system

Abstract

We provide the system. [Solution] A means of obtaining data from an information source, An analytical means for analyzing the acquired data, A generation means for generating the results of the analysis as a report, A notification means for notifying the generated report using a communication means, A means of sharing data among multiple agents, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a 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 in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is an increasing need for a system that can quickly, efficiently collect, analyze, and report information related to a specific industry. Conventional information collection methods involve a lot of manual data collection and settings, which are time-consuming and labor-intensive, making it difficult to obtain up-to-date information on industry trends in a timely manner. Also, there is a problem that it is difficult to integratively analyze data obtained from different data sources to obtain valuable insights.

Means for Solving the Problems

[0005] This invention provides a system comprising: an acquisition means for automatically acquiring data from an information source; an analysis means for analyzing the acquired data; a generation means for generating analysis results in report format; a notification means for notifying the report using a specified communication means; and a sharing means for sharing data among multiple agents. This system makes it possible to effectively collect and analyze information and quickly provide it to users as output. Furthermore, by improving the quality of information through classification and sentiment evaluation using natural language processing technology, and by delivering information according to a set schedule, it enables near real-time industry analysis.

[0006] "Acquisition method" refers to a function for automatically collecting data from information sources.

[0007] "Analysis means" refers to a function that analyzes collected data and processes it to obtain useful information.

[0008] "Generation means" refers to the function of organizing the analyzed information and outputting it as a report.

[0009] "Notification means" refers to the function of sending the generated report to the user using communication means.

[0010] "Sharing methods" refer to functions that enable the exchange of data among multiple agents in order to improve the accuracy of the information. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled 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.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled 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.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is implemented as a system that automatically collects, analyzes, and reports information to users. The program runs on a server in the cloud and provides information in response to requests from multiple user terminals.

[0033] First, the server periodically retrieves information from pre-registered URLs and SNS APIs. This ensures that the latest industry information is always incorporated into the system. Information is collected in various formats (e.g., text, images, videos), but the system primarily focuses on text data.

[0034] Next, the server analyzes the acquired text data using natural language processing technology. It performs topic classification, sentiment determination, and trend analysis to extract important industry trends. Machine learning algorithms are applied to this analysis, and continuous improvement in accuracy is pursued.

[0035] Once the analysis is complete, the server generates a report based on the analysis results. This report is automatically formatted according to the user's specified format. The report includes text, graphs, tables, and other elements to present the information in an easy-to-understand visual format.

[0036] Subsequently, the server sends the generated report to the user's device according to a pre-configured schedule. This transmission is primarily done via email or team chat applications. This ensures that users always receive the latest industry information.

[0037] Furthermore, the server shares data with other AI agents, allowing them to complement each other's information. This sharing enables more multifaceted information analysis, allowing users to understand the industry situation from multiple perspectives. For example, an AI agent specifically designed for the automotive industry can instantly analyze new car announcements and recall information, providing it as reference material for sales strategies.

[0038] Thus, the present invention is a system that covers everything from automated data collection to analysis and reporting, and provides users with useful industry information quickly.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server accesses registered website URLs and SNS API endpoints to retrieve data according to a periodically scheduled process. The retrieved data undergoes an initial duplicate check before being stored in the database.

[0042] Step 2:

[0043] The server uses a natural language processing (NLP) library to cleanse the text in order to analyze the acquired data. Specifically, it removes unnecessary HTML tags, special characters, and line break codes, formatting the data into a form that is easy to analyze.

[0044] Step 3:

[0045] The server performs topic classification using the cleansed data. Using a topic modeling tool, it extracts key topics from the document set and classifies each article into the corresponding topic.

[0046] Step 4:

[0047] The server then performs sentiment analysis. Using NLP, it determines whether each text expresses a positive, negative, or neutral emotion and assigns an emotional score to each document.

[0048] Step 5:

[0049] The server generates a customized report for the user based on the analysis results. The report provides information in a visually easy-to-understand format, including text summaries, topic summaries, and sentiment analysis results.

[0050] Step 6:

[0051] The server sends the generated reports to the user's terminal according to the schedule and contact method specified by the user. Typically, notifications are sent via email or internal company chat tools to ensure users receive industry information in a timely manner.

[0052] Step 7:

[0053] The server shares data with other AI agents, incorporating additional data and analytical information from each agent to improve the accuracy of the analysis results. This collaboration enhances the diversity and reliability of the information provided to users.

[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 today's information society, a vast amount of information exists on the internet, making it a challenging task to efficiently collect, analyze, and present useful information to users. Furthermore, appropriately analyzing acquired information and reporting it in a way that meets specific needs is crucial, requiring advanced technology and effective systems. Traditional methods have limitations in terms of analytical accuracy and the speed of information delivery, making it difficult for users to obtain the latest and most useful information they require in a timely manner.

[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 a collection means for acquiring information from information sources, a processing means for pre-processing the acquired information, an analysis means for analyzing the information using natural language processing technology, an improvement means for improving the accuracy of the analysis by applying machine learning, a generation means for generating the analysis results as a report, a notification means for notifying the generated report using a communication means, and a sharing means for sharing information among multiple agents. This enables efficient and highly accurate collection and analysis of information, and quick provision of optimal information to users.

[0059] "Collection means" refers to a function that automatically retrieves necessary information from information sources.

[0060] "Processing means" refers to a function that removes unnecessary data from acquired information and converts it into a format that is easy to analyze.

[0061] "Analysis tools" refer to functions that use natural language processing technology to analyze the content of information and perform topic classification and sentiment evaluation.

[0062] "Improvement methods" refer to functions that use machine learning techniques to improve the accuracy of analysis results.

[0063] "Generation means" refers to the function of creating a report based on the results of the analyzed information.

[0064] "Notification method" refers to the function of sending the generated report to the user using a specified communication method.

[0065] A "sharing mechanism" is a function that allows multiple agents to exchange and complement information with each other.

[0066] This invention provides a system for effectively collecting and analyzing information over a network and providing the results to users. The following describes embodiments for carrying out the present invention.

[0067] First, the server continuously retrieves information from pre-registered sources (e.g., URLs of news sites or APIs of social media). This process involves various data formats such as text, images, and videos, but primarily focuses on text data.

[0068] Next, the server preprocesses the acquired data using the Python pandas library. This includes noise reduction and formatting standardization, steps taken to improve the quality of the data.

[0069] The server uses Python's NLTK and Transformers libraries for natural language processing to analyze text data. This allows for topic classification and sentiment analysis, enabling the extraction of important information. Furthermore, the accuracy of the analysis is continuously improved through the use of machine learning techniques. As a specific example, it analyzes opinions on new products in the automotive industry to understand market reactions.

[0070] After the analysis is complete, the server automatically generates a report. This report uses Python's matplotlib library to create graphs and charts, presenting the information to the user in a visually easy-to-understand format. The report is formatted according to the specified format and output as an electronic document.

[0071] The server sends the generated report to the user's device via email or chat application. This communication utilizes the SMTP protocol or specific application APIs. For example, it can be configured to send a report summarizing the latest industry trends every Monday at 9:00 AM.

[0072] Furthermore, the server enriches its information by sharing data with other AI agents. This sharing allows for the integration of analysis results from different perspectives, enabling the provision of diverse information to users.

[0073] Examples of specific prompts include, "Generate a report on the key trends in the automotive industry this week."

[0074] This system allows users to quickly obtain useful information and use it to aid in decision-making.

[0075] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0076] Step 1:

[0077] The server accesses information sources and collects data. URLs of news sites and API keys for social media are used as input. The server uses these inputs to send HTTP requests via the Python requests library and receives raw data in text, image, and video formats as output.

[0078] Step 2:

[0079] The server preprocesses the data obtained in Step 1. The input for preprocessing is the raw data output from Step 1. Specifically, it uses the Python pandas library to remove HTML tags and unnecessary whitespace, and to normalize the text. As a result, clean and consistent text data is output.

[0080] Step 3:

[0081] The server analyzes preprocessed data using natural language processing techniques. It receives clean, preprocessed data as input and utilizes libraries such as NLTK and Transformers to perform topic classification and sentiment analysis. Specifically, it divides text into tokens and calculates trends and sentiment scores. This analysis outputs the data's topics and sentiment ratings as results.

[0082] Step 4:

[0083] The server improves the accuracy of the analysis using machine learning techniques. The analysis results are used as input, and a model is applied using either TENSORFLOW® or scikit-learn. Specifically, this involves inputting data into a trained model and refining its predictions. This results in more accurate analysis results as output.

[0084] Step 5:

[0085] The server generates a report based on the analysis results. The improved analysis results from step 4 are used as input, and data visualization is performed using Python's matplotlib library, followed by formatting based on a report template. Specifically, this includes converting the analysis results into graphs and compiling them into a report document. As a result, a visually organized report is output.

[0086] Step 6:

[0087] The server sends the generated report to the user's device. The generated report and recipient information (email address, chat application API key, etc.) are used as input. The report is sent to the user's device at the specified time using the SMTP protocol or the chat application's API. As a result, the user receives a report containing the latest analysis information.

[0088] Step 7:

[0089] The server shares information with other AI agents. Inputs include analyzed data and inter-agent sharing protocols. In practice, it sends analyzed data via an API and integrates responses from other agents. This process yields multifaceted analytical information as output.

[0090] (Application Example 1)

[0091] 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."

[0092] In today's world, a vast amount of data, often referred to as an information flood, is generated daily. There is a need to extract useful information from this data and deliver it quickly to users. However, traditional methods require considerable time and effort for information selection and report personalization, making it difficult to provide information when users need it. There is a need to solve this problem and efficiently provide information tailored to user needs.

[0093] 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.

[0094] In this invention, the server includes acquisition means for obtaining data from information sources, analysis means for analyzing the acquired data, and personalization means for customizing reports based on the user's interests and past browsing history. This makes it possible to quickly and accurately provide users with individually optimized reports.

[0095] "Information source" refers to the base location or medium from which data is obtained, specifically referring to websites on the internet, APIs, and so on.

[0096] "Means of acquisition" refers to a system for extracting and incorporating necessary data from information sources.

[0097] "Analysis methods" refer to the technologies and algorithms used to analyze acquired data and extract necessary information.

[0098] "Generative means" refers to the process or tools used to compile analyzed information and create a formal report.

[0099] "Communication method" refers to the method used to deliver the generated report to the designated user, and includes methods such as email and chat applications.

[0100] "Sharing methods" refer to a system that allows multiple agents to exchange and effectively utilize data with each other.

[0101] "Personalization methods" refer to techniques for selecting content based on a user's past browsing history and interests, and creating individually optimized reports.

[0102] "Display means" refers to devices or methods for providing a generated report to the user visually, such as displays or head-mounted displays.

[0103] To implement this invention, it is necessary to build a system that integrates information gathering, analysis, report generation, and notification as a series of processes. The server first retrieves the latest data from the information source. Here, information is periodically retrieved from websites and APIs on the internet. It is common to use a library such as requests for this purpose.

[0104] Next, the server analyzes the acquired data. This analysis utilizes natural language processing techniques, such as using the nlp_module library for topic classification and sentiment evaluation. Furthermore, a generative AI model is used to organize the information based on the prompt text and extract information that the user is interested in.

[0105] The generated analysis results are compiled into a report. The server generates the report in a visually easy-to-understand format, such as including graphs and tables. The report is customized taking into account the user's past browsing history and interests.

[0106] The server then notifies the user of the generated report via communication means. Notifications are sent via email or chat applications, and the report is automatically sent at a predetermined time. The report can also be directly displayed on a display device such as a head-mounted display.

[0107] As a concrete example, a service could be envisioned that provides soccer fans with a daily report containing the latest match results and player interviews. An example of a prompt would be, "Please summarize today's soccer news." This invention allows users to quickly and accurately receive individually optimized information.

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

[0109] Step 1:

[0110] The server retrieves data from information sources. Specifically, it uses the requests library to send HTTP requests to periodically collect information from websites and APIs. The input is a list of URLs of the information sources, and the output is data in JSON format. The server stores this in a parseable format.

