system

Abstract

We provide the system. [Solution] A means for receiving requests entered by the user, Means for collecting data based on received requests, Means for analyzing the collected data, A means of converting analysis results into answers using generative artificial intelligence, Methods for formatting answers into a template, A means of providing users with formatted templates, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to the description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In many fields, there is a lack of means for automatically acquiring, analyzing the information and data required by users, and generating a specific action plan based on the results. In particular, the process of extracting the necessary information from a large amount of data and formatting it into a form that can be utilized by users in their work is complex and requires specialized knowledge. Therefore, there is a need for a high-precision information providing system that can be easily handled by general users.

Means for Solving the Problems

[0005] The present invention is a system that includes means for receiving requests input by a user and collecting data based on the received requests, means for analyzing the collected data, means for converting the analysis results into answers using generative artificial intelligence, means for formatting the answers into a template format, and means for providing the formatted template to the user. Specifically, by utilizing the internet and an internal database for data collection and applying machine learning algorithms for analysis, it enables highly accurate and rapid responses to user requests. As a result, users can easily obtain the necessary information without specialized knowledge and use it in a way that is directly applicable to their work.

[0006] A "user" is an individual or group that uses the system and is the entity that performs the input.

[0007] A "request" is the information that a user is asked to input into the system, and it is expressed in the form of a search key or a question.

[0008] "Receiving" refers to the action or process by which a system obtains a request from a user.

[0009] "Data" refers to a collection of information related to user requests, gathered from the internet and internal databases.

[0010] "To collect" refers to the action or process of gathering necessary information from various data sources.

[0011] "Analyzing" refers to the action or process of using machine learning algorithms or other analytical methods on collected data to extract useful information that addresses user requirements.

[0012] "Generative artificial intelligence" is an artificial intelligence technology that generates information in natural language based on input data and analysis results.

[0013] "Answer" refers to the informational response to a user's request, generated using generative artificial intelligence.

[0014] "Formatting" refers to the action or process of transforming a generated response into a user-friendly format (for example, a template format).

[0015] A "template format" is a standardized format for displaying information in a specific structure, and includes elements such as headings and bullet points.

[0016] "To provide" refers to the action or process by which a system sends a formatted template to a user, making it accessible.

[0017] The "Internet" is a vast network connecting computer networks worldwide and is a major data source for information gathering.

[0018] An "internal database" is a collection of information held within an organization and is a data source that can be directly accessed from the system.

[0019] A "machine learning algorithm" is a mathematical model or method for automatically learning patterns and relationships from data. [Brief explanation of the drawing]

[0020] [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]It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0021] <s Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0022] First, the language used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] 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."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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".

[0041] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. This system automatically performs a series of processes, from receiving user requests to collecting, analyzing, and generating responses, and then providing formatted templates.

[0042] 1. System Program

[0043] User request input and reception

[0044] The user enters search terms such as "latest treatments for heart disease" using their device.

[0045] The terminal transmits requests to the system by sending user input to the server.

[0046] Data collection

[0047] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[0048] For example, in the medical field, this would involve gathering the latest research papers, research data, and clinical trial results.

[0049] Data Analysis

[0050] The server analyzes the collected data. This analysis utilizes machine learning algorithms (such as clustering and regression analysis).

[0051] For example, we can extract important keywords and trends related to "the latest treatments for heart disease."

[0052] Answer generation using generative artificial intelligence

[0053] The server uses generative artificial intelligence (for example, AI using natural language processing technology) based on the analysis results to generate specific answers.

[0054] For example, it can automatically generate detailed text about "the latest treatments for heart disease."

[0055] Template formatting

[0056] The server formats the generated text into a user-friendly template format.

[0057] For example, if you are creating a report, it should be structured as follows:

[0058] Title: The Latest Treatments for Heart Disease

[0059] Introduction

[0060] Treatment Overview

[0061] Results of clinical trials

[0062] Precautions and side effects

[0063] summary

[0064] Providing results

[0065] The server sends the formatted template to the user's terminal.

[0066] Users download templates sent from their devices and use them in their work.

[0067] Specific example

[0068] For example, consider the medical field:

[0069] The user enters a request stating, "I want to know about the latest diabetes treatments."

[0070] The terminal sends this request to the server.

[0071] The server collects relevant information from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[0072] The server analyzes the collected data using machine learning algorithms to identify important information.

[0073] The server inputs the analysis results into a generative artificial intelligence system, which then generates a detailed report on the "latest diabetes treatments."

[0074] The server formats the report into a template, including headings, figures, tables, bullet points, etc.

[0075] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[0076] Thus, the present invention is a system that processes user requests quickly and accurately, and provides information directly relevant to practical work. Users can easily obtain and utilize the necessary information even without specialized knowledge.

[0077] The following describes the processing flow.

[0078] Step 1:

[0079] The user enters the search key "latest treatments for heart disease" through their device. This allows the user's request to be collected in a specific format.

[0080] Step 2:

[0081] The terminal sends the user's input request to the server via the network. During this process, the system recognizes the user's request.

[0082] Step 3:

[0083] The server analyzes the received request and generates search queries to collect relevant data based on the request. This enables accurate data collection.

[0084] Step 4:

[0085] The server collects relevant data from publicly available databases on the internet and from internal databases. For example, it retrieves the latest medical papers and clinical trial data.

[0086] Step 5:

[0087] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[0088] Step 6:

[0089] The server inputs preprocessed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis and extract knowledge patterns related to user requests.

[0090] Step 7:

[0091] The server inputs the analysis results into a generative artificial intelligence (e.g., natural language processing AI) to generate response text that meets the user's request. For example, it might create detailed text about "the latest treatments for heart disease."

[0092] Step 8:

[0093] The server formats the generated text into a template. Specifically, it adds headings, bullet points, and, if necessary, figures and tables.

[0094] Step 9:

[0095] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[0096] Step 10:

[0097] Users download templates from their devices and use them in their daily work. For example, they might use the provided reports in treatment plan meetings at a medical institution.

