment into consideration. Specifically, the server periodically retrieves data from multiple online platforms on the internet using various data collection methods. This data collection process aims to analyze information in near real-time, utilizing web scraping tools and APIs. For example, the latest articles can be retrieved from news sites using the Python BeautifulSoup library.

[0501] The server analyzes the collected data in more detail using data analysis tools. Machine learning algorithms such as knowledge-based models like TensorFlow and Scikit-learn are used. These analysis tools allow for the identification of industry trends and the activities of specific companies, thereby gaining meaningful insights.

[0502] Furthermore, the server uses sentiment analysis tools to analyze user emotions based on their feedback and voice input. This analysis employs natural language processing techniques, such as using the Google Cloud Natural Language API to identify the sentiment of the input text.

[0503] Users receive information provided by the server via their terminal. For display, visualized reports and customized information generated by the output generation system are presented through the user interface. This allows users to view information in a way that suits their emotional state and needs, supporting efficient decision-making.

[0504] For example, if a user is interested in reviews of a new gadget, the server collects the latest relevant review information and provides the analysis results to the device. At this time, considering the user's past emotional tendencies, the server prioritizes displaying information that better matches the user's preferences. An example of a prompt to the generative AI model would be to instruct the server to "collect information about the launch of a new smartphone and suggest countermeasures if the user's emotional reaction to that information is negative." This allows the server to provide information that more accurately meets the user's needs.

[0505] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0506] Step 1:

[0507] The server periodically retrieves data from news sites, social media, and other online sources using various information gathering methods. It uses URLs and API keys of online platforms as input. Specifically, it employs the Python BeautifulSoup library to extract necessary text data using scraping techniques and convert it into a structured format. As a result, the latest information is accumulated on the server in real time.

[0508] Step 2:

[0509] The server sends the collected data to a data analysis system to analyze industry trends. A knowledge-based model is used for data analysis, taking the previously acquired text data as input. Specifically, a neural network model using TensorFlow is used to classify the data and identify trends. The output is generated as statistical information and graphs showing industry trends based on the analysis results.

[0510] Step 3:

[0511] The server uses sentiment analysis techniques with user feedback as input. It collects feedback and voice data provided by the user through their device and analyzes their emotions using natural language processing technology. Specifically, it uses the Google Cloud Natural Language API to classify emotions from text and assign labels such as positive, negative, or neutral. As a result, the user's emotional state is output in a quantitative format.

[0512] Step 4:

[0513] The server determines task priorities using a task management system based on sentiment analysis results. It uses analyzed sentiment data and industry trend data as input. Specifically, it adjusts task content and deadlines, and then determines priorities. The output is a task list with clearly defined priorities.

[0514] Step 5:

[0515] The server generates customized information for the user using output generation methods. Inputs include analyzed data and sentiment data. Specifically, it uses D3.js to create visualized reports and graphs. The output is a report converted into an easy-to-understand format.

[0516] Step 6:

[0517] The terminal presents visualized reports output from the server to the user through a user interface. It receives customized report data as input. Specifically, it displays necessary information on the dashboard, allowing the user to intuitively understand the information. As a result, users can view information and make decisions based on their own emotions.

[0518] (Application Example 2)

[0519] 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."

[0520] Providing personalized information that takes user emotions into account has been difficult with conventional systems. In particular, dynamically adjusting the priority of information based on user emotions and providing more appropriate content required an advanced system that was linked to emotion recognition technology.

[0521] 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.

[0522] In this invention, the server includes information gathering means for autonomously collecting information related to a specific target area, information analysis means for analyzing the collected information and identifying trends, and emotion recognition means for recognizing the user's emotions and dynamically adjusting accordingly. This enables the provision of personalized information in accordance with the user's emotions.

[0523] "Information gathering means" refers to devices or software that have the function of collecting information related to a specific subject area.

[0524] "Information analysis means" refers to processes or algorithms that have the function of analyzing collected information and identifying trends within related categories.

[0525] "Behavioral management means" refers to a system or control device that executes a process of generating actions based on analyzed information and determining their priority.

[0526] An "emotion recognition tool" is a module or software that has the function of identifying and analyzing the user's emotional state and dynamically adjusting the system's operation.

[0527] "Result generation means" refers to a system or interface for generating and presenting process-based results in a visual or other manner.