[0111] Step 2:

[0112] The server analyzes the acquired data. Using natural language processing techniques, it performs topic classification and sentiment evaluation of the data using the nlp_module. The input is the acquired JSON data, and the output is analysis results including text data classified by topic and sentiment scores. The server then extracts information that matches the user's interests.

[0113] Step 3:

[0114] The server generates a report based on the analysis results. It uses the `report_generator` module to create a customized report, taking into account the user's past browsing history and interests. The input is the analysis results, and the output is a visually represented report. The server formats the report, including graphs and tables, in a user-friendly format.

[0115] Step 4:

[0116] The server notifies the terminal of the generated report via communication means. The report is automatically sent using email or a chat application. The input is the generated report, and the output is the notification sent to the user's terminal. The server uses a scheduling function to repeat this process at predetermined times.

[0117] Step 5:

[0118] The user views the received report on a display device. The report can be viewed on the terminal's display or a head-mounted display. The input is the received report, and the output is the information displayed on the user's visual display device. Based on this, the user can access the latest information and view content that matches their interests.

[0119] 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.

[0120] This invention combines a system for information gathering, analysis, report generation, and notification with an emotion engine that recognizes user emotions, thereby enabling the provision of information that is more tailored to user needs. This system is implemented by servers running in a cloud or local environment.

[0121] First, the server automatically collects data from information sources. This process utilizes APIs from specific websites and social networking platforms, extracting data based on pre-configured keywords and areas of interest. The information is kept up-to-date through regular updates.

[0122] Next, the server analyzes the acquired data using natural language processing (NLP) techniques. Through NLP, the data is categorized by topic, and the mood of each document is evaluated through sentiment analysis. This analysis result is used to improve the value provided to the user.

[0123] Furthermore, in this invention, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is performed based on the user's past feedback and interaction data, forming a kind of emotional profile. For example, it learns the user's tendencies, such as what kind of news they usually like or what kind of information they avoid when stressed. Based on this profile, the server provides information that corresponds to the user's current emotional state, personalizing the user experience.

[0124] In generating reports, the server integrates analysis results with the user's emotional profile to create individually optimized content. For example, if positive emotions are needed, the report is adjusted to highlight positive news and positive analysis. This report is generated in real time and notified to the device. Notifications are made via email or chat applications, allowing users to access the information immediately.

[0125] For example, if a user prefers financial news, we can support their decision-making by providing the latest information on recent market trends, and if a user is feeling anxious, we can recommend information that helps with risk hedging.

[0126] By incorporating an emotion engine in this way, it becomes possible to provide more personalized and emotionally resonant information, maximizing the value of the information for the user.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server collects data from registered information sources. Specifically, it uses RSS feeds from news sites and APIs from social media to periodically retrieve the latest data related to topics of interest and store it in a database.

[0130] Step 2:

[0131] The server cleanses the acquired data and analyzes it using natural language processing techniques. It removes noise from the text, tokenizes the documents, and then performs topic classification and sentiment analysis. This allows the content and mood of each document to be evaluated.

[0132] Step 3:

[0133] The server updates the user's sentiment profile based on the user's past behavior history and feedback data. It learns what kind of news the user has preferred to read in the past and what kind of information they are currently avoiding, thereby enriching the profile.

[0134] Step 4:

[0135] The server generates a report based on the analysis results and the user's emotional profile. The report incorporates appropriately personalized information, taking into account the user's current emotional state.

[0136] Step 5:

[0137] The server notifies the user's device of the generated report. The report is sent via the user's preferred communication method (e.g., email or chat app), allowing the user to check the information in real time.

[0138] Step 6:

[0139] The server shares data and analysis results with other AI agents. This allows for improved accuracy and diversity of information not only within the company's own system but also across the entire network. Users can then receive broader and more accurate information.

[0140] (Example 2)

[0141] 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".

[0142] In today's information-saturated society, there is a need to provide users with the information they need accurately and in a context-appropriate manner. However, current information delivery systems lack sufficient personalization to respond to users' emotions and needs, making it difficult for users to obtain the necessary information at the right time.

[0143] 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.

[0144] In this invention, the server includes an acquisition means for obtaining data from an information source, an analysis means for analyzing the acquired data using natural language processing technology, performing classification and sentiment evaluation, and a generation means for integrating the analysis results with the user's sentiment profile to generate a report. This enables the provision of personalized information tailored to the user's emotional state and needs. Furthermore, since the content is notified in real time via email or chat applications, users can quickly access the information they need.

[0145] "Acquisition method" refers to a mechanism for automatically retrieving data from an information source.

[0146] "Analysis means" refers to a function that uses natural language processing technology on collected data to classify topics and evaluate sentiment.

[0147] "Generation method" refers to the process of integrating the analyzed data with the user's emotional profile to create a report.

[0148] "Notification method" refers to the use of email or chat applications to communicate generated reports to users in real time.

[0149] "Personalization methods" refer to technologies that analyze a user's past behavioral data to create an emotional profile and then provide personalized information based on that profile.

[0150] A "generative AI model" is an artificial intelligence-based technology used to optimize report content based on prompt text.

[0151] A "prompt" is input text that gives instructions to a generative AI model, causing it to generate desired information or content.

[0152] This invention is a system that provides user-optimized information according to specific emotional states, and is implemented by combining multiple technological elements. The system is mainly composed of servers operating in a cloud environment or local environment, and its functions are as follows:

[0153] The server first has means of acquiring data from information sources. In this process, data is collected from various information sources, such as websites and APIs of social networking platforms. Subsequently, the collected data is analyzed using analytical tools that employ natural language processing (NLP) techniques. In this analysis, the data is classified by topic, and sentiment evaluation is performed using sentiment analysis tools.

[0154] Next, the server generates a report that integrates the analysis results and the user's sentiment profile. In this process, a generation AI model is used to generate optimized information based on the prompt text. For example, if the prompt text "Please report recent market information positively" is entered, the AI ​​model will create a report according to that instruction.

[0155] The generated reports are notified to the device in real time, and users can access them immediately. Data is sent via email or chat applications, and reports are delivered at times specified by the user using a scheduling function.

[0156] For example, if a user prefers technology-related news, this system will collect and analyze information on the latest technological trends and report them in a way that suits the user's interests. Furthermore, when a user is feeling stressed, it will recommend news containing relaxing information and positive content to support the user's decision-making.

[0157] Thus, the present invention is a system that improves the user experience and enables the provision of necessary information at the appropriate time.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The server retrieves data from information sources. Input is a specific URL or endpoint using APIs from websites or social networking platforms, and output is the retrieved raw data. Specifically, it calls APIs according to configured keywords and themes, and stores the retrieved news articles and social networking posts in a database.

[0161] Step 2:

[0162] The server performs analysis on the acquired data using natural language processing techniques. The input is the raw data collected in step 1, and the output is data classified by topic and assigned sentiment scores. Specifically, the analysis tool is used to classify each text into a topic, and a sentiment analysis algorithm is applied to perform sentiment evaluation.

[0163] Step 3:

[0164] The server creates an emotional profile based on the user's past behavioral data. The input is the user's past feedback and behavioral history data, and the output is the user's emotional profile. Specifically, it applies machine learning algorithms to analyze the user's preferences and past selection tendencies.

[0165] Step 4:

[0166] The server generates a report based on the analysis results and the user's sentiment profile. The input is the analysis data from step 2 and the sentiment profile from step 3, and the output is a personalized report. A generative AI model is used to generate prompt sentences, such as "Create a report highlighting positive technology news."

[0167] Step 5:

[0168] The terminal notifies the user of the generated report. The input is the report generated in step 4, and the output is the real-time notification the user receives. Specifically, the report is sent via email or chat application, and the scheduling function is used to set delivery at a specified time.

[0169] (Application Example 2)

[0170] 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".

[0171] In today's various information provision systems, it is difficult to provide optimal information tailored to the individual emotions and interests of users. Therefore, there is a need for a system that understands emotions and provides timely information appropriate to the user. In particular, a flexible response that accommodates information needs that vary depending on stress levels and moods is desirable.

[0172] 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.

[0173] In this invention, the server includes acquisition means for obtaining information from information sources, analysis means for analyzing the acquired information, and emotion recognition means for recognizing the user's emotional state using an emotion engine and selecting information according to that emotional state. This makes it possible to form an emotional profile of the user and provide individually optimized information.

[0174] "Information sources" refer to the sources of information, such as websites and social media platforms on the internet, that are used to obtain data.

[0175] "Acquisition means" refers to the processes and technologies used to collect data from information sources, and includes functions that automatically extract information using APIs, etc.

[0176] "Analysis methods" refer to the means used to analyze acquired data, specifically the process of organizing the data using natural language processing techniques and evaluating the emotional state and topics of the information.

[0177] "Generation means" refers to the process of generating documents based on the results of analysis, and has the function of formatting information into reports or other formats.

[0178] "Notification means" refers to a communication function for sending and receiving generated documents to users, providing information in real time or at a specified time.

[0179] "Emotion recognition means" refers to the process of analyzing a user's emotional state using an emotion engine, selecting data based on the results, and providing appropriate information.

[0180] "Personalization" refers to the process of individually optimizing information and adjusting the content provided based on the user's emotional profile.

[0181] A "knowledge system" refers to an integrated system that acquires, analyzes, and generates information, and provides users with the most relevant information based on their emotional state.

[0182] This invention is a knowledge system for providing information based on the emotional state of users. The server automatically acquires information from information sources and analyzes that information using natural language processing technology. Specifically, it classifies data acquired from websites and social media platforms using a word processing engine and performs sentiment evaluation.

[0183] The emotion engine recognizes the user's current emotional state based on their past behavioral history and feedback data. Based on this recognition, the server selects the most appropriate information and generates it as an individually optimized document. This generated document is delivered to the user in real time or at a specified time via a terminal with notification capabilities.

[0184] The processing utilizes cloud-based servers (e.g., Amazon Web Services), a natural language processing engine (e.g., Google Cloud Natural Language API), and a sentiment analysis library (e.g., NVIDIA DeepStream SDK). This allows the server to effectively organize information and provide it in a way that meets the user's needs.

[0185] For example, if a user is feeling stressed after a trip, the server might recommend a playlist containing relaxing music that they previously enjoyed. In this way, personalized information tailored to the user's emotions is provided.

[0186] An example of a prompt would be, "When a user is looking for music to relax after a delayed flight, how would you create a playlist that includes jazz artists they have liked in the past?" Based on such prompts, a generative AI model can provide the most suitable suggestions to the user.

[0187] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0188] Step 1:

[0189] The server collects information from information sources. These sources include specific websites and social media platforms, and the server retrieves data from these sources based on preset keywords. The input is the URL or API key of the information source, and the output is the retrieved raw data.

[0190] Step 2:

[0191] The server analyzes the acquired raw data using natural language processing techniques. Specifically, the server converts the data into text, classifies it by topic using a word processing engine, and performs sentiment evaluation. The input is raw data, and the output is classified and sentiment-evaluated data.

[0192] Step 3:

[0193] The server uses an emotion engine to recognize the user's emotional state. Based on past feedback and behavioral history, the server updates the user's emotional profile. The input is the user's historical data and analyzed data, and the output is the updated emotional profile.

[0194] Step 4:

[0195] The server selects the most relevant information based on the sentiment profile and generates individually optimized documents. A generative AI model is used to format the document in a way that responds to prompts. The input is the updated sentiment profile and analyzed data, and the output is the optimized document.

[0196] Step 5:

[0197] The server sends the generated document to a terminal with notification capabilities. Using a scheduling function, information can be sent in real time or at a specified time to provide information to the user. Input consists of the optimized document and the user's contact information, while output is the provision of information to the user's terminal.

[0198] 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.

[0199] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0200] 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.

[0201] [Second Embodiment]

[0202] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0203] 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.

[0204] 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).

[0205] 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.

[0206] 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.

[0207] 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).

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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".