[0098] (Example 1)

[0099] 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."

[0100] Conventional information retrieval systems often fail to respond quickly to user requests, and the information provided frequently does not meet the user's specific needs. In particular, the process of generating useful information using big data is complex and requires specialized knowledge, making it difficult for the average user to utilize. Furthermore, there is a need for more efficient methods for pre-processing and analyzing collected data, as well as for formatting the generated information.

[0101] 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.

[0102] In this invention, the server includes means for receiving requests entered by a user, means for collecting relevant data from a database based on the received requests, means for preprocessing the collected data, means for analyzing the preprocessed data with a machine learning algorithm, means for inputting the analysis results into a generating AI model to generate an answer, means for formatting the generated answer into a template format, and means for providing the formatted template to the user. This enables a system that can respond quickly and accurately to user requests and allows users to easily obtain useful information even without specialized knowledge.

[0103] "Means of receiving requests entered by the user" refers to the function by which the server receives requests such as search keys and questions entered by the user through a terminal.

[0104] "Means of collecting relevant data from a database based on received requests" refers to a function in which a server automatically collects relevant information from publicly available databases on the internet or internal databases in response to user requests.

[0105] "Means for pre-processing collected data" refers to the function of the server that performs pre-processing on the collected data, such as cleansing, format conversion, and noise reduction.

[0106] "Means of analyzing pre-processed data with machine learning algorithms" refers to the function of a server that analyzes pre-processed data using machine learning algorithms (for example, clustering or regression analysis).

[0107] "A means of inputting analysis results into a generative AI model to generate answers" refers to a function in which a server automatically generates specific answers using a generative AI model (for example, an AI using natural language processing technology) based on the results analyzed by a machine learning algorithm.

[0108] "Means of formatting generated responses into a template format" refers to a function that allows the server to convert generated responses into a user-friendly template format (for example, a report format).

[0109] "Means of providing formatted templates to users" refers to a function in which the server sends formatted templates to the user's terminal, allowing the user to download and use them.

[0110] "Means of using the internet and internal databases in data collection" refers to the function of obtaining information by using publicly available databases on the internet or dedicated internal databases during the data collection process.

[0111] "Means for creating prompt statements when inputting analysis results into a generating AI model" refers to a function that constructs prompt statements based on analysis results in order to obtain appropriate output from the generating AI model.

[0112] This invention describes a specific embodiment of a system for automating complex information retrieval and analysis processes and providing useful information in response to user requests. This system uses various hardware and software to automatically execute a series of processes from request reception to result provision.

[0113] System Configuration

[0114] This system mainly consists of the following hardware and software:

[0115] Server: Possesses high-performance data collection, analysis, generation, and formatting capabilities.

[0116] Terminal: A device used by a user to input information (e.g., a personal computer, a smartphone).

[0117] Generative AI model: An AI that generates answers using natural language processing technology (e.g., GPT-3(registered trademark)).

[0118] Databases: Publicly accessible databases on the internet and internal databases.

[0119] Process details

[0120] User request input and reception

[0121] The user enters a search key through their device's browser or a dedicated application. For example, they might enter "latest treatments for heart disease." The device sends this request to the server, which then communicates the request to the entire system.

[0122] Data collection

[0123] After receiving a user request, the server collects the relevant data. This collection utilizes publicly available internet databases (e.g., PubMed) and internal databases.

[0124] Data preprocessing

[0125] The server preprocesses the collected data. This preprocessing includes data cleansing, format conversion, and noise reduction.

[0126] Data analysis

[0127] The server performs analysis on the pre-processed data using machine learning algorithms (e.g., clustering, regression analysis). Through this analysis, important keywords and trends are extracted.

[0128] Answer generation using generative artificial intelligence

[0129] The server generates a prompt based on the analysis results and inputs it into the AI ​​model to generate an answer. For example, the prompt might look like this:

[0130] "Provide the latest treatments for heart disease based on these key findings: ..."

[0131] Template formatting

[0132] The generated responses are formatted by the server into a template. This template is in a user-friendly format for reports and presentations. For example, the template format may look like this:

[0133] Title: The Latest Treatments for Heart Disease

[0134] Introduction

[0135] Treatment Overview

[0136] Results of clinical trials

[0137] Precautions and side effects

[0138] summary

[0139] Providing results

[0140] The formatted template is sent from the server to the user's terminal. The user can download this template and use it in their work.

[0141] Specific example

[0142] For example, in the medical field, a user might input a request such as "I want to know about the latest diabetes treatments," and their device sends this request to a server. The server uses the internet and internal databases to collect relevant information and preprocess the data. Using the preprocessed data, it performs analysis using machine learning algorithms and inputs prompts into a generative AI model to generate an answer. The generated answer is formatted into a template and sent to the user's device. The user downloads the template and uses it in their daily work in the medical field.

[0143] Through the above process, the system of the present invention can provide users with information quickly and with high accuracy.

[0144] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0145] Step 1:

[0146] The user enters a search term on their device. For example, they might type "latest treatments for heart disease."

[0147] The terminal receives user input and sends that request to the server. The input data is the user's request, and this becomes the basis for the next step.

[0148] Step 2:

[0149] The server receives user requests and collects relevant data from the internet and internal databases. This collected data may include, for example, publicly available papers, research data, and clinical trial results.

[0150] In practice, the server uses an API to query the database. The input is the user's request, and the output is the relevant raw data.

[0151] Step 3:

[0152] The server preprocesses the collected data. This preprocessing includes data cleansing (deduplication and noise reduction), format conversion, and other steps.

[0153] The input is the collected raw data, and the output is pre-processed, clean data. Specifically, the data cleansing is performed using Python code.

[0154] Step 4:

[0155] The server performs analysis using machine learning algorithms based on preprocessed data. For example, it extracts important keywords and trends using clustering methods and regression analysis.