[0528] "User interface means" refers to a terminal or application that displays the results of the system to the user and allows them to operate it.

[0529] In this embodiment of the invention, the server first automatically collects information related to a specific area using information collection means. The information is mainly obtained from a communication network, and real-time information updates are possible. This allows analysis to always be performed based on the latest information.

[0530] Next, the server utilizes information analysis tools to analyze the collected information and identify trends. This analysis can use machine learning models such as Google's TensorFlow to precisely identify and analyze information trends.

[0531] Furthermore, the system includes emotion recognition capabilities, using Microsoft Azure's Emotion API to identify the user's emotions. The user's emotion data is analyzed based on data acquired through the device's camera and microphone. This functionality enables flexible information delivery tailored to the user's emotions.

[0532] The result generation mechanism, which integrates analysis results and emotion recognition results, uses React Native to provide a user interface for visually presenting information to the user. Through this interface, the user can receive information adapted to their own emotional state.

[0533] For example, if the system detects that a user is experiencing excessive stress, it will prioritize recommending relaxation music or soothing videos. This allows users to enjoy an emotionally sensitive experience.

[0534] An example of input to the generative AI model would be a prompt sentence like, "Recommend the best music or video content for a user who is feeling stressed."

[0535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0536] Step 1:

[0537] The server uses information gathering tools to collect information related to a specific area from communication networks. Inputs include specific keywords and categories, and data is retrieved from news sites and social media. The output is a collection of the retrieved raw data. The server performs this process periodically to keep the information up-to-date.

[0538] Step 2:

[0539] The server analyzes the collected raw data using information analysis tools. The input is the raw data collected in step 1, and data patterns and trends are extracted through a machine learning model (e.g., TensorFlow). The output is an analysis result showing specific patterns or trends. The specific operation here is the process of preprocessing the data, inputting it into the analysis model, and obtaining the results.

[0540] Step 3:

[0541] The server activates emotion recognition based on the analyzed data to identify the user's emotional state. It uses video and audio data acquired from the user's device as input. Using the Emotion API, it performs emotion analysis and outputs emotion labels such as positive or negative. The actual operation includes real-time evaluation of the captured user's facial expressions and voice.

[0542] Step 4:

[0543] The server integrates the results of emotion recognition and analysis, and uses a result generation mechanism to select appropriate content. The input consists of the emotional state and analysis results, and the server performs calculations to determine content priority based on these. The output is a list of content tailored to the user's emotions. Data processing is performed dynamically by a priority engine and is constantly optimized.

[0544] Step 5:

[0545] The terminal presents the content obtained from the result generation means to the user through the user interface means. The input is the content list created in step 4, and the output is the interface behavior displayed to the user. The user can intuitively manipulate and select information through this interface. Specific examples of this behavior include visualization and navigation functionality provided by React Native.

[0546] 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.

[0547] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0548] 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.

[0549] [Fourth Embodiment]

[0550] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0551] 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.

[0552] 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).

[0553] 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.

[0554] 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.

[0555] 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).

[0556] 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.

[0557] 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.

[0558] 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.

[0559] 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.

[0560] 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.

[0561] 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.

[0562] 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".

[0563] The present invention is a system whose primary purpose is to autonomously collect and analyze information in a specific field and to rapidly report the results. This system includes information collection means, data analysis means, task management means, output generation means, and user interface means.

[0564] The server automatically collects relevant data from various sources on the internet using web crawlers and APIs as information gathering tools. This includes news sites, social networking platforms, and official company websites. Information gathering is designed to be autonomous and performed regularly.

[0565] The collected data is processed by data analysis tools. The server uses multiple machine learning algorithms to analyze the collected data, deriving insights such as industry trends and the actions of specific companies. In this process, it is possible to identify new trends by comparing them with past data.

[0566] Based on the analysis results, the AI ​​agent generates new tasks using task management tools. Task priorities are determined according to the importance and urgency of the discovered information. For example, information regarding rapid market changes is recognized as a high-priority task.

[0567] In the output generation method, the server generates analysis results as reports and visualized data. This generated output is then presented as graphs and charts, making it visible to the user. This allows the user to quickly understand the information and use it to aid in decision-making.

[0568] Through a user interface, users operating on a terminal can receive these outputs in a dashboard format. Users can customize the dashboard to prioritize the display of information relevant to specific industries or topics. This allows users to quickly obtain the information they need and perform their tasks efficiently.