[0214] This invention is implemented as a system that automatically collects, analyzes, and reports information to users. The program runs on a server in the cloud and provides information in response to requests from multiple user terminals.

[0215] First, the server periodically retrieves information from pre-registered URLs and SNS APIs. This ensures that the latest industry information is always incorporated into the system. Information is collected in various formats (e.g., text, images, videos), but the system primarily focuses on text data.

[0216] Next, the server analyzes the acquired text data using natural language processing technology. It performs topic classification, sentiment determination, and trend analysis to extract important industry trends. Machine learning algorithms are applied to this analysis, and continuous improvement in accuracy is pursued.

[0217] Once the analysis is complete, the server generates a report based on the analysis results. This report is automatically formatted according to the user's specified format. The report includes text, graphs, tables, and other elements to present the information in an easy-to-understand visual format.

[0218] Subsequently, the server sends the generated report to the user's device according to a pre-configured schedule. This transmission is primarily done via email or team chat applications. This ensures that users always receive the latest industry information.

[0219] Furthermore, the server shares data with other AI agents, allowing them to complement each other's information. This sharing enables more multifaceted information analysis, allowing users to understand the industry situation from multiple perspectives. For example, an AI agent specifically designed for the automotive industry can instantly analyze new car announcements and recall information, providing it as reference material for sales strategies.

[0220] Thus, the present invention is a system that covers everything from automated data collection to analysis and reporting, and provides users with useful industry information quickly.

[0221] The following describes the processing flow.

[0222] Step 1:

[0223] The server accesses registered website URLs and SNS API endpoints to retrieve data according to a periodically scheduled process. The retrieved data undergoes an initial duplicate check before being stored in the database.

[0224] Step 2:

[0225] The server uses a natural language processing (NLP) library to cleanse the text in order to analyze the acquired data. Specifically, it removes unnecessary HTML tags, special characters, and line break codes, formatting the data into a form that is easy to analyze.

[0226] Step 3:

[0227] The server performs topic classification using the cleansed data. Using a topic modeling tool, it extracts key topics from the document set and classifies each article into the corresponding topic.

[0228] Step 4:

[0229] The server then performs sentiment analysis. Using NLP, it determines whether each text expresses a positive, negative, or neutral emotion and assigns an emotional score to each document.

[0230] Step 5:

[0231] The server generates a customized report for the user based on the analysis results. The report provides information in a visually easy-to-understand format, including text summaries, topic summaries, and sentiment analysis results.

[0232] Step 6:

[0233] The server sends the generated reports to the user's terminal according to the schedule and contact method specified by the user. Typically, notifications are sent via email or internal company chat tools to ensure users receive industry information in a timely manner.

[0234] Step 7:

[0235] The server shares data with other AI agents, incorporating additional data and analytical information from each agent to improve the accuracy of the analysis results. This collaboration enhances the diversity and reliability of the information provided to users.

[0236] (Example 1)

[0237] 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."

[0238] In today's information society, a vast amount of information exists on the internet, making it a challenging task to efficiently collect, analyze, and present useful information to users. Furthermore, appropriately analyzing acquired information and reporting it in a way that meets specific needs is crucial, requiring advanced technology and effective systems. Traditional methods have limitations in terms of analytical accuracy and the speed of information delivery, making it difficult for users to obtain the latest and most useful information they require in a timely manner.

[0239] 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.

[0240] In this invention, the server includes a collection means for acquiring information from information sources, a processing means for pre-processing the acquired information, an analysis means for analyzing the information using natural language processing technology, an improvement means for improving the accuracy of the analysis by applying machine learning, a generation means for generating the analysis results as a report, a notification means for notifying the generated report using a communication means, and a sharing means for sharing information among multiple agents. This enables efficient and highly accurate collection and analysis of information, and quick provision of optimal information to users.

[0241] "Collection means" refers to a function that automatically retrieves necessary information from information sources.

[0242] "Processing means" refers to a function that removes unnecessary data from acquired information and converts it into a format that is easy to analyze.

[0243] "Analysis tools" refer to functions that use natural language processing technology to analyze the content of information and perform topic classification and sentiment evaluation.

[0244] "Improvement methods" refer to functions that use machine learning techniques to improve the accuracy of analysis results.

[0245] "Generation means" refers to the function of creating a report based on the results of the analyzed information.

[0246] "Notification method" refers to the function of sending the generated report to the user using a specified communication method.

[0247] A "sharing mechanism" is a function that allows multiple agents to exchange and complement information with each other.

[0248] This invention provides a system for effectively collecting and analyzing information over a network and providing the results to users. The following describes embodiments for carrying out the present invention.

[0249] First, the server continuously retrieves information from pre-registered sources (e.g., URLs of news sites or APIs of social media). This process involves various data formats such as text, images, and videos, but primarily focuses on text data.

[0250] Next, the server preprocesses the acquired data using the Python pandas library. This includes noise reduction and formatting standardization, steps taken to improve the quality of the data.

[0251] The server uses Python's NLTK and Transformers libraries for natural language processing to analyze text data. This allows for topic classification and sentiment analysis, enabling the extraction of important information. Furthermore, the accuracy of the analysis is continuously improved through the use of machine learning techniques. As a specific example, it analyzes opinions on new products in the automotive industry to understand market reactions.

[0252] After the analysis is complete, the server automatically generates a report. This report uses Python's matplotlib library to create graphs and charts, presenting the information to the user in a visually easy-to-understand format. The report is formatted according to the specified format and output as an electronic document.

[0253] The server sends the generated report to the user's device via email or chat application. This communication utilizes the SMTP protocol or specific application APIs. For example, it can be configured to send a report summarizing the latest industry trends every Monday at 9:00 AM.

[0254] Furthermore, the server enriches its information by sharing data with other AI agents. This sharing allows for the integration of analysis results from different perspectives, enabling the provision of diverse information to users.

[0255] Examples of specific prompts include, "Generate a report on the key trends in the automotive industry this week."

[0256] This system allows users to quickly obtain useful information and use it to aid in decision-making.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The server accesses information sources and collects data. URLs of news sites and API keys for social media are used as input. The server uses these inputs to send HTTP requests via the Python requests library and receives raw data in text, image, and video formats as output.

[0260] Step 2:

[0261] The server preprocesses the data obtained in Step 1. The input for preprocessing is the raw data output from Step 1. Specifically, it uses the Python pandas library to remove HTML tags and unnecessary whitespace, and to normalize the text. As a result, clean and consistent text data is output.

[0262] Step 3:

[0263] The server analyzes preprocessed data using natural language processing techniques. It receives clean, preprocessed data as input and utilizes libraries such as NLTK and Transformers to perform topic classification and sentiment analysis. Specifically, it divides text into tokens and calculates trends and sentiment scores. This analysis outputs the data's topics and sentiment ratings as results.

[0264] Step 4:

[0265] The server improves the accuracy of the analysis using machine learning techniques. The analysis results are used as input, and a model is applied using either TensorFlow or scikit-learn. Specifically, this involves inputting data into a pre-trained model and refining its predictions. This results in more accurate analysis results as output.

[0266] Step 5:

[0267] The server generates a report based on the analysis results. The improved analysis results from step 4 are used as input, and data visualization is performed using Python's matplotlib library, followed by formatting based on a report template. Specifically, this includes converting the analysis results into graphs and compiling them into a report document. As a result, a visually organized report is output.

[0268] Step 6:

[0269] The server sends the generated report to the user's device. The generated report and recipient information (email address, chat application API key, etc.) are used as input. The report is sent to the user's device at the specified time using the SMTP protocol or the chat application's API. As a result, the user receives a report containing the latest analysis information.

[0270] Step 7:

[0271] The server shares information with other AI agents. Inputs include analyzed data and inter-agent sharing protocols. In practice, it sends analyzed data via an API and integrates responses from other agents. This process yields multifaceted analytical information as output.

[0272] (Application Example 1)

[0273] 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."

[0274] In today's world, a vast amount of data, often referred to as an information flood, is generated daily. There is a need to extract useful information from this data and deliver it quickly to users. However, traditional methods require considerable time and effort for information selection and report personalization, making it difficult to provide information when users need it. There is a need to solve this problem and efficiently provide information tailored to user needs.

[0275] 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.

[0276] In this invention, the server includes acquisition means for obtaining data from information sources, analysis means for analyzing the acquired data, and personalization means for customizing reports based on the user's interests and past browsing history. This makes it possible to quickly and accurately provide users with individually optimized reports.

[0277] "Information source" refers to the base location or medium from which data is obtained, specifically referring to websites on the internet, APIs, and so on.

[0278] "Means of acquisition" refers to a system for extracting and incorporating necessary data from information sources.

[0279] "Analysis methods" refer to the technologies and algorithms used to analyze acquired data and extract necessary information.

[0280] "Generative means" refers to the process or tools used to compile analyzed information and create a formal report.

[0281] "Communication method" refers to the method used to deliver the generated report to the designated user, and includes methods such as email and chat applications.

[0282] "Sharing methods" refer to a system that allows multiple agents to exchange and effectively utilize data with each other.

[0283] The "personalization means" refers to a method for selecting content according to the user's past browsing history and interests and creating an individually optimized report.

[0284] The "display means" is a device or method for visually providing the generated report to the user, and refers to, for example, a display or a head-mounted display.

[0285] To implement this invention, it is necessary to construct a system that integrates information collection, analysis, report generation, and notification as a series of processes. The server first obtains the latest data from an information source. Here, information is regularly retrieved from websites and APIs on the Internet. It is common to use libraries such as requests for this.

[0286] Next, the server analyzes the acquired data. Natural language processing technology is used for this analysis. For example, topic classification and sentiment evaluation are performed using the nlp_module library. Furthermore, a generative AI model is utilized to organize information based on a prompt sentence and extract information that the user is interested in.

[0287] The generated analysis results are summarized as a report. The server generates the report in a visually easy-to-understand format, for example, including graphs and tables. The customization of the report takes into account the user's past browsing history and interests.

[0288] After that, the server notifies the user of the generated report through communication means. Email or chat apps are used for notification, and the report is automatically sent at a specified time. Also, the report can be directly displayed on a display device such as a head-mounted display.

[0289] As a concrete example, a service could be envisioned that provides soccer fans with a daily report containing the latest match results and player interviews. An example of a prompt would be, "Please summarize today's soccer news." This invention allows users to quickly and accurately receive individually optimized information.

[0290] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0291] Step 1:

[0292] The server retrieves data from information sources. Specifically, it uses the requests library to send HTTP requests to periodically collect information from websites and APIs. The input is a list of URLs of the information sources, and the output is data in JSON format. The server stores this in a parseable format.

[0293] Step 2:

[0294] The server analyzes the acquired data. Using natural language processing techniques, it performs topic classification and sentiment evaluation of the data using the nlp_module. The input is the acquired JSON data, and the output is analysis results including text data classified by topic and sentiment scores. The server then extracts information that matches the user's interests.

[0295] Step 3:

[0296] The server generates a report based on the analysis results. It uses the `report_generator` module to create a customized report, taking into account the user's past browsing history and interests. The input is the analysis results, and the output is a visually represented report. The server formats the report, including graphs and tables, in a user-friendly format.

[0297] Step 4:

[0298] The server notifies the terminal of the generated report via communication means. The report is automatically sent using email or a chat application. The input is the generated report, and the output is the notification sent to the user's terminal. The server uses a scheduling function to repeat this process at predetermined times.

[0299] Step 5:

[0300] The user views the received report on a display device. The report can be viewed on the terminal's display or a head-mounted display. The input is the received report, and the output is the information displayed on the user's visual display device. Based on this, the user can access the latest information and view content that matches their interests.

[0301] 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.

[0302] This invention combines a system for information gathering, analysis, report generation, and notification with an emotion engine that recognizes user emotions, thereby enabling the provision of information that is more tailored to user needs. This system is implemented by servers running in a cloud or local environment.

[0303] First, the server automatically collects data from information sources. This process utilizes APIs from specific websites and social networking platforms, extracting data based on pre-configured keywords and areas of interest. The information is kept up-to-date through regular updates.