[0156] The input is pre-processed data, and the output is the analysis result. Specifically, the analysis is performed using libraries such as scikit-learn.

[0157] Step 5:

[0158] The server generates prompt sentences based on the analysis results and inputs them into a generative AI model to generate an answer. Here, for example, an AI (generative AI model) using natural language processing technology is used.

[0159] The input is the analysis result, which is the prompt text to be input into the generating AI model. The output is the generated detailed answer. Examples of specific prompt texts are as follows:

[0160] "Provide the latest treatments for heart disease based on these key findings: ..."

[0161] Step 6:

[0162] The server formats the generated responses into a template format. This is the process of converting them into a user-friendly format for reports and presentation materials.

[0163] The input is the response from a generative AI model, and the output is a document formatted in a template. Examples of specific template formats are as follows:

[0164] Title: The Latest Treatments for Heart Disease

[0165] Introduction

[0166] Treatment Overview

[0167] Results of clinical trials

[0168] Precautions and side effects

[0169] summary

[0170] Step 7:

[0171] The server sends the formatted template to the user's terminal.

[0172] The input is a document formatted into a template, and the output is a formatted template sent to the user's terminal.

[0173] Users can download formatted templates on their devices and use them in their work.

[0174] (Application Example 1)

[0175] 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."

[0176] In today's information society, it is becoming increasingly important for users to access the latest and most useful information. Information regarding electronic payment services, in particular, is evolving rapidly, requiring users to accurately understand trends, convenience, and points to be aware of. However, traditional information gathering methods require users to manually search and analyze large amounts of data, which is time-consuming and laborious, and the reliability of the information is inconsistent. Therefore, there is a need for more efficient information delivery methods.

[0177] 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.

[0178] In this invention, the server includes means for receiving requests entered by a user, means for collecting data based on the received requests, means for analyzing the collected data, means for converting the analysis results into answers using generative artificial intelligence, means for formatting the answers into a template format, means for providing the formatted template to the user, means for receiving user input and sending it to a server on the cloud, and means for using natural language processing technology for analyzing the collected data. This makes it possible for users to efficiently and accurately obtain the latest trend information on electronic payments even without specialized knowledge.

[0179] "Means for receiving requests entered by a user" refers to the hardware or software mechanism by which a system receives requests entered by a user to obtain specific information.

[0180] "Means for collecting data based on received requests" refers to a system that automatically collects data corresponding to user requests from the internet or internal databases.

[0181] "Means for analyzing collected data" refers to algorithms and technologies used to analyze collected data and extract necessary information and trends.

[0182] "Means of converting analysis results into answers using generative artificial intelligence" refers to a system that uses generative artificial intelligence (for example, natural language processing technology) to generate actual answers based on the analyzed data.

[0183] "Methods for formatting responses into a template format" refers to methods for converting generated responses into a template format that is easy for users to understand.

[0184] "Means of providing users with formatted templates" refers to a mechanism that transmits formatted information to the user's device, allowing the user to receive and use it.

[0185] "Means of receiving user input and sending it to a server on the cloud" refers to a method of receiving a user's request and sending it to a server on a cloud service.

[0186] "Methods for using natural language processing technology in the analysis of collected data" refers to techniques that use natural language processing technology to automatically extract important information when analyzing collected data.

[0187] The system implementing this invention automatically generates and provides useful information using big data in response to user requests. This system is broadly composed of the following hardware and software elements.

[0188] 1. Hardware and software used

[0189] hardware

[0190] User terminal: A device that can connect to the internet, such as a smartphone or smart glasses, is used.

[0191] Cloud server: A server is required for data collection, analysis, and provision of generated information.

[0192] software

[0193] Flask: Used as an API server on a cloud server.

[0194] Generative AI: Specifically, generative AI models that utilize natural language processing technologies such as OpenAI® GPT-3 are used.

[0195] 2. Data Processing and Data Calculation Flow

[0196] Receiving user input

[0197] The user uses a smartphone or smart glasses to input a request for specific information. For example, they might input, "Tell me about the latest cashless payment trends." The user's device sends this request to the cloud server.

[0198] Data collection

[0199] The server collects relevant information from the internet and internal databases based on the received request. This collected data includes the latest news, reports, articles, and user reviews.

[0200] Data analysis

[0201] The server automatically analyzes the collected data using natural language processing technology. This analysis extracts important keywords and trends related to the requests.

[0202] Generating an answer

[0203] Using generative artificial intelligence (GPT-3), specific answers are generated based on the analyzed data. The generated answers are presented in a format that is easy for the user to understand.

[0204] Template formatting

[0205] The server formats the generated responses into a user-friendly template. For example, it might be structured as follows:

[0206] Title: Latest Cashless Payment Trends

[0207] Introduction

[0208] Overview of payment methods

[0209] Details and convenience of each method

[0210] Points to note

[0211] summary

[0212] Providing results

[0213] The server sends a formatted template to the user's terminal, and the user receives and views this information.

[0214] Examples of specific cases and prompt statements

[0215] For example, suppose a user types "Tell me the latest cashless payment trends" into their smartphone. This request is immediately sent to a cloud server, where it undergoes automated analysis and AI generation to produce a detailed and structured report. The user can then receive the information directly in report format.

[0216] Example of a prompt

[0217] "Please tell me about the latest cashless payment trends. Include key points, trends, convenience, and points to note."

[0218] This prompt allows generative artificial intelligence to automatically generate detailed answers, enabling it to respond quickly and accurately to the information the user is seeking.

[0219] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0220] Step 1:

[0221] The user inputs specific information using a smartphone or smart glasses. For example, they might input a request such as, "Tell me about the latest cashless payment trends." The input request is then sent from the device to a server in the cloud.

[0222] Input: User request (e.g., "Tell me about the latest cashless payment trends")

[0223] Output: Request data sent to the cloud server

[0224] Step 2:

[0225] The server receives requests sent by users. Based on the received requests, it collects relevant data. The server collects relevant information from publicly available databases on the internet and from its own internal databases. This includes, for example, the latest news, reports, papers, and user reviews.