[0569] In this way, the system of the present invention achieves consistent automation from information collection to analysis and reporting, supporting companies' marketing activities and rapid decision-making.

[0570] The following describes the processing flow.

[0571] Step 1:

[0572] The server launches an information gathering script, using a web crawler and APIs to collect data related to a specific area from news sites and social media on the internet. The collection is performed regularly on an automated schedule, filtering the data based on specified keywords.

[0573] Step 2:

[0574] The server stores the collected data in a temporary database and uses natural language processing techniques to extract relevant information. It then removes noisy and duplicate data to create a clean dataset.

[0575] Step 3:

[0576] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This reveals industry trends and the actions of specific companies, and new insights can be derived by comparing them with past trends.

[0577] Step 4:

[0578] Based on the analysis results, the server generates tasks through an AI agent and determines the priority of those tasks. Information regarding rapid market changes and important events is given the utmost attention when prioritizing.

[0579] Step 5:

[0580] The server uses output generation mechanisms to generate reports and visualized data based on the analysis results. This output is generated in the form of graphs, charts, and sometimes video clips, formatting the information in an easy-to-understand manner.

[0581] Step 6:

[0582] This final output is delivered to the user interface, where users can view it on a dashboard via their devices. Users can customize the dashboard to their individual needs, quickly access the information they require, and make efficient business decisions.

[0583] (Example 1)

[0584] 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".

[0585] In modern society, a vast amount of information exists on digital networks, but efficiently collecting, analyzing, and obtaining useful information from this data is difficult. Furthermore, appropriately prioritizing information and presenting it visually to users is also a challenge. In particular, in business, there is a need to acquire and analyze relevant information in a timely manner to support rapid decision-making.

[0586] 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.

[0587] In this invention, the server includes data collection means, information processing means, and business management means. This makes it possible to automatically collect large amounts of information, analyze that information to generate tasks, and set priorities as needed. Through this series of processes, users can quickly obtain useful information and perform their tasks efficiently.

[0588] "Data collection means" refers to a device or process for efficiently acquiring necessary information from a digital network.

[0589] "Information processing means" refers to a device or method for analyzing acquired information using an automated calculation model to derive useful insights and trends.

[0590] A "business management tool" is a device or process for generating necessary tasks based on analysis results and appropriately setting their priorities.

[0591] "Result generation means" refers to a device or method for visually representing the results of analyzed information and presenting them in a way that is easy for the user to understand.

[0592] "User connection means" refers to a device or process for providing the generated results to the user via a communication device.

[0593] This invention relates to a system that efficiently collects and analyzes vast amounts of information on a digital network and provides useful information to users. This system includes data collection means, information processing means, and business management means.

[0594] The server collects information from the internet using web crawlers and APIs as data collection tools. Specific software used in this process includes Python's Beautiful Soup and Scrapy. The server retrieves data from news sites and social media platforms based on configured keywords. For example, to collect articles related to a specific industry, it periodically crawls web pages and retrieves their content as text data.

[0595] Next, the server uses information processing tools to analyze the collected data. This analysis utilizes machine learning algorithms to identify data trends and patterns. Specifically, it leverages tools such as Scikit-learn and TensorFlow. The server can compare historical and current data to identify new business trends. For example, it can use sales data to predict new market trends.

[0596] The task management system allows the server to generate new tasks based on analysis results and determine their priority. Tasks can be allocated according to urgency and importance. For example, if the entry of a new competitor is discovered, tasks for further investigation into that competitor may be prioritized and scheduled.

[0597] The output is visually represented through result generation methods and accessible to users on their devices. For example, data can be presented as graphs and charts using visualization tools such as Tableau. This allows users to quickly grasp information and support their decision-making in their work.

[0598] Users can access information through their devices in a dashboard format, obtaining the latest information on specific fields and topics. For example, by entering a prompt such as, "Show me important news related to the latest technology in a dashboard format," predefined information will be organized and displayed. In this way, the system effectively collects and analyzes information, providing users with the information they need in a timely manner.

[0599] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0600] Step 1:

[0601] The server accesses the digital network and collects data using web crawlers and APIs. Specific keywords or topics are provided as input. For example, to obtain information about art exhibitions or cultural events, the URL of a configured website and the data format to be retrieved are specified. The server uses Beautiful Soup to parse the HTML document and extract text information from the specified elements. The output is the collected raw data.