[0304] Next, the server analyzes the acquired data using natural language processing (NLP) techniques. Through NLP, the data is categorized by topic, and the mood of each document is evaluated through sentiment analysis. This analysis result is used to improve the value provided to the user.

[0305] Furthermore, in the present invention, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is based on the user's past feedback and interaction data, forming a kind of emotion profile. For example, it learns tendencies such as what kind of news the user usually likes and what kind of information to avoid when stressed. Based on this profile, the server provides information according to the user's current emotional state, personalizing the user experience.

[0306] In the generation of the report, the server integrates the analysis results and the user's emotion profile to create content optimized individually. For example, when positive emotions are required, it is adjusted so that favorable news and positive analysis are emphasized. This report is generated in real time and notified to the terminal. The notification uses an email or a chat app to make it accessible to the user immediately.

[0307] As a specific example, when the user likes financial-related news, by providing the latest information on recent market trends and recommending information useful for risk hedging when the user is feeling anxious, it supports the user's decision-making.

[0308] In this way, by incorporating an emotion engine, it becomes possible to provide more personalized and emotion-resonating information, maximizing the information value to the user.

[0309] The following describes the processing flow.

[0310] Step 1:

[0311] The server collects data from registered information sources. Specifically, it uses the RSS feed of news sites and the API of SNS to periodically obtain the latest data related to interesting topics and saves it in the database.

[0312] Step 2:

[0313] The server cleanses the acquired data and analyzes it using natural language processing techniques. It removes noise from the text, tokenizes the documents, and then performs topic classification and sentiment analysis. This allows the content and mood of each document to be evaluated.

[0314] Step 3:

[0315] The server updates the user's sentiment profile based on the user's past behavior history and feedback data. It learns what kind of news the user has preferred to read in the past and what kind of information they are currently avoiding, thereby enriching the profile.

[0316] Step 4:

[0317] The server generates a report based on the analysis results and the user's emotional profile. The report incorporates appropriately personalized information, taking into account the user's current emotional state.

[0318] Step 5:

[0319] The server notifies the user's device of the generated report. The report is sent via the user's preferred communication method (e.g., email or chat app), allowing the user to check the information in real time.

[0320] Step 6:

[0321] The server shares data and analysis results with other AI agents. This allows for improved accuracy and diversity of information not only within the company's own system but also across the entire network. Users can then receive broader and more accurate information.

[0322] (Example 2)

[0323] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0324] In today's information-saturated society, there is a need to provide users with the information they need accurately and in a context-appropriate manner. However, current information delivery systems lack sufficient personalization to respond to users' emotions and needs, making it difficult for users to obtain the necessary information at the right time.

[0325] 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.

[0326] In this invention, the server includes an acquisition means for obtaining data from an information source, an analysis means for analyzing the acquired data using natural language processing technology, performing classification and sentiment evaluation, and a generation means for integrating the analysis results with the user's sentiment profile to generate a report. This enables the provision of personalized information tailored to the user's emotional state and needs. Furthermore, since the content is notified in real time via email or chat applications, users can quickly access the information they need.

[0327] "Acquisition method" refers to a mechanism for automatically retrieving data from an information source.

[0328] "Analysis means" refers to a function that uses natural language processing technology on collected data to classify topics and evaluate sentiment.

[0329] "Generation method" refers to the process of integrating the analyzed data with the user's emotional profile to create a report.

[0330] "Notification method" refers to the use of email or chat applications to communicate generated reports to users in real time.

[0331] "Personalization methods" refer to technologies that analyze a user's past behavioral data to create an emotional profile and then provide personalized information based on that profile.

[0332] A "generative AI model" is an artificial intelligence-based technology used to optimize report content based on prompt text.

[0333] A "prompt" is input text that gives instructions to a generative AI model, causing it to generate desired information or content.

[0334] This invention is a system that provides user-optimized information according to specific emotional states, and is implemented by combining multiple technological elements. The system is mainly composed of servers operating in a cloud environment or local environment, and its functions are as follows:

[0335] The server first has means of acquiring data from information sources. In this process, data is collected from various information sources, such as websites and APIs of social networking platforms. Subsequently, the collected data is analyzed using analytical tools that employ natural language processing (NLP) techniques. In this analysis, the data is classified by topic, and sentiment evaluation is performed using sentiment analysis tools.

[0336] Next, the server generates a report that integrates the analysis results and the user's sentiment profile. In this process, a generation AI model is used to generate optimized information based on the prompt text. For example, if the prompt text "Please report recent market information positively" is entered, the AI ​​model will create a report according to that instruction.

[0337] The generated reports are notified to the device in real time, and users can access them immediately. Data is sent via email or chat applications, and reports are delivered at times specified by the user using a scheduling function.

[0338] For example, if a user prefers technology-related news, this system will collect and analyze information on the latest technological trends and report them in a way that suits the user's interests. Furthermore, when a user is feeling stressed, it will recommend news containing relaxing information and positive content to support the user's decision-making.

[0339] Thus, the present invention is a system that improves the user experience and enables the provision of necessary information at the appropriate time.

[0340] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0341] Step 1:

[0342] The server retrieves data from information sources. Input is a specific URL or endpoint using APIs from websites or social networking platforms, and output is the retrieved raw data. Specifically, it calls APIs according to configured keywords and themes, and stores the retrieved news articles and social networking posts in a database.

[0343] Step 2:

[0344] The server performs analysis on the acquired data using natural language processing techniques. The input is the raw data collected in step 1, and the output is data classified by topic and assigned sentiment scores. Specifically, the analysis tool is used to classify each text into a topic, and a sentiment analysis algorithm is applied to perform sentiment evaluation.

[0345] Step 3:

[0346] The server creates an emotional profile based on the user's past behavioral data. The input is the user's past feedback and behavioral history data, and the output is the user's emotional profile. Specifically, it applies machine learning algorithms to analyze the user's preferences and past selection tendencies.

[0347] Step 4:

[0348] The server generates a report based on the analysis results and the user's sentiment profile. The input is the analysis data from step 2 and the sentiment profile from step 3, and the output is a personalized report. A generative AI model is used to generate prompt sentences, such as "Create a report highlighting positive technology news."

[0349] Step 5:

[0350] The terminal notifies the user of the generated report. The input is the report generated in step 4, and the output is the real-time notification the user receives. Specifically, the report is sent via email or chat application, and the scheduling function is used to set delivery at a specified time.

[0351] (Application Example 2)

[0352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0353] In today's various information provision systems, it is difficult to provide optimal information tailored to the individual emotions and interests of users. Therefore, there is a need for a system that understands emotions and provides timely information appropriate to the user. In particular, a flexible response that accommodates information needs that vary depending on stress levels and moods is desirable.

[0354] 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.

[0355] In this invention, the server includes acquisition means for obtaining information from information sources, analysis means for analyzing the acquired information, and emotion recognition means for recognizing the user's emotional state using an emotion engine and selecting information according to that emotional state. This makes it possible to form an emotional profile of the user and provide individually optimized information.

[0356] "Information sources" refer to the sources of information, such as websites and social media platforms on the internet, that are used to obtain data.

[0357] "Acquisition means" refers to the processes and technologies used to collect data from information sources, and includes functions that automatically extract information using APIs, etc.

[0358] "Analysis methods" refer to the means used to analyze acquired data, specifically the process of organizing the data using natural language processing techniques and evaluating the emotional state and topics of the information.

[0359] "Generation means" refers to the process of generating documents based on the results of analysis, and has the function of formatting information into reports or other formats.

[0360] "Notification means" refers to a communication function for sending and receiving generated documents to users, providing information in real time or at a specified time.

[0361] "Emotion recognition means" refers to the process of analyzing a user's emotional state using an emotion engine, selecting data based on the results, and providing appropriate information.

[0362] "Personalization" refers to the process of individually optimizing information and adjusting the content provided based on the user's emotional profile.

[0363] A "knowledge system" refers to an integrated system that acquires, analyzes, and generates information, and provides users with the most relevant information based on their emotional state.

[0364] This invention is a knowledge system for providing information based on the emotional state of users. The server automatically acquires information from information sources and analyzes that information using natural language processing technology. Specifically, it classifies data acquired from websites and social media platforms using a word processing engine and performs sentiment evaluation.

[0365] The emotion engine recognizes the user's current emotional state based on their past behavioral history and feedback data. Based on this recognition, the server selects the most appropriate information and generates it as an individually optimized document. This generated document is delivered to the user in real time or at a specified time via a terminal with notification capabilities.

[0366] The processing utilizes cloud-based servers (e.g., Amazon Web Services), a natural language processing engine (e.g., Google Cloud Natural Language API), and a sentiment analysis library (e.g., NVIDIA DeepStream SDK). This allows the server to effectively organize information and provide it in a way that meets the user's needs.

[0367] For example, if a user is feeling stressed after a trip, the server might recommend a playlist containing relaxing music that they previously enjoyed. In this way, personalized information tailored to the user's emotions is provided.

[0368] An example of a prompt would be, "When a user is looking for music to relax after a delayed flight, how would you create a playlist that includes jazz artists they have liked in the past?" Based on such prompts, a generative AI model can provide the most suitable suggestions to the user.

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] The server collects information from information sources. These sources include specific websites and social media platforms, and the server retrieves data from these sources based on preset keywords. The input is the URL or API key of the information source, and the output is the retrieved raw data.

[0372] Step 2:

[0373] The server analyzes the acquired raw data using natural language processing techniques. Specifically, the server converts the data into text, classifies it by topic using a word processing engine, and performs sentiment evaluation. The input is raw data, and the output is classified and sentiment-evaluated data.

[0374] Step 3:

[0375] The server uses an emotion engine to recognize the user's emotional state. Based on past feedback and behavioral history, the server updates the user's emotional profile. The input is the user's historical data and analyzed data, and the output is the updated emotional profile.

[0376] Step 4:

[0377] The server selects the most relevant information based on the sentiment profile and generates individually optimized documents. A generative AI model is used to format the document in a way that responds to prompts. The input is the updated sentiment profile and analyzed data, and the output is the optimized document.

[0378] Step 5:

[0379] The server sends the generated document to a terminal with notification capabilities. Using a scheduling function, information can be sent in real time or at a specified time to provide information to the user. Input consists of the optimized document and the user's contact information, while output is the provision of information to the user's terminal.

[0380] 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.

[0381] 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.

[0382] 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.

[0383] [Third Embodiment]

[0384] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0385] 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.

[0386] 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).

[0387] 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.

[0388] 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.

[0389] 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).

[0390] 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.

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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".

[0396] This invention is implemented as a system that automatically collects, analyzes, and reports information to users. The program runs on a server in the cloud and provides information in response to requests from multiple user terminals.

[0397] First, the server periodically retrieves information from pre-registered URLs and SNS APIs. This ensures that the latest industry information is always incorporated into the system. Information is collected in various formats (e.g., text, images, videos), but the system primarily focuses on text data.

[0398] Next, the server analyzes the acquired text data using natural language processing technology. It performs topic classification, sentiment determination, and trend analysis to extract important industry trends. Machine learning algorithms are applied to this analysis, and continuous improvement in accuracy is pursued.

[0399] Once the analysis is complete, the server generates a report based on the analysis results. This report is automatically formatted according to the user's specified format. The report includes text, graphs, tables, and other elements to present the information in an easy-to-understand visual format.

[0400] Subsequently, the server sends the generated report to the user's device according to a pre-configured schedule. This transmission is primarily done via email or team chat applications. This ensures that users always receive the latest industry information.

[0401] Furthermore, the server shares data with other AI agents, allowing them to complement each other's information. This sharing enables more multifaceted information analysis, allowing users to understand the industry situation from multiple perspectives. For example, an AI agent specifically designed for the automotive industry can instantly analyze new car announcements and recall information, providing it as reference material for sales strategies.

[0402] Thus, the present invention is a system that covers everything from automated data collection to analysis and reporting, and provides users with useful industry information quickly.

[0403] The following describes the processing flow.