[0226] Input: Request data sent to the cloud server

[0227] Output: Collected data (latest news, reports, papers, user reviews, etc.)

[0228] Step 3:

[0229] The server analyzes the collected data. This analysis utilizes natural language processing techniques, including keyword extraction and trend analysis.

[0230] Input: Collected data

[0231] Output: Analysis results (extraction of important keywords and trends)

[0232] Step 4:

[0233] The server generates specific answers using generative artificial intelligence (such as GPT-3) based on the analysis results. A prompt (e.g., "Tell me about the latest cashless payment trends") is input to the generative AI model to obtain a detailed response.

[0234] Input: Analysis result, prompt message

[0235] Output: Generated answer text

[0236] Step 5:

[0237] The server formats the generated response text into a user-friendly template. For example, it might be structured as follows: Title, Introduction, Overview of Payment Methods, Details and Convenience of Each Method, Points to Note, Summary.

[0238] Input: Generated response text

[0239] Output: Answer text formatted in template format

[0240] Step 6:

[0241] The server provides a formatted template to the user's terminal. The terminal receives the template, and the user views the results on their smartphone or smart glasses.

[0242] Input: Answer text formatted in template format

[0243] Output: Sending to the user's terminal, allowing the user to view the results.

[0244] 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.

[0245] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. In particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to provide even more accurate information. This system automatically performs a series of processes, from receiving the user's request to collecting and analyzing the necessary data, generating the response, formatting it, and providing an emotion-conscious template.

[0246] 1. System Program

[0247] User request input and reception

[0248] The user enters their emotional state (e.g., nervous, relieved, excited) along with the search keyword "latest treatments for heart disease" via their device. Emotions can also be automatically collected through facial recognition or voice analysis.

[0249] The terminal transmits the user's input requests and emotional data to the server via the network.

[0250] Data collection

[0251] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[0252] For example, obtaining the latest medical papers and clinical trial data.

[0253] Data analysis

[0254] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[0255] The server inputs pre-processed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis. It extracts knowledge patterns related to user requests.

[0256] Emotional analysis using an emotion engine

[0257] The server uses the user's emotional data to input into the emotion engine, which then analyzes the emotional state.

[0258] For example, if a user is feeling anxious, information to generate a relaxing response should also be considered.

[0259] Answer generation using generative artificial intelligence

[0260] The server uses generative artificial intelligence based on the analysis results and sentiment analysis results to generate specific response text to the user's request.

[0261] For example, it can generate detailed text about "the latest treatments for heart disease" and add content that takes the user's emotions into consideration.

[0262] Template formatting

[0263] The server formats the generated text into a template. It adds headings and descriptions that reflect the user's emotional state.

[0264] For example, include headings, bullet points, charts, and other elements to provide reassuring language and explanations to users.

[0265] Providing results

[0266] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[0267] Users download templates from their devices and use them in their daily work. The provided reports could also be used in treatment plan meetings at medical institutions.

[0268] Specific example

[0269] For example, consider the medical field:

[0270] When a user requests to learn about the latest diabetes treatments, they simultaneously input their emotions at the time of making that request (e.g., anxiety).

[0271] The terminal sends this request to the server.

[0272] The server collects relevant data from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[0273] The server analyzes the collected data using machine learning algorithms to identify important information.

[0274] The server analyzes the user's emotional state (anxiety) using an emotion engine and derives elements that provide a sense of security.

[0275] The server uses generative artificial intelligence to generate a detailed report on the "latest diabetes treatments," adding reassuring content.

[0276] The server formats the report into a template, adding headings, charts, and reassuring explanatory text.

[0277] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[0278] Thus, the present invention is a system that takes into account the user's emotions and realizes more personalized and highly accurate information provision. Even without specialized knowledge, the user can easily obtain the necessary information and use it in a form that takes into account their emotions.

[0279] The processing flow will be described below.

[0280] Step 1:

[0281] The user inputs their emotional state (e.g., anxiety, relief) together with the search keyword "latest treatment methods for heart disease" through the terminal. In particular, emotions can also be automatically collected through face recognition, voice analysis, etc.

[0282] Step 2:

[0283] The terminal sends the user's input request and emotional data to the server through the network. As a result, the user's specific request and their emotions at that time are sent to the system.

[0284] Step 3:

[0285] The server receives the user's request and generates a search query based on its content. This query is used to collect specific data such as "latest treatment methods for heart disease".

[0286] Step 4:

[0287] The server collects relevant data by referring to public databases and internal databases on the Internet. The collected data includes the latest medical papers, research data, clinical trial results, etc.

[0288] Step 5:

[0289] The server preprocesses the collected data. Data preprocessing includes data normalization, missing data supplementation, format unification, etc. As a result, the data is prepared in an analyzable form.

[0290] Step 6:

[0291] The server inputs pre-processed data into machine learning algorithms (e.g., clustering or regression analysis) to perform data analysis. The goal of the analysis is to extract the knowledge and patterns most relevant to the user's requirements.

[0292] Step 7:

[0293] The server inputs the user's emotional data into the emotion engine and analyzes their emotional state. Based on the results of the emotion analysis, it identifies the user's current emotional state.

[0294] Step 8:

[0295] The server integrates the analysis results and sentiment analysis results, and uses generative artificial intelligence to generate specific response text to the user's request. For example, if the user is looking for information on "the latest treatments for heart disease," it will generate detailed text in response to that request, and further add content that takes into account the user's emotions (such as anxiety).

[0296] Step 9:

[0297] The server formats the generated text into a template. This formatting process includes adding headings, bullet points, and, if necessary, charts and graphs. It also adds reassuring language and explanations based on the user's emotional state.

[0298] Step 10:

[0299] The server sends a formatted template to the user's terminal. During this process, the necessary information is provided in a format that is easy for the user to understand.