[0602] Step 2:

[0603] The server utilizes Scikit-learn to begin analyzing the collected data. The input is the raw data collected in the previous step. Specifically, it filters out the necessary information from the data and performs data cleansing. During this process, data preprocessing such as normalization and handling of missing values ​​is performed. The output is an analyzable dataset.

[0604] Step 3:

[0605] The server uses the cleansed data to perform trend analysis using machine learning algorithms. The input for this step is the dataset generated in the previous step. Specifically, it performs regression analysis and clustering to predict new trends and patterns by comparing them with historical data. The output is the results of the trend analysis and the recognized patterns.

[0606] Step 4:

[0607] The server generates new tasks and sets their priorities based on the analysis results. The input utilizes the results of trend analysis. Specifically, it runs a scoring model to identify high-priority tasks. For example, tasks such as detailed investigation and action planning are automatically generated for topics that are rapidly gaining attention. The output is a prioritized list of tasks.

[0608] Step 5:

[0609] The server uses visualization tools such as Tableau to generate a visual report of the analysis results. The input for this process is the task list and analysis results generated in step 4. Specifically, it converts the data into graphs and charts and creates a report in a format that is easy for the user to understand intuitively. The output is a visualized report.

[0610] Step 6:

[0611] The user receives generated reports and task lists through their device. The input for this step is reports generated by a visualization tool. The information is displayed in a dashboard format on the device, and the interface is customized to allow the user to focus on specific data. The output is visualized information to support user decision-making. The user can obtain this information by entering a prompt such as, "Please display important news related to the latest technology in a dashboard format."

[0612] (Application Example 1)

[0613] 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".

[0614] Autonomous vehicles are required to accurately grasp traffic and weather conditions in real time to support safe and efficient driving. However, current systems face the challenge of not being able to effectively collect and analyze this information and feed it back into autonomous driving.

[0615] 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.

[0616] In this invention, the server includes data collection means for autonomously collecting information related to a specific area, information analysis means for analyzing the collected information and identifying industry trends, and means for collecting and analyzing real-time information including traffic conditions, road conditions, and weather information. This enables autonomous vehicles to operate safely and efficiently in real time.

[0617] "Information related to a specific domain" refers to data that affects the operation of autonomous vehicles, such as traffic conditions, road conditions, and weather information.

[0618] "Data collection means" refers to technological means for autonomously acquiring necessary information via online services on the internet or sensors.

[0619] "Information analysis methods" refer to technical means that use machine learning techniques to derive patterns and trends based on collected data, and utilize them to optimize operations.

[0620] A "command management system" is a technical means for generating tasks to be executed based on analysis results and determining their priority according to their importance.

[0621] A "display generation means" is a technical means that outputs analysis results in a visually easy-to-understand format and presents them in a way that is easy for the user to understand.

[0622] A "human interaction interface means" is a communication means in which a user receives information from a system and sends commands as needed.

[0623] An "online service" is a platform that serves as a source of data and information provided via the internet.

[0624] "Machine learning methods" refer to technologies that include algorithms and techniques for performing pattern recognition and prediction based on data.

[0625] "Real-time information" refers to the latest data that is constantly updated and is immediately reflected in the decision-making of autonomous vehicles.

[0626] In this invention, the following configuration is conceivable for realizing an information collection and analysis system for autonomous vehicles. First, the server autonomously collects real-time information such as traffic conditions, road conditions, and weather information using data collection means, utilizing sensors and online services on the internet. Next, the information analysis means analyzes the collected data to identify traffic patterns and potential risks. Machine learning algorithms such as TensorFlow can be used in this process.

[0627] The analysis results are generated as commands on the server and prioritized by the command management system. This information is visualized through the display generation system and delivered to the terminal in real time via the user interface. Users can check the latest information necessary for vehicle operation through the dashboard on their terminal and take action or make decisions as needed.

[0628] As a concrete example, an autonomous vehicle in Tokyo can receive traffic congestion information for its planned route five minutes later and plan the optimal detour based on that information. Examples of prompts in this system include:

[0629] "Show me the optimal route from my current location to my destination, taking into account traffic accident information and weather conditions."

[0630] "Analyze the weather changes over the next 15 minutes and how they will affect driving conditions."