[0404] Step 1:

[0405] The server accesses registered website URLs and SNS API endpoints to retrieve data according to a periodically scheduled process. The retrieved data undergoes an initial duplicate check before being stored in the database.

[0406] Step 2:

[0407] The server uses a natural language processing (NLP) library to cleanse the text in order to analyze the acquired data. Specifically, it removes unnecessary HTML tags, special characters, and line break codes, formatting the data into a form that is easy to analyze.

[0408] Step 3:

[0409] The server performs topic classification using the cleansed data. Using a topic modeling tool, it extracts key topics from the document set and classifies each article into the corresponding topic.

[0410] Step 4:

[0411] The server then performs sentiment analysis. Using NLP, it determines whether each text expresses a positive, negative, or neutral emotion and assigns an emotional score to each document.

[0412] Step 5:

[0413] The server generates a customized report for the user based on the analysis results. The report provides information in a visually easy-to-understand format, including text summaries, topic summaries, and sentiment analysis results.

[0414] Step 6:

[0415] The server sends the generated reports to the user's terminal according to the schedule and contact method specified by the user. Typically, notifications are sent via email or internal company chat tools to ensure users receive industry information in a timely manner.

[0416] Step 7:

[0417] The server shares data with other AI agents, incorporating additional data and analytical information from each agent to improve the accuracy of the analysis results. This collaboration enhances the diversity and reliability of the information provided to users.

[0418] (Example 1)

[0419] 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."

[0420] In today's information society, a vast amount of information exists on the internet, making it a challenging task to efficiently collect, analyze, and present useful information to users. Furthermore, appropriately analyzing acquired information and reporting it in a way that meets specific needs is crucial, requiring advanced technology and effective systems. Traditional methods have limitations in terms of analytical accuracy and the speed of information delivery, making it difficult for users to obtain the latest and most useful information they require in a timely manner.

[0421] 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.

[0422] In this invention, the server includes a collection means for acquiring information from information sources, a processing means for pre-processing the acquired information, an analysis means for analyzing the information using natural language processing technology, an improvement means for improving the accuracy of the analysis by applying machine learning, a generation means for generating the analysis results as a report, a notification means for notifying the generated report using a communication means, and a sharing means for sharing information among multiple agents. This enables efficient and highly accurate collection and analysis of information, and quick provision of optimal information to users.

[0423] "Collection means" refers to a function that automatically retrieves necessary information from information sources.

[0424] "Processing means" refers to a function that removes unnecessary data from acquired information and converts it into a format that is easy to analyze.

[0425] "Analysis tools" refer to functions that use natural language processing technology to analyze the content of information and perform topic classification and sentiment evaluation.

[0426] "Improvement methods" refer to functions that use machine learning techniques to improve the accuracy of analysis results.

[0427] "Generation means" refers to the function of creating a report based on the results of the analyzed information.

[0428] "Notification method" refers to the function of sending the generated report to the user using a specified communication method.

[0429] A "sharing mechanism" is a function that allows multiple agents to exchange and complement information with each other.

[0430] This invention provides a system for effectively collecting and analyzing information over a network and providing the results to users. The following describes embodiments for carrying out the present invention.

[0431] First, the server continuously retrieves information from pre-registered sources (e.g., URLs of news sites or APIs of social media). This process involves various data formats such as text, images, and videos, but primarily focuses on text data.

[0432] Next, the server preprocesses the acquired data using the Python pandas library. This includes noise reduction and formatting standardization, steps taken to improve the quality of the data.

[0433] The server uses Python's NLTK and Transformers libraries for natural language processing to analyze text data. This allows for topic classification and sentiment analysis, enabling the extraction of important information. Furthermore, the accuracy of the analysis is continuously improved through the use of machine learning techniques. As a specific example, it analyzes opinions on new products in the automotive industry to understand market reactions.

[0434] After the analysis is complete, the server automatically generates a report. This report uses Python's matplotlib library to create graphs and charts, presenting the information to the user in a visually easy-to-understand format. The report is formatted according to the specified format and output as an electronic document.

[0435] The server sends the generated report to the user's device via email or chat application. This communication utilizes the SMTP protocol or specific application APIs. For example, it can be configured to send a report summarizing the latest industry trends every Monday at 9:00 AM.

[0436] Furthermore, the server enriches its information by sharing data with other AI agents. This sharing allows for the integration of analysis results from different perspectives, enabling the provision of diverse information to users.

[0437] Examples of specific prompts include, "Generate a report on the key trends in the automotive industry this week."

[0438] This system allows users to quickly obtain useful information and use it to aid in decision-making.

[0439] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0440] Step 1:

[0441] The server accesses information sources and collects data. URLs of news sites and API keys for social media are used as input. The server uses these inputs to send HTTP requests via the Python requests library and receives raw data in text, image, and video formats as output.

[0442] Step 2:

[0443] The server preprocesses the data obtained in Step 1. The input for preprocessing is the raw data output from Step 1. Specifically, it uses the Python pandas library to remove HTML tags and unnecessary whitespace, and to normalize the text. As a result, clean and consistent text data is output.

[0444] Step 3:

[0445] The server analyzes preprocessed data using natural language processing techniques. It receives clean, preprocessed data as input and utilizes libraries such as NLTK and Transformers to perform topic classification and sentiment analysis. Specifically, it divides text into tokens and calculates trends and sentiment scores. This analysis outputs the data's topics and sentiment ratings as results.

[0446] Step 4:

[0447] The server improves the accuracy of the analysis using machine learning techniques. The analysis results are used as input, and a model is applied using either TensorFlow or scikit-learn. Specifically, this involves inputting data into a pre-trained model and refining its predictions. This results in more accurate analysis results as output.

[0448] Step 5:

[0449] The server generates a report based on the analysis results. The improved analysis results from step 4 are used as input, and data visualization is performed using Python's matplotlib library, followed by formatting based on a report template. Specifically, this includes converting the analysis results into graphs and compiling them into a report document. As a result, a visually organized report is output.

[0450] Step 6:

[0451] The server sends the generated report to the user's device. The generated report and recipient information (email address, chat application API key, etc.) are used as input. The report is sent to the user's device at the specified time using the SMTP protocol or the chat application's API. As a result, the user receives a report containing the latest analysis information.

[0452] Step 7:

[0453] The server shares information with other AI agents. Inputs include analyzed data and inter-agent sharing protocols. In practice, it sends analyzed data via an API and integrates responses from other agents. This process yields multifaceted analytical information as output.

[0454] (Application Example 1)

[0455] 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."

[0456] In today's world, a vast amount of data, often referred to as an information flood, is generated daily. There is a need to extract useful information from this data and deliver it quickly to users. However, traditional methods require considerable time and effort for information selection and report personalization, making it difficult to provide information when users need it. There is a need to solve this problem and efficiently provide information tailored to user needs.

[0457] 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.

[0458] In this invention, the server includes acquisition means for obtaining data from information sources, analysis means for analyzing the acquired data, and personalization means for customizing reports based on the user's interests and past browsing history. This makes it possible to quickly and accurately provide users with individually optimized reports.

[0459] "Information source" refers to the base location or medium from which data is obtained, specifically referring to websites on the internet, APIs, and so on.

[0460] "Means of acquisition" refers to a system for extracting and incorporating necessary data from information sources.

[0461] "Analysis methods" refer to the technologies and algorithms used to analyze acquired data and extract necessary information.

[0462] "Generative means" refers to the process or tools used to compile analyzed information and create a formal report.

[0463] "Communication method" refers to the method used to deliver the generated report to the designated user, and includes methods such as email and chat applications.

[0464] "Sharing methods" refer to a system that allows multiple agents to exchange and effectively utilize data with each other.

[0465] "Personalization methods" refer to techniques for selecting content based on a user's past browsing history and interests, and creating individually optimized reports.

[0466] "Display means" refers to devices or methods for providing a generated report to the user visually, such as displays or head-mounted displays.

[0467] To implement this invention, it is necessary to build a system that integrates information gathering, analysis, report generation, and notification as a series of processes. The server first retrieves the latest data from the information source. Here, information is periodically retrieved from websites and APIs on the internet. It is common to use a library such as requests for this purpose.

[0468] Next, the server analyzes the acquired data. This analysis utilizes natural language processing techniques, such as using the nlp_module library for topic classification and sentiment evaluation. Furthermore, a generative AI model is used to organize the information based on the prompt text and extract information that the user is interested in.

[0469] The generated analysis results are compiled into a report. The server generates the report in a visually easy-to-understand format, such as including graphs and tables. The report is customized taking into account the user's past browsing history and interests.

[0470] The server then notifies the user of the generated report via communication means. Notifications are sent via email or chat applications, and the report is automatically sent at a predetermined time. The report can also be directly displayed on a display device such as a head-mounted display.

[0471] As a concrete example, a service could be envisioned that provides soccer fans with a daily report containing the latest match results and player interviews. An example of a prompt would be, "Please summarize today's soccer news." This invention allows users to quickly and accurately receive individually optimized information.

[0472] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0473] Step 1:

[0474] The server retrieves data from information sources. Specifically, it uses the requests library to send HTTP requests to periodically collect information from websites and APIs. The input is a list of URLs of the information sources, and the output is data in JSON format. The server stores this in a parseable format.

[0475] Step 2:

[0476] The server analyzes the acquired data. Using natural language processing techniques, it performs topic classification and sentiment evaluation of the data using the nlp_module. The input is the acquired JSON data, and the output is analysis results including text data classified by topic and sentiment scores. The server then extracts information that matches the user's interests.

[0477] Step 3:

[0478] The server generates a report based on the analysis results. It uses the `report_generator` module to create a customized report, taking into account the user's past browsing history and interests. The input is the analysis results, and the output is a visually represented report. The server formats the report, including graphs and tables, in a user-friendly format.

[0479] Step 4:

[0480] The server notifies the terminal of the generated report via communication means. The report is automatically sent using email or a chat application. The input is the generated report, and the output is the notification sent to the user's terminal. The server uses a scheduling function to repeat this process at predetermined times.

[0481] Step 5:

[0482] The user views the received report on a display device. The report can be viewed on the terminal's display or a head-mounted display. The input is the received report, and the output is the information displayed on the user's visual display device. Based on this, the user can access the latest information and view content that matches their interests.

[0483] 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.

[0484] This invention combines a system for information gathering, analysis, report generation, and notification with an emotion engine that recognizes user emotions, thereby enabling the provision of information that is more tailored to user needs. This system is implemented by servers running in a cloud or local environment.

[0485] First, the server automatically collects data from information sources. This process utilizes APIs from specific websites and social networking platforms, extracting data based on pre-configured keywords and areas of interest. The information is kept up-to-date through regular updates.

[0486] Next, the server analyzes the acquired data using natural language processing (NLP) techniques. Through NLP, the data is categorized by topic, and the mood of each document is evaluated through sentiment analysis. This analysis result is used to improve the value provided to the user.

[0487] Furthermore, in this invention, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is performed based on the user's past feedback and interaction data, forming a kind of emotional profile. For example, it learns the user's tendencies, such as what kind of news they usually like or what kind of information they avoid when stressed. Based on this profile, the server provides information that corresponds to the user's current emotional state, personalizing the user experience.

[0488] In generating reports, the server integrates analysis results with the user's emotional profile to create individually optimized content. For example, if positive emotions are needed, the report is adjusted to highlight positive news and positive analysis. This report is generated in real time and notified to the device. Notifications are made via email or chat applications, allowing users to access the information immediately.

[0489] For example, if a user prefers financial news, we can support their decision-making by providing the latest information on recent market trends, and if a user is feeling anxious, we can recommend information that helps with risk hedging.

[0490] By incorporating an emotion engine in this way, it becomes possible to provide more personalized and emotionally resonant information, maximizing the value of the information for the user.

[0491] The following describes the processing flow.

[0492] Step 1:

[0493] The server collects data from registered information sources. Specifically, it uses RSS feeds from news sites and APIs from social media to periodically retrieve the latest data related to topics of interest and store it in a database.