[0300] Step 11:

[0301] The user checks and downloads the template sent through the terminal. The template contains reassuring explanations and specific treatment methods, and provides the information necessary for practical use. For example, it can be used in the treatment policy meeting at a medical institution.

[0302] (Example 2)

[0303] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0304] In recent years, with the progress of information technology, it has been required that users quickly and accurately obtain the necessary information from a large amount of information. However, in the conventional system, since information is provided without considering the user's emotional state, there is a problem that the user satisfaction is low. Also, in the analysis of the collected data, optimal information is not always provided. As a result, the accuracy and personalization of the information required by the user are insufficient, and it is difficult to obtain information particularly in the fields that require specialized knowledge.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0306] In this invention, the server includes [means for receiving a request and an emotional state input from a user, [means for collecting data from a public database and an internal database based on the received request, [means for preprocessing and analyzing the collected data]. Thereby, [personalized and highly accurate information provision considering the user's emotional state] becomes possible.

[0307] A "user" is a subject who searches for and receives information using the system.

[0308] A "request" refers to a search key or question content input by the user to the system.

[0309] "Emotional state" refers to the state of the user's emotions (e.g., tension, relief, excitement), and is data collected through facial recognition, voice analysis, etc.

[0310] A "public database" refers to an information source that exists on the internet and is accessible to anyone (e.g., academic paper databases, open data platforms).

[0311] An "internal database" is a private database managed by the system owner, accessible only to users or specific stakeholders.

[0312] "Preprocessing" refers to the process of preparing collected data into an analyzable format, and specifically includes data normalization, imputation of missing values, and removal of unnecessary information.

[0313] "Analysis" is the process of using collected and pre-processed data to extract knowledge patterns related to user requests using machine learning algorithms or similar methods.

[0314] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state and output the results of that emotional analysis.

[0315] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates appropriate text and responses based on analysis results.

[0316] A "template format" is a visually formatted format that makes generated responses easy for users to understand, and includes headings, paragraphs, bullet points, charts, and other elements.

[0317] A "server" refers to a computer system that processes data for the entire system, performing the steps of collection, analysis, generation, and delivery.

[0318] "Terminal" refers to a device used by a user to input requests and receive results.

[0319] This invention is a system that provides useful information based on user requests, and in particular, improves the accuracy of information provision by taking into account the user's emotional state. This system consists of a series of processing steps: inputting and receiving requests from the user, collecting data, analyzing data, performing emotional analysis using an emotion engine, generating responses using generative artificial intelligence, formatting templates, and providing results.

[0320] User request input and reception

[0321] The user enters a search key (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) through the device. The user's emotional state can also be automatically collected through facial recognition using the device's camera and microphone, or through voice analysis. The device sends the request and emotional data to the server via a secure communication protocol (e.g., HTTPS).

[0322] Data collection

[0323] After receiving a user request, the server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal databases. The collected data is temporarily stored in storage.

[0324] Data analysis

[0325] The server preprocesses the collected data, preparing it for analysis. This preprocessing includes data normalization, imputation of missing values, and removal of unnecessary information. The preprocessed data is then fed into machine learning algorithms (e.g., clustering, regression analysis) to extract knowledge patterns that meet the user's requirements. The analysis results are stored as structured data.

[0326] Emotional analysis using an emotion engine

[0327] The server inputs the user's emotional data into the emotion engine, which then analyzes the user's emotional state. For example, if the user is "stressed," the emotion engine generates elements to help the user relax. The results of the emotional analysis are then reflected in the subsequent response generation by the generative artificial intelligence system.

[0328] Answer generation using generative artificial intelligence

[0329] The server integrates the analysis results and sentiment analysis results and generates specific response text using generative artificial intelligence (e.g., GPT models). For example, it generates a response that combines detailed text about "the latest treatments for heart disease" with phrases that alleviate the user's anxiety.

[0330] Template formatting

[0331] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other visual elements to make the information easier for users to understand. Furthermore, it applies templates tailored to the user's emotional state, adding elements that create a sense of security.

[0332] Providing results

[0333] The server sends a formatted template as the final answer to the user's terminal. The user downloads the provided template via their terminal and uses it as actual reference material. If necessary, the template can also be printed or shared with other users.

[0334] Specific example

[0335] A concrete example of a prompt might be, "I want to learn about the latest diabetes treatments. Please also include information that will alleviate my anxieties." Based on this prompt, the system collects medical data and generates information that includes elements to reduce anxiety. The resulting template would include detailed information about the latest diabetes treatments and explanations to alleviate anxiety.

[0336] Thus, the present invention is a system that provides personalized and highly accurate information while taking into consideration the user's emotions. As a result, users can easily obtain the necessary information even without specialized knowledge and use it in a way that is sensitive to their emotions.

[0337] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0338] Step 1: Inputting and receiving requests from the user.

[0339] Users enter search keywords (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) via their device. Emotional states may also be automatically collected using facial recognition or voice analysis via the device's camera and microphone.

[0340] Input: User request (search key) and sentiment state data

[0341] Output: Packetized data of user requests and emotional states

[0342] The terminal sends the generated packetized data to the server using a secure communication protocol (e.g., HTTPS).

[0343] Step 2: Data Collection

[0344] The server analyzes the user's request data and generates queries to collect the requested information.

[0345] Input: User's requested data

[0346] Output: Database query

[0347] The server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal company databases.

[0348] Input: Database query

[0349] Output: Collected data (medical papers, clinical trial data, etc.)

[0350] The server stores the collected data in temporary storage.

[0351] Step 3: Data Analysis

[0352] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data, imputing missing values, and removing unnecessary information.

[0353] Input: Collected data

[0354] Output: Preprocessed data

[0355] The server inputs pre-processed data into machine learning algorithms (e.g., clustering, regression analysis) and extracts knowledge patterns that meet the user's requirements.

[0356] Input: Preprocessed data

[0357] Output: Analysis results (structured data)

[0358] Step 4: Emotional analysis using the emotion engine

[0359] The server inputs the user's emotional state data into the emotion engine and analyzes the emotional state.