[0631] In this way, autonomous vehicles can achieve safer and more efficient operation.

[0632] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0633] Step 1:

[0634] The server collects traffic conditions, road conditions, and weather information from sensors and web APIs. The input consists of data from online services and various sensors, resulting in a clean and consistent dataset. Here, the Scrapy framework is used to retrieve the data and record it in a database.

[0635] Step 2:

[0636] The server analyzes the collected data using TensorFlow. The input is the dataset obtained in step 1, and the output is insights into traffic patterns and potential risks. The analysis process involves comparison with historical data and predictions using machine learning models.

[0637] Step 3:

[0638] The server autonomously generates commands from the analysis results and prioritizes them based on their importance. The input is the insight from step 2, and the output is a list of commands to be executed. A Python script is used to implement the conditional branching and priority algorithms.

[0639] Step 4:

[0640] The server visualizes the information to be displayed based on the instructions and delivers it to the terminal in a dashboard format. The input is the instructions generated in step 3, and the output is graphs and charts for the user. A web application is built using the Flask framework, and the dashboard is displayed using HTML and JavaScript.

[0641] Step 5:

[0642] The user reviews the provided information on the device's dashboard and adjusts the route and settings as needed. The input is the visualization displayed in step 4, and the output is the result of executing commands based on user settings. The user can customize the information and notifications they need by manipulating the dashboard options.

[0643] 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.

[0644] This invention provides a system that enables more adaptive information provision and task management by autonomously collecting data related to a specific field and analyzing it in combination with a function that recognizes user emotions. This system includes information collection means, data analysis means, emotion engine, task management means, output generation means, and user interface means.

[0645] The server utilizes information gathering tools to collect relevant data from news sites, social networking services, and other online platforms on the internet. This data collection is performed regularly, with the aim of providing near real-time information.

[0646] The collected data is sent to data analysis tools and analyzed in detail by machine learning algorithms. This identifies industry trends and the activities of specific companies, and provides insights based on them. This analysis is also supported by an emotion engine, which analyzes user emotions based on user-provided feedback and voice input.

[0647] The emotion engine, for example, recognizes whether a user has positive or negative feelings towards data and provides that information to the task management system. As a result, task priorities are dynamically adjusted based on the user's emotional state.

[0648] The output generation mechanism generates an integrated output combining these analysis results and emotion recognition results. The server creates visualized reports and customized information, providing the data in a format that is easily understandable to the user.

[0649] Users accessing the device receive this information through the user interface. The dashboard displays information optimized based on the user's needs, allowing users to view information and make decisions that align with their own emotions.

[0650] For example, if a user places importance on product launch information and is experiencing stress, the system recognizes this emotion and provides relevant information with greater accuracy and speed than usual to support decision-making. In this way, the system of the present invention achieves flexible and efficient information processing and reporting that takes user emotions into account.

[0651] The following describes the processing flow.

[0652] Step 1:

[0653] The server utilizes information gathering tools, including web crawlers and APIs, to collect data from news sites and social media on the internet. This includes filtering the data using keywords related to specific fields. Collection is performed regularly, ensuring that new information is constantly being added.

[0654] Step 2:

[0655] The server temporarily stores the collected data in a database and extracts relevant information using natural language processing techniques. Data cleansing is also performed here, removing duplicate and noisy data.

[0656] Step 3:

[0657] The server uses data analysis tools to analyze the cleaned data with machine learning algorithms. This analysis helps to understand industry trends and company movements, and new insights can be gained by comparing them with historical data. The analysis results are stored in a database.

[0658] Step 4:

[0659] When a user accesses the system, the emotion engine is activated and analyzes the user's emotions based on their input (e.g., voice or text). The server receives this analysis and identifies the user's current emotional state. Emotional information, such as positive or negative, influences task management.

[0660] Step 5:

[0661] The server generates tasks through an AI agent based on information obtained from the emotion engine and determines task priorities. It is designed to prioritize the delivery of particularly important information when the user is experiencing stress.

[0662] Step 6:

[0663] The server uses output generation mechanisms to create visualized reports and customized information. This generates output that is easy for users to understand. The generated output is provided as graphs, charts, or custom messages.

[0664] Step 7:

[0665] From a user interface running on the device, users receive generated output in a dashboard format. Users can customize the dashboard and prioritize viewing information according to their specific needs and emotions. This allows users to make decisions efficiently.