[0494] Step 2:

[0495] The server cleanses the acquired data and analyzes it using natural language processing techniques. It removes noise from the text, tokenizes the documents, and then performs topic classification and sentiment analysis. This allows the content and mood of each document to be evaluated.

[0496] Step 3:

[0497] The server updates the user's sentiment profile based on the user's past behavior history and feedback data. It learns what kind of news the user has preferred to read in the past and what kind of information they are currently avoiding, thereby enriching the profile.

[0498] Step 4:

[0499] The server generates a report based on the analysis results and the user's emotional profile. The report incorporates appropriately personalized information, taking into account the user's current emotional state.

[0500] Step 5:

[0501] The server notifies the user's device of the generated report. The report is sent via the user's preferred communication method (e.g., email or chat app), allowing the user to check the information in real time.

[0502] Step 6:

[0503] The server shares data and analysis results with other AI agents. This allows for improved accuracy and diversity of information not only within the company's own system but also across the entire network. Users can then receive broader and more accurate information.

[0504] (Example 2)

[0505] 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."

[0506] In today's information-saturated society, there is a need to provide users with the information they need accurately and in a context-appropriate manner. However, current information delivery systems lack sufficient personalization to respond to users' emotions and needs, making it difficult for users to obtain the necessary information at the right time.

[0507] 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.

[0508] In this invention, the server includes an acquisition means for obtaining data from an information source, an analysis means for analyzing the acquired data using natural language processing technology, performing classification and sentiment evaluation, and a generation means for integrating the analysis results with the user's sentiment profile to generate a report. This enables the provision of personalized information tailored to the user's emotional state and needs. Furthermore, since the content is notified in real time via email or chat applications, users can quickly access the information they need.

[0509] "Acquisition method" refers to a mechanism for automatically retrieving data from an information source.

[0510] "Analysis means" refers to a function that uses natural language processing technology on collected data to classify topics and evaluate sentiment.

[0511] "Generation method" refers to the process of integrating the analyzed data with the user's emotional profile to create a report.

[0512] "Notification method" refers to the use of email or chat applications to communicate generated reports to users in real time.

[0513] "Personalization methods" refer to technologies that analyze a user's past behavioral data to create an emotional profile and then provide personalized information based on that profile.

[0514] A "generative AI model" is an artificial intelligence-based technology used to optimize report content based on prompt text.

[0515] A "prompt" is input text that gives instructions to a generative AI model, causing it to generate desired information or content.

[0516] This invention is a system that provides user-optimized information according to specific emotional states, and is implemented by combining multiple technological elements. The system is mainly composed of servers operating in a cloud environment or local environment, and its functions are as follows:

[0517] The server first has means of acquiring data from information sources. In this process, data is collected from various information sources, such as websites and APIs of social networking platforms. Subsequently, the collected data is analyzed using analytical tools that employ natural language processing (NLP) techniques. In this analysis, the data is classified by topic, and sentiment evaluation is performed using sentiment analysis tools.

[0518] Next, the server generates a report that integrates the analysis results and the user's sentiment profile. In this process, a generation AI model is used to generate optimized information based on the prompt text. For example, if the prompt text "Please report recent market information positively" is entered, the AI ​​model will create a report according to that instruction.

[0519] The generated reports are notified to the device in real time, and users can access them immediately. Data is sent via email or chat applications, and reports are delivered at times specified by the user using a scheduling function.

[0520] For example, if a user prefers technology-related news, this system will collect and analyze information on the latest technological trends and report them in a way that suits the user's interests. Furthermore, when a user is feeling stressed, it will recommend news containing relaxing information and positive content to support the user's decision-making.

[0521] Thus, the present invention is a system that improves the user experience and enables the provision of necessary information at the appropriate time.

[0522] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0523] Step 1:

[0524] The server retrieves data from information sources. Input is a specific URL or endpoint using APIs from websites or social networking platforms, and output is the retrieved raw data. Specifically, it calls APIs according to configured keywords and themes, and stores the retrieved news articles and social networking posts in a database.

[0525] Step 2:

[0526] The server performs analysis on the acquired data using natural language processing techniques. The input is the raw data collected in step 1, and the output is data classified by topic and assigned sentiment scores. Specifically, the analysis tool is used to classify each text into a topic, and a sentiment analysis algorithm is applied to perform sentiment evaluation.

[0527] Step 3:

[0528] The server creates an emotional profile based on the user's past behavioral data. The input is the user's past feedback and behavioral history data, and the output is the user's emotional profile. Specifically, it applies machine learning algorithms to analyze the user's preferences and past selection tendencies.

[0529] Step 4:

[0530] The server generates a report based on the analysis results and the user's sentiment profile. The input is the analysis data from step 2 and the sentiment profile from step 3, and the output is a personalized report. A generative AI model is used to generate prompt sentences, such as "Create a report highlighting positive technology news."

[0531] Step 5:

[0532] The terminal notifies the user of the generated report. The input is the report generated in step 4, and the output is the real-time notification the user receives. Specifically, the report is sent via email or chat application, and the scheduling function is used to set delivery at a specified time.

[0533] (Application Example 2)

[0534] 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."

[0535] In today's various information provision systems, it is difficult to provide optimal information tailored to the individual emotions and interests of users. Therefore, there is a need for a system that understands emotions and provides timely information appropriate to the user. In particular, a flexible response that accommodates information needs that vary depending on stress levels and moods is desirable.

[0536] 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.

[0537] In this invention, the server includes acquisition means for obtaining information from information sources, analysis means for analyzing the acquired information, and emotion recognition means for recognizing the user's emotional state using an emotion engine and selecting information according to that emotional state. This makes it possible to form an emotional profile of the user and provide individually optimized information.

[0538] "Information sources" refer to the sources of information, such as websites and social media platforms on the internet, that are used to obtain data.

[0539] "Acquisition means" refers to the processes and technologies used to collect data from information sources, and includes functions that automatically extract information using APIs, etc.

[0540] "Analysis methods" refer to the means used to analyze acquired data, specifically the process of organizing the data using natural language processing techniques and evaluating the emotional state and topics of the information.

[0541] "Generation means" refers to the process of generating documents based on the results of analysis, and has the function of formatting information into reports or other formats.

[0542] "Notification means" refers to a communication function for sending and receiving generated documents to users, providing information in real time or at a specified time.

[0543] "Emotion recognition means" refers to the process of analyzing a user's emotional state using an emotion engine, selecting data based on the results, and providing appropriate information.

[0544] "Personalization" refers to the process of individually optimizing information and adjusting the content provided based on the user's emotional profile.

[0545] A "knowledge system" refers to an integrated system that acquires, analyzes, and generates information, and provides users with the most relevant information based on their emotional state.

[0546] This invention is a knowledge system for providing information based on the emotional state of users. The server automatically acquires information from information sources and analyzes that information using natural language processing technology. Specifically, it classifies data acquired from websites and social media platforms using a word processing engine and performs sentiment evaluation.

[0547] The emotion engine recognizes the user's current emotional state based on their past behavioral history and feedback data. Based on this recognition, the server selects the most appropriate information and generates it as an individually optimized document. This generated document is delivered to the user in real time or at a specified time via a terminal with notification capabilities.

[0548] The processing utilizes cloud-based servers (e.g., Amazon Web Services), a natural language processing engine (e.g., Google Cloud Natural Language API), and a sentiment analysis library (e.g., NVIDIA DeepStream SDK). This allows the server to effectively organize information and provide it in a way that meets the user's needs.

[0549] For example, if a user is feeling stressed after a trip, the server might recommend a playlist containing relaxing music that they previously enjoyed. In this way, personalized information tailored to the user's emotions is provided.

[0550] An example of a prompt would be, "When a user is looking for music to relax after a delayed flight, how would you create a playlist that includes jazz artists they have liked in the past?" Based on such prompts, a generative AI model can provide the most suitable suggestions to the user.

[0551] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0552] Step 1:

[0553] The server collects information from information sources. These sources include specific websites and social media platforms, and the server retrieves data from these sources based on preset keywords. The input is the URL or API key of the information source, and the output is the retrieved raw data.

[0554] Step 2:

[0555] The server analyzes the acquired raw data using natural language processing techniques. Specifically, the server converts the data into text, classifies it by topic using a word processing engine, and performs sentiment evaluation. The input is raw data, and the output is classified and sentiment-evaluated data.

[0556] Step 3:

[0557] The server uses an emotion engine to recognize the user's emotional state. Based on past feedback and behavioral history, the server updates the user's emotional profile. The input is the user's historical data and analyzed data, and the output is the updated emotional profile.

[0558] Step 4:

[0559] The server selects the most relevant information based on the sentiment profile and generates individually optimized documents. A generative AI model is used to format the document in a way that responds to prompts. The input is the updated sentiment profile and analyzed data, and the output is the optimized document.

[0560] Step 5:

[0561] The server sends the generated document to a terminal with notification capabilities. Using a scheduling function, information can be sent in real time or at a specified time to provide information to the user. Input consists of the optimized document and the user's contact information, while output is the provision of information to the user's terminal.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] [Fourth Embodiment]

[0566] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0567] 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.

[0568] 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).

[0569] 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.

[0570] 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.

[0571] 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).

[0572] 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.

[0573] 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.

[0574] 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.

[0575] 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.

[0576] 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.

[0577] 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.

[0578] 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".

[0579] This invention is implemented as a system that automatically collects, analyzes, and reports information to users. The program runs on a server in the cloud and provides information in response to requests from multiple user terminals.

[0580] First, the server periodically retrieves information from pre-registered URLs and SNS APIs. This ensures that the latest industry information is always incorporated into the system. Information is collected in various formats (e.g., text, images, videos), but the system primarily focuses on text data.

[0581] Next, the server analyzes the acquired text data using natural language processing technology. It performs topic classification, sentiment determination, and trend analysis to extract important industry trends. Machine learning algorithms are applied to this analysis, and continuous improvement in accuracy is pursued.

[0582] Once the analysis is complete, the server generates a report based on the analysis results. This report is automatically formatted according to the user's specified format. The report includes text, graphs, tables, and other elements to present the information in an easy-to-understand visual format.

[0583] Subsequently, the server sends the generated report to the user's device according to a pre-configured schedule. This transmission is primarily done via email or team chat applications. This ensures that users always receive the latest industry information.

[0584] Furthermore, the server shares data with other AI agents, allowing them to complement each other's information. This sharing enables more multifaceted information analysis, allowing users to understand the industry situation from multiple perspectives. For example, an AI agent specifically designed for the automotive industry can instantly analyze new car announcements and recall information, providing it as reference material for sales strategies.

[0585] Thus, the present invention is a system that covers everything from automated data collection to analysis and reporting, and provides users with useful industry information quickly.

[0586] The following describes the processing flow.

[0587] Step 1:

[0588] The server accesses registered website URLs and SNS API endpoints to retrieve data according to a periodically scheduled process. The retrieved data undergoes an initial duplicate check before being stored in the database.

[0589] Step 2:

[0590] The server uses a natural language processing (NLP) library to cleanse the text in order to analyze the acquired data. Specifically, it removes unnecessary HTML tags, special characters, and line break codes, formatting the data into a form that is easy to analyze.

[0591] Step 3:

[0592] The server performs topic classification using the cleansed data. Using a topic modeling tool, it extracts key topics from the document set and classifies each article into the corresponding topic.

[0593] Step 4:

[0594] The server then performs sentiment analysis. Using NLP, it determines whether each text expresses a positive, negative, or neutral emotion and assigns an emotional score to each document.

[0595] Step 5:

[0596] The server generates a customized report for the user based on the analysis results. The report provides information in a visually easy-to-understand format, including text summaries, topic summaries, and sentiment analysis results.

[0597] Step 6:

[0598] The server sends the generated reports to the user's terminal according to the schedule and contact method specified by the user. Typically, notifications are sent via email or internal company chat tools to ensure users receive industry information in a timely manner.

[0599] Step 7:

[0600] The server shares data with other AI agents, incorporating additional data and analytical information from each agent to improve the accuracy of the analysis results. This collaboration enhances the diversity and reliability of the information provided to users.