[0360] Input: User's emotional state data

[0361] Output: Emotion analysis results (identification of emotional state, suggestions for appropriate responses, etc.)

[0362] For example, if a user is feeling "stressed," the emotion engine will generate elements that promote "relaxation."

[0363] Step 5: Answer generation using generative artificial intelligence

[0364] The server uses generative artificial intelligence (e.g., GPT models) to generate specific response text based on the analysis results and sentiment analysis results.

[0365] Input: Analysis results and sentiment analysis results

[0366] Output: Specific answer text

[0367] For example, the system generates responses that combine detailed text about "the latest treatments for heart disease" with phrases designed to ease the user's anxiety.

[0368] Step 6: Template Formatting

[0369] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other elements.

[0370] Input: Generated response text

[0371] Output: Template-formatted answer

[0372] Furthermore, templates tailored to the user's emotional state are applied, and elements that help users feel more secure are added.

[0373] Step 7: Results Provision

[0374] The server sends the formatted template to the user's terminal.

[0375] Input: Template-style answer

[0376] Output: Template-formatted response sent to the user's device.

[0377] Users download templates provided through their devices and use them in their work. They can also print templates or share them with other users as needed.

[0378] (Application Example 2)

[0379] 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".

[0380] Traditional e-commerce sites offer systems that recommend products based on user requests, but these recommendations do not take into account the user's emotional state, making it difficult to improve user psychological satisfaction. Therefore, when a user is stressed or agitated, the system fails to recommend suitable products, hindering the improvement of the user experience. Furthermore, it has not been possible to provide personalized information that reflects the user's emotional state.

[0381] 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.

[0382] In this invention, the server includes means for receiving requests and emotional data entered by the user, means for collecting data based on the received requests and emotional data, and means for preprocessing and analyzing the collected data. This enables product recommendations tailored to the user's emotional state, improves the user's psychological satisfaction, and provides personalized, highly accurate information.

[0383] "Means for receiving requests and sentiment data entered by users" refers to a function that collects and receives product search requests and sentiment data entered by users through their terminals.

[0384] "Means for collecting data based on received requests and sentiment data" refers to a function that collects relevant product information and data from the internet and internal databases based on the user's search requests and sentiment data.

[0385] "Means for preprocessing and analyzing collected data" refers to functions that perform preprocessing such as normalizing collected data into an analyzable format or imputing missing values, and then performing data analysis.

[0386] "A means of inputting analysis results into a generative artificial intelligence system using a machine learning algorithm to generate a response" refers to a function that applies a machine learning algorithm based on pre-processed results, and uses generative artificial intelligence to generate specific responses and recommendations to the user's requests as text.

[0387] "A means of formatting generated responses into a template and adding emotionally sensitive content" refers to a function that formats the generated response text and adds headings and explanations that are sensitive to the user's emotions.

[0388] "Means of providing formatted templates to users" refers to a function that sends formatted templates to the user's device, making the information easily accessible to the user.

[0389] Modes for carrying out the invention

[0390] This invention provides a product recommendation system for e-commerce sites that takes into account the emotional state of the user. The following describes specific embodiments of this invention in detail.

[0391] System configuration and programs to be used

[0392] Hardware and software

[0393] 1. Hardware: Smartphone or tablet

[0394] 2. Software:

[0395] Emotion recognition technology: Image recognition technology is used for facial recognition, and speech recognition technology is used for voice analysis. For example, general image recognition APIs and speech recognition APIs are used.

[0396] Data analysis tools: Python and its libraries (pandas, scikit-learn) will be used.

[0397] Generative artificial intelligence: Uses a generative AI model (e.g., GPT-4®).

[0398] Backend server: Uses Node.js and Express.

[0399] Database: Use MySQL (registered trademark).

[0400] Processing flow and data calculations

[0401] The server receives requests and emotional data entered by the user. For example, a user inputs their emotional state using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. As a result, the user's request data and emotional data are sent from the device to the server.

[0402] The server collects relevant product information from the internet and internal databases based on received request and sentiment data. The collected data is preprocessed, for example, by imputing missing values ​​and normalizing the data.

[0403] After the preprocessing of the collected data is complete, analysis will be performed. The analysis will be carried out using Python and its libraries (pandas, scikit-learn), and related product information will be analyzed using machine learning algorithms such as clustering.

[0404] Next, the analysis results are input into a generative artificial intelligence (generative AI model) to generate product recommendation text, which is a specific response to the user's request. The following example prompt sentences are input into this generative AI model:

[0405] "Please recommend five relaxation products that would be suitable for users who are feeling anxious."

[0406] The generated responses are formatted into a template with added content that takes the user's emotions into consideration. This template includes headings and descriptions that reflect the user's emotions.

[0407] Finally, a formatted template is provided to the user's device, allowing the user to intuitively view product information.

[0408] Adding specific examples

[0409] For example, if a user requests to learn about the latest gadgets and the system recognizes that the user is also experiencing anxiety, the system will collect relevant gadget information from the internet and its internal database. Based on the analyzed data, a generative AI model will generate detailed text about the latest gadgets, and further add explanatory text that helps alleviate the user's anxiety. This allows the user to obtain information while feeling at ease.

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The user inputs their emotional data using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. The input includes the user's emotional data (e.g., nervous, relieved, excited) and product search keys (e.g., "latest gadgets"). The output is the device sending this data to a server.

[0413] Step 2:

[0414] The server receives user requests and sentiment data over the network. It takes user sentiment data and product search request data as input and passes that data to the next processing step as output.

[0415] Step 3:

[0416] The server collects relevant product information based on requests received from the internet and internal databases. It uses user search requests (e.g., "latest gadgets") as input and collects and stores relevant data (e.g., product names, specifications, reviews, etc.) as output.

[0417] Step 4:

[0418] The server preprocesses the collected data and prepares it for analysis. It takes the collected raw data as input, performs specific data processing (imputation of missing values, data normalization), and generates a clean, preprocessed dataset as output.