[0666] (Example 2)

[0667] 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".

[0668] Conventional information delivery systems did not adequately consider the emotional state of users when providing information or managing tasks. As a result, users found it difficult to obtain information that was always appropriate to their emotions and circumstances quickly and accurately, which forced them into inefficient decision-making.

[0669] 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.

[0670] In this invention, the server includes means for autonomously collecting data related to a specific field, means for analyzing the collected data and identifying industry trends, and means for analyzing emotions based on feedback input from users. This enables highly adaptive information provision and efficient task management that takes into account the emotional state of the user.

[0671] "Information gathering means" refers to a means for autonomously collecting data related to a specific field, and has the function of acquiring necessary data from electronic information providers.

[0672] "Data analysis methods" refer to methods of analyzing data using knowledge-based models in order to identify industry trends based on collected data.

[0673] An "emotion analysis tool" is a means of analyzing emotions based on feedback entered by the user and understanding the user's emotional state.

[0674] A "task management system" is a means of generating tasks based on analyzed data and determining their priority.

[0675] An "output generation means" is a means of visualizing and generating output results based on a prioritized task.

[0676] A "user interface means" is a means for delivering the generated output results to a terminal, and has the function of presenting the information in a format that is easy for the user to receive.

[0677] This system can autonomously collect data from various digital sources and provide information that takes user sentiment into consideration. Specifically, the server periodically retrieves data from multiple online platforms on the internet using various data collection methods. This data collection process aims to analyze information in near real-time, utilizing web scraping tools and APIs. For example, the latest articles can be retrieved from news sites using the Python BeautifulSoup library.

[0678] The server analyzes the collected data in more detail using data analysis tools. Machine learning algorithms such as knowledge-based models like TensorFlow and Scikit-learn are used. These analysis tools allow for the identification of industry trends and the activities of specific companies, thereby gaining meaningful insights.

[0679] Furthermore, the server uses sentiment analysis tools to analyze user emotions based on their feedback and voice input. This analysis employs natural language processing techniques, such as using the Google Cloud Natural Language API to identify the sentiment of the input text.

[0680] Users receive information provided by the server via their terminal. For display, visualized reports and customized information generated by the output generation system are presented through the user interface. This allows users to view information in a way that suits their emotional state and needs, supporting efficient decision-making.

[0681] For example, if a user is interested in reviews of a new gadget, the server collects the latest relevant review information and provides the analysis results to the device. At this time, considering the user's past emotional tendencies, the server prioritizes displaying information that better matches the user's preferences. An example of a prompt to the generative AI model would be to instruct the server to "collect information about the launch of a new smartphone and suggest countermeasures if the user's emotional reaction to that information is negative." This allows the server to provide information that more accurately meets the user's needs.

[0682] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0683] Step 1:

[0684] The server periodically retrieves data from news sites, social media, and other online sources using various information gathering methods. It uses URLs and API keys of online platforms as input. Specifically, it employs the Python BeautifulSoup library to extract necessary text data using scraping techniques and convert it into a structured format. As a result, the latest information is accumulated on the server in real time.

[0685] Step 2:

[0686] The server sends the collected data to a data analysis system to analyze industry trends. A knowledge-based model is used for data analysis, taking the previously acquired text data as input. Specifically, a neural network model using TensorFlow is used to classify the data and identify trends. The output is generated as statistical information and graphs showing industry trends based on the analysis results.

[0687] Step 3:

[0688] The server uses sentiment analysis techniques with user feedback as input. It collects feedback and voice data provided by the user through their device and analyzes their emotions using natural language processing technology. Specifically, it uses the Google Cloud Natural Language API to classify emotions from text and assign labels such as positive, negative, or neutral. As a result, the user's emotional state is output in a quantitative format.

[0689] Step 4:

[0690] The server determines task priorities using a task management system based on sentiment analysis results. It uses analyzed sentiment data and industry trend data as input. Specifically, it adjusts task content and deadlines, and then determines priorities. The output is a task list with clearly defined priorities.

[0691] Step 5:

[0692] The server generates customized information for the user using output generation methods. Inputs include analyzed data and sentiment data. Specifically, it uses D3.js to create visualized reports and graphs. The output is a report converted into an easy-to-understand format.