[0601] (Example 1)

[0602] 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".

[0603] In today's information society, a vast amount of information exists on the internet, making it a challenging task to efficiently collect, analyze, and present useful information to users. Furthermore, appropriately analyzing acquired information and reporting it in a way that meets specific needs is crucial, requiring advanced technology and effective systems. Traditional methods have limitations in terms of analytical accuracy and the speed of information delivery, making it difficult for users to obtain the latest and most useful information they require in a timely manner.

[0604] 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.

[0605] In this invention, the server includes a collection means for acquiring information from information sources, a processing means for pre-processing the acquired information, an analysis means for analyzing the information using natural language processing technology, an improvement means for improving the accuracy of the analysis by applying machine learning, a generation means for generating the analysis results as a report, a notification means for notifying the generated report using a communication means, and a sharing means for sharing information among multiple agents. This enables efficient and highly accurate collection and analysis of information, and quick provision of optimal information to users.

[0606] "Collection means" refers to a function that automatically retrieves necessary information from information sources.

[0607] "Processing means" refers to a function that removes unnecessary data from acquired information and converts it into a format that is easy to analyze.

[0608] "Analysis tools" refer to functions that use natural language processing technology to analyze the content of information and perform topic classification and sentiment evaluation.

[0609] "Improvement methods" refer to functions that use machine learning techniques to improve the accuracy of analysis results.

[0610] "Generation means" refers to the function of creating a report based on the results of the analyzed information.

[0611] "Notification method" refers to the function of sending the generated report to the user using a specified communication method.

[0612] A "sharing mechanism" is a function that allows multiple agents to exchange and complement information with each other.

[0613] This invention provides a system for effectively collecting and analyzing information over a network and providing the results to users. The following describes embodiments for carrying out the present invention.

[0614] First, the server continuously retrieves information from pre-registered sources (e.g., URLs of news sites or APIs of social media). This process involves various data formats such as text, images, and videos, but primarily focuses on text data.

[0615] Next, the server preprocesses the acquired data using the Python pandas library. This includes noise reduction and formatting standardization, steps taken to improve the quality of the data.

[0616] The server uses Python's NLTK and Transformers libraries for natural language processing to analyze text data. This allows for topic classification and sentiment analysis, enabling the extraction of important information. Furthermore, the accuracy of the analysis is continuously improved through the use of machine learning techniques. As a specific example, it analyzes opinions on new products in the automotive industry to understand market reactions.

[0617] After the analysis is complete, the server automatically generates a report. This report uses Python's matplotlib library to create graphs and charts, presenting the information to the user in a visually easy-to-understand format. The report is formatted according to the specified format and output as an electronic document.

[0618] The server sends the generated report to the user's device via email or chat application. This communication utilizes the SMTP protocol or specific application APIs. For example, it can be configured to send a report summarizing the latest industry trends every Monday at 9:00 AM.

[0619] Furthermore, the server enriches its information by sharing data with other AI agents. This sharing allows for the integration of analysis results from different perspectives, enabling the provision of diverse information to users.

[0620] Examples of specific prompts include, "Generate a report on the key trends in the automotive industry this week."

[0621] This system allows users to quickly obtain useful information and use it to aid in decision-making.

[0622] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0623] Step 1:

[0624] The server accesses information sources and collects data. URLs of news sites and API keys for social media are used as input. The server uses these inputs to send HTTP requests via the Python requests library and receives raw data in text, image, and video formats as output.

[0625] Step 2:

[0626] The server preprocesses the data obtained in Step 1. The input for preprocessing is the raw data output from Step 1. Specifically, it uses the Python pandas library to remove HTML tags and unnecessary whitespace, and to normalize the text. As a result, clean and consistent text data is output.

[0627] Step 3:

[0628] The server analyzes preprocessed data using natural language processing techniques. It receives clean, preprocessed data as input and utilizes libraries such as NLTK and Transformers to perform topic classification and sentiment analysis. Specifically, it divides text into tokens and calculates trends and sentiment scores. This analysis outputs the data's topics and sentiment ratings as results.

[0629] Step 4:

[0630] The server improves the accuracy of the analysis using machine learning techniques. The analysis results are used as input, and a model is applied using either TensorFlow or scikit-learn. Specifically, this involves inputting data into a pre-trained model and refining its predictions. This results in more accurate analysis results as output.

[0631] Step 5:

[0632] The server generates a report based on the analysis results. The improved analysis results from step 4 are used as input, and data visualization is performed using Python's matplotlib library, followed by formatting based on a report template. Specifically, this includes converting the analysis results into graphs and compiling them into a report document. As a result, a visually organized report is output.

[0633] Step 6:

[0634] The server sends the generated report to the user's device. The generated report and recipient information (email address, chat application API key, etc.) are used as input. The report is sent to the user's device at the specified time using the SMTP protocol or the chat application's API. As a result, the user receives a report containing the latest analysis information.

[0635] Step 7:

[0636] The server shares information with other AI agents. Inputs include analyzed data and inter-agent sharing protocols. In practice, it sends analyzed data via an API and integrates responses from other agents. This process yields multifaceted analytical information as output.

[0637] (Application Example 1)

[0638] 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".

[0639] In today's world, a vast amount of data, often referred to as an information flood, is generated daily. There is a need to extract useful information from this data and deliver it quickly to users. However, traditional methods require considerable time and effort for information selection and report personalization, making it difficult to provide information when users need it. There is a need to solve this problem and efficiently provide information tailored to user needs.

[0640] 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.

[0641] In this invention, the server includes acquisition means for obtaining data from information sources, analysis means for analyzing the acquired data, and personalization means for customizing reports based on the user's interests and past browsing history. This makes it possible to quickly and accurately provide users with individually optimized reports.

[0642] "Information source" refers to the base location or medium from which data is obtained, specifically referring to websites on the internet, APIs, and so on.

[0643] "Means of acquisition" refers to a system for extracting and incorporating necessary data from information sources.

[0644] "Analysis methods" refer to the technologies and algorithms used to analyze acquired data and extract necessary information.

[0645] "Generative means" refers to the process or tools used to compile analyzed information and create a formal report.

[0646] "Communication method" refers to the method used to deliver the generated report to the designated user, and includes methods such as email and chat applications.

[0647] "Sharing methods" refer to a system that allows multiple agents to exchange and effectively utilize data with each other.

[0648] "Personalization methods" refer to techniques for selecting content based on a user's past browsing history and interests, and creating individually optimized reports.

[0649] "Display means" refers to devices or methods for providing a generated report to the user visually, such as displays or head-mounted displays.

[0650] To implement this invention, it is necessary to build a system that integrates information gathering, analysis, report generation, and notification as a series of processes. The server first retrieves the latest data from the information source. Here, information is periodically retrieved from websites and APIs on the internet. It is common to use a library such as requests for this purpose.

[0651] Next, the server analyzes the acquired data. This analysis utilizes natural language processing techniques, such as using the nlp_module library for topic classification and sentiment evaluation. Furthermore, a generative AI model is used to organize the information based on the prompt text and extract information that the user is interested in.

[0652] The generated analysis results are compiled into a report. The server generates the report in a visually easy-to-understand format, such as including graphs and tables. The report is customized taking into account the user's past browsing history and interests.

[0653] The server then notifies the user of the generated report via communication means. Notifications are sent via email or chat applications, and the report is automatically sent at a predetermined time. The report can also be directly displayed on a display device such as a head-mounted display.

[0654] As a concrete example, a service could be envisioned that provides soccer fans with a daily report containing the latest match results and player interviews. An example of a prompt would be, "Please summarize today's soccer news." This invention allows users to quickly and accurately receive individually optimized information.

[0655] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0656] Step 1:

[0657] The server retrieves data from information sources. Specifically, it uses the requests library to send HTTP requests to periodically collect information from websites and APIs. The input is a list of URLs of the information sources, and the output is data in JSON format. The server stores this in a parseable format.

[0658] Step 2:

[0659] The server analyzes the acquired data. Using natural language processing techniques, it performs topic classification and sentiment evaluation of the data using the nlp_module. The input is the acquired JSON data, and the output is analysis results including text data classified by topic and sentiment scores. The server then extracts information that matches the user's interests.

[0660] Step 3:

[0661] The server generates a report based on the analysis results. It uses the `report_generator` module to create a customized report, taking into account the user's past browsing history and interests. The input is the analysis results, and the output is a visually represented report. The server formats the report, including graphs and tables, in a user-friendly format.

[0662] Step 4:

[0663] The server notifies the terminal of the generated report via communication means. The report is automatically sent using email or a chat application. The input is the generated report, and the output is the notification sent to the user's terminal. The server uses a scheduling function to repeat this process at predetermined times.

[0664] Step 5:

[0665] The user views the received report on a display device. The report can be viewed on the terminal's display or a head-mounted display. The input is the received report, and the output is the information displayed on the user's visual display device. Based on this, the user can access the latest information and view content that matches their interests.

[0666] 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.

[0667] This invention combines a system for information gathering, analysis, report generation, and notification with an emotion engine that recognizes user emotions, thereby enabling the provision of information that is more tailored to user needs. This system is implemented by servers running in a cloud or local environment.

[0668] First, the server automatically collects data from information sources. This process utilizes APIs from specific websites and social networking platforms, extracting data based on pre-configured keywords and areas of interest. The information is kept up-to-date through regular updates.

[0669] Next, the server analyzes the acquired data using natural language processing (NLP) techniques. Through NLP, the data is categorized by topic, and the mood of each document is evaluated through sentiment analysis. This analysis result is used to improve the value provided to the user.

[0670] Furthermore, in this invention, the server uses an emotion engine to recognize the user's emotional state. This emotion recognition is performed based on the user's past feedback and interaction data, forming a kind of emotional profile. For example, it learns the user's tendencies, such as what kind of news they usually like or what kind of information they avoid when stressed. Based on this profile, the server provides information that corresponds to the user's current emotional state, personalizing the user experience.

[0671] In generating reports, the server integrates analysis results with the user's emotional profile to create individually optimized content. For example, if positive emotions are needed, the report is adjusted to highlight positive news and positive analysis. This report is generated in real time and notified to the device. Notifications are made via email or chat applications, allowing users to access the information immediately.

[0672] For example, if a user prefers financial news, we can support their decision-making by providing the latest information on recent market trends, and if a user is feeling anxious, we can recommend information that helps with risk hedging.

[0673] By incorporating an emotion engine in this way, it becomes possible to provide more personalized and emotionally resonant information, maximizing the value of the information for the user.

[0674] The following describes the processing flow.

[0675] Step 1:

[0676] The server collects data from registered information sources. Specifically, it uses RSS feeds from news sites and APIs from social media to periodically retrieve the latest data related to topics of interest and store it in a database.

[0677] Step 2:

[0678] The server cleanses the acquired data and analyzes it using natural language processing techniques. It removes noise from the text, tokenizes the documents, and then performs topic classification and sentiment analysis. This allows the content and mood of each document to be evaluated.

[0679] Step 3:

[0680] The server updates the user's sentiment profile based on the user's past behavior history and feedback data. It learns what kind of news the user has preferred to read in the past and what kind of information they are currently avoiding, thereby enriching the profile.

[0681] Step 4:

[0682] The server generates a report based on the analysis results and the user's emotional profile. The report incorporates appropriately personalized information, taking into account the user's current emotional state.

[0683] Step 5:

[0684] The server notifies the user's device of the generated report. The report is sent via the user's preferred communication method (e.g., email or chat app), allowing the user to check the information in real time.

[0685] Step 6:

[0686] The server shares data and analysis results with other AI agents. This allows for improved accuracy and diversity of information not only within the company's own system but also across the entire network. Users can then receive broader and more accurate information.

[0687] (Example 2)

[0688] 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".

[0689] In today's information-saturated society, there is a need to provide users with the information they need accurately and in a context-appropriate manner. However, current information delivery systems lack sufficient personalization to respond to users' emotions and needs, making it difficult for users to obtain the necessary information at the right time.