[0419] Step 5:

[0420] The server analyzes the pre-processed data. It takes a clean dataset as input, analyzes the data using machine learning algorithms (e.g., clustering and regression analysis), and outputs the analysis results.

[0421] Step 6:

[0422] The server inputs the analysis results into a generative AI model to generate specific answers (product recommendation text) to the user's request. The generative AI model is fed with the analysis results and a prompt (for example, "Please recommend 5 relaxation products for when the user is feeling anxious") as input, and the generated answer text is obtained as output.

[0423] Step 7:

[0424] The server formats the generated response text into a template and adds headings and descriptions that take into account the user's emotional state. It takes the generated text and user emotional information as input, formats the headings and additional descriptions, and outputs a final document in template format.

[0425] Step 8:

[0426] The server sends a formatted template to the user's terminal and provides it to the user. It takes a final document in template format as input and sends and displays the document on the user's terminal as output.

[0427] This will enable a system that allows users to obtain product information in an intuitive and emotionally resonant way.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Second Embodiment]

[0432] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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".

[0444] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. This system automatically performs a series of processes, from receiving user requests to collecting, analyzing, and generating responses, and then providing formatted templates.

[0445] 1. System Program

[0446] User request input and reception

[0447] The user enters search terms such as "latest treatments for heart disease" using their device.

[0448] The terminal transmits requests to the system by sending user input to the server.

[0449] Data collection

[0450] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[0451] For example, in the medical field, this would involve gathering the latest research papers, research data, and clinical trial results.

[0452] Data Analysis

[0453] The server analyzes the collected data. This analysis utilizes machine learning algorithms (such as clustering and regression analysis).

[0454] For example, we can extract important keywords and trends related to "the latest treatments for heart disease."

[0455] Answer generation using generative artificial intelligence

[0456] The server uses generative artificial intelligence (for example, AI using natural language processing technology) based on the analysis results to generate specific answers.

[0457] For example, it can automatically generate detailed text about "the latest treatments for heart disease."

[0458] Template formatting

[0459] The server formats the generated text into a user-friendly template format.

[0460] For example, if you are creating a report, it should be structured as follows:

[0461] Title: The Latest Treatments for Heart Disease

[0462] Introduction

[0463] Treatment Overview

[0464] Results of clinical trials

[0465] Precautions and side effects

[0466] summary

[0467] Providing results

[0468] The server sends the formatted template to the user's terminal.

[0469] Users download templates sent from their devices and use them in their work.

[0470] Specific example

[0471] For example, consider the medical field:

[0472] The user enters a request stating, "I want to know about the latest diabetes treatments."

[0473] The terminal sends this request to the server.

[0474] The server collects relevant information from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[0475] The server analyzes the collected data using machine learning algorithms to identify important information.

[0476] The server inputs the analysis results into a generative artificial intelligence system, which then generates a detailed report on the "latest diabetes treatments."

[0477] The server formats the report into a template, including headings, figures, tables, bullet points, etc.

[0478] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[0479] Thus, the present invention is a system that processes user requests quickly and accurately, and provides information directly relevant to practical work. Users can easily obtain and utilize the necessary information even without specialized knowledge.

[0480] The following describes the processing flow.

[0481] Step 1:

[0482] The user enters the search key "latest treatments for heart disease" through their device. This allows the user's request to be collected in a specific format.

[0483] Step 2:

[0484] The terminal sends the user's input request to the server via the network. During this process, the system recognizes the user's request.

[0485] Step 3:

[0486] The server analyzes the received request and generates search queries to collect relevant data based on the request. This enables accurate data collection.

[0487] Step 4:

[0488] The server collects relevant data from publicly available databases on the internet and from internal databases. For example, it retrieves the latest medical papers and clinical trial data.

[0489] Step 5:

[0490] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[0491] Step 6:

[0492] The server inputs preprocessed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis and extract knowledge patterns related to user requests.

[0493] Step 7:

[0494] The server inputs the analysis results into a generative artificial intelligence (e.g., natural language processing AI) to generate response text that meets the user's request. For example, it might create detailed text about "the latest treatments for heart disease."

[0495] Step 8:

[0496] The server formats the generated text into a template. Specifically, it adds headings, bullet points, and, if necessary, figures and tables.

[0497] Step 9:

[0498] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[0499] Step 10:

[0500] Users download templates from their devices and use them in their daily work. For example, they might use the provided reports in treatment plan meetings at a medical institution.

[0501] (Example 1)

[0502] 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."

[0503] Conventional information retrieval systems often fail to respond quickly to user requests, and the information provided frequently does not meet the user's specific needs. In particular, the process of generating useful information using big data is complex and requires specialized knowledge, making it difficult for the average user to utilize. Furthermore, there is a need for more efficient methods for pre-processing and analyzing collected data, as well as for formatting the generated information.

[0504] 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.

[0505] In this invention, the server includes means for receiving requests entered by a user, means for collecting relevant data from a database based on the received requests, means for preprocessing the collected data, means for analyzing the preprocessed data with a machine learning algorithm, means for inputting the analysis results into a generating AI model to generate an answer, means for formatting the generated answer into a template format, and means for providing the formatted template to the user. This enables a system that can respond quickly and accurately to user requests and allows users to easily obtain useful information even without specialized knowledge.

[0506] "Means of receiving requests entered by the user" refers to the function by which the server receives requests such as search keys and questions entered by the user through a terminal.

[0507] "Means of collecting relevant data from a database based on received requests" refers to a function in which a server automatically collects relevant information from publicly available databases on the internet or internal databases in response to user requests.

[0508] "Means for pre-processing collected data" refers to the function of the server that performs pre-processing on the collected data, such as cleansing, format conversion, and noise reduction.

[0509] "Means of analyzing pre-processed data with machine learning algorithms" refers to the function of a server that analyzes pre-processed data using machine learning algorithms (for example, clustering or regression analysis).