[0693] Step 6:

[0694] The terminal presents visualized reports output from the server to the user through a user interface. It receives customized report data as input. Specifically, it displays necessary information on the dashboard, allowing the user to intuitively understand the information. As a result, users can view information and make decisions based on their own emotions.

[0695] (Application Example 2)

[0696] 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".

[0697] Providing personalized information that takes user emotions into account has been difficult with conventional systems. In particular, dynamically adjusting the priority of information based on user emotions and providing more appropriate content required an advanced system that was linked to emotion recognition technology.

[0698] 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.

[0699] In this invention, the server includes information gathering means for autonomously collecting information related to a specific target area, information analysis means for analyzing the collected information and identifying trends, and emotion recognition means for recognizing the user's emotions and dynamically adjusting accordingly. This enables the provision of personalized information in accordance with the user's emotions.

[0700] "Information gathering means" refers to devices or software that have the function of collecting information related to a specific subject area.

[0701] "Information analysis means" refers to processes or algorithms that have the function of analyzing collected information and identifying trends within related categories.

[0702] "Behavioral management means" refers to a system or control device that executes a process of generating actions based on analyzed information and determining their priority.

[0703] An "emotion recognition tool" is a module or software that has the function of identifying and analyzing the user's emotional state and dynamically adjusting the system's operation.

[0704] "Result generation means" refers to a system or interface for generating and presenting process-based results in a visual or other manner.

[0705] "User interface means" refers to a terminal or application that displays the results of the system to the user and allows them to operate it.

[0706] In this embodiment of the invention, the server first automatically collects information related to a specific area using information collection means. The information is mainly obtained from a communication network, and real-time information updates are possible. This allows analysis to always be performed based on the latest information.

[0707] Next, the server utilizes information analysis tools to analyze the collected information and identify trends. This analysis can use machine learning models such as Google's TensorFlow to precisely identify and analyze information trends.

[0708] Furthermore, the system includes emotion recognition capabilities, using Microsoft Azure's Emotion API to identify the user's emotions. The user's emotion data is analyzed based on data acquired through the device's camera and microphone. This functionality enables flexible information delivery tailored to the user's emotions.

[0709] The result generation mechanism, which integrates analysis results and emotion recognition results, uses React Native to provide a user interface for visually presenting information to the user. Through this interface, the user can receive information adapted to their own emotional state.

[0710] For example, if the system detects that a user is experiencing excessive stress, it will prioritize recommending relaxation music or soothing videos. This allows users to enjoy an emotionally sensitive experience.

[0711] An example of input to the generative AI model would be a prompt sentence like, "Recommend the best music or video content for a user who is feeling stressed."

[0712] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0713] Step 1:

[0714] The server uses information gathering tools to collect information related to a specific area from communication networks. Inputs include specific keywords and categories, and data is retrieved from news sites and social media. The output is a collection of the retrieved raw data. The server performs this process periodically to keep the information up-to-date.

[0715] Step 2:

[0716] The server analyzes the collected raw data using information analysis tools. The input is the raw data collected in step 1, and data patterns and trends are extracted through a machine learning model (e.g., TensorFlow). The output is an analysis result showing specific patterns or trends. The specific operation here is the process of preprocessing the data, inputting it into the analysis model, and obtaining the results.

[0717] Step 3:

[0718] The server activates emotion recognition based on the analyzed data to identify the user's emotional state. It uses video and audio data acquired from the user's device as input. Using the Emotion API, it performs emotion analysis and outputs emotion labels such as positive or negative. The actual operation includes real-time evaluation of the captured user's facial expressions and voice.

[0719] Step 4:

[0720] The server integrates the results of emotion recognition and analysis, and uses a result generation mechanism to select appropriate content. The input consists of the emotional state and analysis results, and the server performs calculations to determine content priority based on these. The output is a list of content tailored to the user's emotions. Data processing is performed dynamically by a priority engine and is constantly optimized.

[0721] Step 5:

[0722] The terminal presents the content obtained from the result generation means to the user through the user interface means. The input is the content list created in step 4, and the output is the interface behavior displayed to the user. The user can intuitively manipulate and select information through this interface. Specific examples of this behavior include visualization and navigation functionality provided by React Native.

[0723] 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.

[0724] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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."

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] The following is further disclosed regarding the embodiments described above.