[0690] 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.

[0691] In this invention, the server includes an acquisition means for obtaining data from an information source, an analysis means for analyzing the acquired data using natural language processing technology, performing classification and sentiment evaluation, and a generation means for integrating the analysis results with the user's sentiment profile to generate a report. This enables the provision of personalized information tailored to the user's emotional state and needs. Furthermore, since the content is notified in real time via email or chat applications, users can quickly access the information they need.

[0692] "Acquisition method" refers to a mechanism for automatically retrieving data from an information source.

[0693] "Analysis means" refers to a function that uses natural language processing technology on collected data to classify topics and evaluate sentiment.

[0694] "Generation method" refers to the process of integrating the analyzed data with the user's emotional profile to create a report.

[0695] "Notification method" refers to the use of email or chat applications to communicate generated reports to users in real time.

[0696] "Personalization methods" refer to technologies that analyze a user's past behavioral data to create an emotional profile and then provide personalized information based on that profile.

[0697] A "generative AI model" is an artificial intelligence-based technology used to optimize report content based on prompt text.

[0698] A "prompt" is input text that gives instructions to a generative AI model, causing it to generate desired information or content.

[0699] This invention is a system that provides user-optimized information according to specific emotional states, and is implemented by combining multiple technological elements. The system is mainly composed of servers operating in a cloud environment or local environment, and its functions are as follows:

[0700] The server first has means of acquiring data from information sources. In this process, data is collected from various information sources, such as websites and APIs of social networking platforms. Subsequently, the collected data is analyzed using analytical tools that employ natural language processing (NLP) techniques. In this analysis, the data is classified by topic, and sentiment evaluation is performed using sentiment analysis tools.

[0701] Next, the server generates a report that integrates the analysis results and the user's sentiment profile. In this process, a generation AI model is used to generate optimized information based on the prompt text. For example, if the prompt text "Please report recent market information positively" is entered, the AI ​​model will create a report according to that instruction.

[0702] The generated reports are notified to the device in real time, and users can access them immediately. Data is sent via email or chat applications, and reports are delivered at times specified by the user using a scheduling function.

[0703] For example, if a user prefers technology-related news, this system will collect and analyze information on the latest technological trends and report them in a way that suits the user's interests. Furthermore, when a user is feeling stressed, it will recommend news containing relaxing information and positive content to support the user's decision-making.

[0704] Thus, the present invention is a system that improves the user experience and enables the provision of necessary information at the appropriate time.

[0705] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0706] Step 1:

[0707] The server retrieves data from information sources. Input is a specific URL or endpoint using APIs from websites or social networking platforms, and output is the retrieved raw data. Specifically, it calls APIs according to configured keywords and themes, and stores the retrieved news articles and social networking posts in a database.

[0708] Step 2:

[0709] The server performs analysis on the acquired data using natural language processing techniques. The input is the raw data collected in step 1, and the output is data classified by topic and assigned sentiment scores. Specifically, the analysis tool is used to classify each text into a topic, and a sentiment analysis algorithm is applied to perform sentiment evaluation.

[0710] Step 3:

[0711] The server creates an emotional profile based on the user's past behavioral data. The input is the user's past feedback and behavioral history data, and the output is the user's emotional profile. Specifically, it applies machine learning algorithms to analyze the user's preferences and past selection tendencies.

[0712] Step 4:

[0713] The server generates a report based on the analysis results and the user's sentiment profile. The input is the analysis data from step 2 and the sentiment profile from step 3, and the output is a personalized report. A generative AI model is used to generate prompt sentences, such as "Create a report highlighting positive technology news."

[0714] Step 5:

[0715] The terminal notifies the user of the generated report. The input is the report generated in step 4, and the output is the real-time notification the user receives. Specifically, the report is sent via email or chat application, and the scheduling function is used to set delivery at a specified time.

[0716] (Application Example 2)

[0717] 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".

[0718] In today's various information provision systems, it is difficult to provide optimal information tailored to the individual emotions and interests of users. Therefore, there is a need for a system that understands emotions and provides timely information appropriate to the user. In particular, a flexible response that accommodates information needs that vary depending on stress levels and moods is desirable.

[0719] 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.

[0720] In this invention, the server includes acquisition means for obtaining information from information sources, analysis means for analyzing the acquired information, and emotion recognition means for recognizing the user's emotional state using an emotion engine and selecting information according to that emotional state. This makes it possible to form an emotional profile of the user and provide individually optimized information.

[0721] "Information sources" refer to the sources of information, such as websites and social media platforms on the internet, that are used to obtain data.

[0722] "Acquisition means" refers to the processes and technologies used to collect data from information sources, and includes functions that automatically extract information using APIs, etc.

[0723] "Analysis methods" refer to the means used to analyze acquired data, specifically the process of organizing the data using natural language processing techniques and evaluating the emotional state and topics of the information.

[0724] "Generation means" refers to the process of generating documents based on the results of analysis, and has the function of formatting information into reports or other formats.

[0725] "Notification means" refers to a communication function for sending and receiving generated documents to users, providing information in real time or at a specified time.

[0726] "Emotion recognition means" refers to the process of analyzing a user's emotional state using an emotion engine, selecting data based on the results, and providing appropriate information.

[0727] "Personalization" refers to the process of individually optimizing information and adjusting the content provided based on the user's emotional profile.

[0728] A "knowledge system" refers to an integrated system that acquires, analyzes, and generates information, and provides users with the most relevant information based on their emotional state.

[0729] This invention is a knowledge system for providing information based on the emotional state of users. The server automatically acquires information from information sources and analyzes that information using natural language processing technology. Specifically, it classifies data acquired from websites and social media platforms using a word processing engine and performs sentiment evaluation.

[0730] The emotion engine recognizes the user's current emotional state based on their past behavioral history and feedback data. Based on this recognition, the server selects the most appropriate information and generates it as an individually optimized document. This generated document is delivered to the user in real time or at a specified time via a terminal with notification capabilities.

[0731] The processing utilizes cloud-based servers (e.g., Amazon Web Services), a natural language processing engine (e.g., Google Cloud Natural Language API), and a sentiment analysis library (e.g., NVIDIA DeepStream SDK). This allows the server to effectively organize information and provide it in a way that meets the user's needs.

[0732] For example, if a user is feeling stressed after a trip, the server might recommend a playlist containing relaxing music that they previously enjoyed. In this way, personalized information tailored to the user's emotions is provided.

[0733] An example of a prompt would be, "When a user is looking for music to relax after a delayed flight, how would you create a playlist that includes jazz artists they have liked in the past?" Based on such prompts, a generative AI model can provide the most suitable suggestions to the user.

[0734] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0735] Step 1:

[0736] The server collects information from information sources. These sources include specific websites and social media platforms, and the server retrieves data from these sources based on preset keywords. The input is the URL or API key of the information source, and the output is the retrieved raw data.

[0737] Step 2:

[0738] The server analyzes the acquired raw data using natural language processing techniques. Specifically, the server converts the data into text, classifies it by topic using a word processing engine, and performs sentiment evaluation. The input is raw data, and the output is classified and sentiment-evaluated data.

[0739] Step 3:

[0740] The server uses an emotion engine to recognize the user's emotional state. Based on past feedback and behavioral history, the server updates the user's emotional profile. The input is the user's historical data and analyzed data, and the output is the updated emotional profile.

[0741] Step 4:

[0742] The server selects the most relevant information based on the sentiment profile and generates individually optimized documents. A generative AI model is used to format the document in a way that responds to prompts. The input is the updated sentiment profile and analyzed data, and the output is the optimized document.

[0743] Step 5:

[0744] The server sends the generated document to a terminal with notification capabilities. Using a scheduling function, information can be sent in real time or at a specified time to provide information to the user. Input consists of the optimized document and the user's contact information, while output is the provision of information to the user's terminal.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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."

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] The following is further disclosed regarding the embodiments described above.

[0767] (Claim 1)

[0768] A means of obtaining data from an information source,

[0769] An analytical means for analyzing the acquired data,

[0770] A generation means for generating the results of the analysis as a report,

[0771] A notification means for notifying the generated report using a communication means,

[0772] A means of sharing data among multiple agents,

[0773] A system that includes this.

[0774] (Claim 2)

[0775] The system according to claim 1, wherein the analysis means performs data classification and sentiment evaluation using natural language processing technology.

[0776] (Claim 3)

[0777] The system according to claim 1, wherein the notification means has a scheduling function for sending a report at a predetermined time.

[0778] "Example 1"

[0779] (Claim 1)

[0780] means of collecting information from information sources,

[0781] Processing means for preprocessing acquired information,

[0782] An analytical means for analyzing information using natural language processing technology,

[0783] A means of improving analysis accuracy by applying machine learning,

[0784] A generation means for generating the results of the analysis as a report,

[0785] A notification means for notifying the generated report using a communication means,

[0786] A means of sharing information among multiple agents,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] The system according to claim 1, wherein the analysis means classifies and sentimentally evaluates information.

[0790] (Claim 3)

[0791] The system according to claim 1, wherein the notification means has a scheduling function for sending a report at a predetermined time.

[0792] "Application Example 1"

[0793] (Claim 1)

[0794] A means of obtaining data from an information source,

[0795] An analytical means for analyzing the acquired data,

[0796] A generation means for generating the results of the analysis as a report,

[0797] A notification means for notifying the generated report using a communication means,

[0798] A means of sharing data among multiple agents,

[0799] Personalization methods that customize reports based on the user's interests and past browsing history,

[0800] A display means for displaying the report on a visual display device,

[0801] A system that includes this.

[0802] (Claim 2)

[0803] The system according to claim 1, wherein the analysis means classifies and evaluates the sentiment of data using natural language processing technology, and organizes information based on prompt sentences generated using a generative AI model.

[0804] (Claim 3)

[0805] The system according to claim 1, wherein the notification means has a scheduling function for sending reports at a predetermined time and a function for directly notifying a visual display device.

[0806] "Example 2 of combining an emotion engine"

[0807] (Claim 1)

[0808] A means of obtaining data from an information source,

[0809] An analysis means that analyzes acquired data using natural language processing technology and performs classification and sentiment evaluation,

[0810] A generation method that integrates the analysis results and the user's emotional profile to generate a report,

[0811] A notification means that notifies the generated report in real time using a communication means,

[0812] A personalization method that forms an emotional profile based on the user's past behavioral data and individualizes the information provided,

[0813] A system that includes this.

[0814] (Claim 2)

[0815] The system according to claim 1, further comprising a scheduling function for sending generated reports at a predetermined time.

[0816] (Claim 3)

[0817] The system according to claim 1, further comprising a generation means for generating prompt sentences using a generation AI model and optimizing the report content.

[0818] "Application example 2 when combining with an emotional engine"

[0819] (Claim 1)

[0820] Means of obtaining information from information sources,

[0821] Analytical means for analyzing acquired information,

[0822] A generation means for generating the results of the analysis as a document,

[0823] A notification means for notifying the generated document using communication technology,

[0824] An emotion recognition means that uses an emotion engine to recognize the user's emotional state and selects information according to that emotional state,

[0825] Personalization methods that adjust the content of documents to be individually optimized,

[0826] A knowledge system that includes this.

[0827] (Claim 2)

[0828] The knowledge system according to claim 1, wherein the analysis means classifies and sentimentally evaluates information using word processing technology to form a user's emotional profile.

[0829] (Claim 3)

[0830] The knowledge system according to claim 1, wherein the notification means has a function to transmit a document in real time that is appropriate to the user's current emotional state. [Explanation of symbols]

[0831] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining data from an information source, An analytical means for analyzing the acquired data, A generation means for generating the results of the analysis as a report, A notification means for notifying the generated report using a communication means, A means of sharing data among multiple agents, A system that includes this.

2. The system according to claim 1, wherein the analysis means classifies and evaluates the sentiment of data using natural language processing technology.

3. The system according to claim 1, wherein the notification means has a scheduling function for sending a report at a predetermined time.

Images