[0745] (Claim 1)

[0746] Information gathering means that autonomously collect data related to a specific field,

[0747] A data analysis method that analyzes data based on collected data and identifies industry trends,

[0748] A task management system that generates tasks based on analyzed data and determines their priority,

[0749] An output generation means that visualizes and generates output results based on prioritized tasks,

[0750] A user interface means for delivering the output results to a terminal,

[0751] A system that includes this.

[0752] (Claim 2)

[0753] The system according to claim 1, characterized in that the information gathering means includes means for collecting data from an online platform.

[0754] (Claim 3)

[0755] The system according to claim 1, characterized in that the data analysis means analyzes the data using a machine learning algorithm.

[0756] "Example 1"

[0757] (Claim 1)

[0758] Data collection methods for obtaining information from digital networks,

[0759] An information processing means that uses an automated calculation model to analyze the acquired information and identify trends,

[0760] A business management system that generates tasks based on analyzed information and sets their priorities,

[0761] A result generation means that visually represents and produces results based on prioritized tasks,

[0762] A user connection means for transmitting the above results to a communication device,

[0763] A system that includes this.

[0764] (Claim 2)

[0765] The system according to claim 1, characterized in that the data collection means includes means for obtaining information from an internet environment.

[0766] (Claim 3)

[0767] The system according to claim 1, characterized in that the information processing means processes information using an automatic calculation method.

[0768] "Application Example 1"

[0769] (Claim 1)

[0770] A data collection means that autonomously collects information related to a specific domain,

[0771] Information analysis means that analyzes information based on collected data and identifies industry trends,

[0772] A command management means that generates commands based on the analyzed information and determines their priority,

[0773] A display generation means that visualizes and generates output results based on prioritized commands,

[0774] A human interaction interface means for delivering the output results to a terminal,

[0775] A means of collecting and analyzing real-time information including traffic conditions, road conditions, and weather information,

[0776] A system that includes this.

[0777] (Claim 2)

[0778] The system according to claim 1, characterized in that the data collection means includes means for collecting information from online services.

[0779] (Claim 3)

[0780] The system according to claim 1, characterized in that the information analysis means processes information using machine learning techniques.

[0781] "Example 2 of combining an emotion engine"

[0782] (Claim 1)

[0783] Information gathering means that autonomously collect data related to a specific field,

[0784] A data analysis method that analyzes data based on collected data and identifies industry trends,

[0785] A means of analyzing emotions based on feedback entered by users,

[0786] A task management system that generates tasks based on analyzed data and determines their priority,

[0787] An output generation means that visualizes and generates output results based on prioritized tasks,

[0788] A user interface means for delivering the output results to a terminal,

[0789] A system that includes this.

[0790] (Claim 2)

[0791] The system according to claim 1, characterized in that the information gathering means includes means for collecting data from an electronic information provider.

[0792] (Claim 3)

[0793] The system according to claim 1, characterized in that the data analysis means analyzes the data using a knowledge-based model.

[0794] "Application example 2 when combining with an emotional engine"

[0795] (Claim 1)

[0796] Information gathering means that autonomously collect information related to a specific target area,

[0797] Information analysis means for analyzing collected information and identifying trends,

[0798] An action management system that generates actions based on analyzed information and determines their priority,

[0799] An emotion recognition means that recognizes and dynamically adjusts the user's emotions,

[0800] A result generation means that visualizes and generates results based on coordinated actions,

[0801] A user interface means for delivering the results to a terminal,

[0802] A system that includes this.

[0803] (Claim 2)

[0804] The system according to claim 1, characterized in that the information gathering means includes means for acquiring information on a communication network.

[0805] (Claim 3)

[0806] The system according to claim 1, characterized in that the information analysis means analyzes the information using a machine learning model. [Explanation of Symbols]

[0807] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data collection means that autonomously collects information related to a specific domain, Information analysis means that analyzes information based on collected data and identifies industry trends, A command management means that generates commands based on the analyzed information and determines their priority, A display generation means that visualizes and generates output results based on prioritized commands, A human interaction interface means for delivering the output results to a terminal, A means of collecting and analyzing real-time information including traffic conditions, road conditions, and weather information, A system that includes this.

2. The system according to claim 1, characterized in that the data collection means includes means for collecting information from online services.

3. The system according to claim 1, characterized in that the information analysis means processes information using machine learning techniques.

Images