[0510] "A means of inputting analysis results into a generative AI model to generate answers" refers to a function in which a server automatically generates specific answers using a generative AI model (for example, an AI using natural language processing technology) based on the results analyzed by a machine learning algorithm.

[0511] "Means of formatting generated responses into a template format" refers to a function that allows the server to convert generated responses into a user-friendly template format (for example, a report format).

[0512] "Means of providing formatted templates to users" refers to a function in which the server sends formatted templates to the user's terminal, allowing the user to download and use them.

[0513] "Means of using the internet and internal databases in data collection" refers to the function of obtaining information by using publicly available databases on the internet or dedicated internal databases during the data collection process.

[0514] "Means for creating prompt statements when inputting analysis results into a generating AI model" refers to a function that constructs prompt statements based on analysis results in order to obtain appropriate output from the generating AI model.

[0515] This invention describes a specific embodiment of a system for automating complex information retrieval and analysis processes and providing useful information in response to user requests. This system uses various hardware and software to automatically execute a series of processes from request reception to result provision.

[0516] System Configuration

[0517] This system mainly consists of the following hardware and software:

[0518] Server: Possesses high-performance data collection, analysis, generation, and formatting capabilities.

[0519] Terminal: A device used by a user to input information (e.g., a personal computer, a smartphone).

[0520] Generative AI models: AI that generates answers using natural language processing techniques (e.g., GPT-3).

[0521] Databases: Publicly accessible databases on the internet and internal databases.

[0522] Process details

[0523] User request input and reception

[0524] The user enters a search key through their device's browser or a dedicated application. For example, they might enter "latest treatments for heart disease." The device sends this request to the server, which then communicates the request to the entire system.

[0525] Data collection

[0526] After receiving a user request, the server collects the relevant data. This collection utilizes publicly available internet databases (e.g., PubMed) and internal databases.

[0527] Data preprocessing

[0528] The server preprocesses the collected data. This preprocessing includes data cleansing, format conversion, and noise reduction.

[0529] Data Analysis

[0530] The server performs analysis on the preprocessed data using machine learning algorithms (e.g., clustering, regression analysis). Through this analysis, important keywords and trends are extracted.

[0531] Answer generation using generative artificial intelligence

[0532] The server generates a prompt based on the analysis results and inputs it into the AI ​​model to generate an answer. For example, the prompt might look like this:

[0533] "Provide the latest treatments for heart disease based on these key findings: ..."

[0534] Template formatting

[0535] The generated responses are formatted by the server into a template. This template is in a user-friendly format for reports and presentations. For example, the template format may look like this:

[0536] Title: The Latest Treatments for Heart Disease

[0537] Introduction

[0538] Treatment Overview

[0539] Results of clinical trials

[0540] Precautions and side effects

[0541] summary

[0542] Providing results

[0543] The formatted template is sent from the server to the user's terminal. The user can download this template and use it in their work.

[0544] Specific example

[0545] For example, in the medical field, a user might input a request such as "I want to know about the latest diabetes treatments," and their device sends this request to a server. The server uses the internet and internal databases to collect relevant information and preprocess the data. Using the preprocessed data, it performs analysis using machine learning algorithms and inputs prompts into a generative AI model to generate an answer. The generated answer is formatted into a template and sent to the user's device. The user downloads the template and uses it in their daily work in the medical field.

[0546] Through the above process, the system of the present invention can provide users with information quickly and with high accuracy.

[0547] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0548] Step 1:

[0549] The user enters a search term on their device. For example, they might type "latest treatments for heart disease."

[0550] The terminal receives user input and sends that request to the server. The input data is the user's request, and this becomes the basis for the next step.

[0551] Step 2:

[0552] The server receives user requests and collects relevant data from the internet and internal databases. This collected data may include, for example, publicly available papers, research data, and clinical trial results.

[0553] In practice, the server uses an API to query the database. The input is the user's request, and the output is the relevant raw data.

[0554] Step 3:

[0555] The server preprocesses the collected data. This preprocessing includes data cleansing (deduplication and noise reduction), format conversion, and other steps.

[0556] The input is the collected raw data, and the output is pre-processed, clean data. Specifically, the data cleansing is performed using Python code.

[0557] Step 4:

[0558] The server performs analysis using machine learning algorithms based on preprocessed data. For example, it extracts important keywords and trends using clustering methods and regression analysis.

[0559] The input is pre-processed data, and the output is the analysis result. Specifically, the analysis is performed using libraries such as scikit-learn.

[0560] Step 5:

[0561] The server generates prompt sentences based on the analysis results and inputs them into a generative AI model to generate an answer. Here, for example, an AI (generative AI model) using natural language processing technology is used.

[0562] The input is the analysis result, which is the prompt text to be input into the generating AI model. The output is the generated detailed answer. Examples of specific prompt texts are as follows:

[0563] "Provide the latest treatments for heart disease based on these key findings: ..."

[0564] Step 6:

[0565] The server formats the generated responses into a template format. This is the process of converting them into a user-friendly format for reports and presentation materials.

[0566] The input is the response from a generative AI model, and the output is a document formatted in a template. Examples of specific template formats are as follows:

[0567] Title: The Latest Treatments for Heart Disease

[0568] Introduction

[0569] Treatment Overview

[0570] Results of clinical trials

[0571] Precautions and side effects

[0572] summary

[0573] Step 7:

[0574] The server sends the formatted template to the user's terminal.

[0575] The input is a document formatted into a template, and the output is a formatted template sent to the user's terminal.

[0576] Users can download formatted templates on their devices and use them in their work.

[0577] (Application Example 1)

[0578] 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."

[0579] In today's information society, it is becoming increasingly important for users to access the latest and most useful information. Information regarding electronic payment services, in particular, is evolving rapidly, requiring users to accurately understand trends, convenience, and points to be aware of. However, traditional information gathering methods require users to manually search and analyze large amounts of data, which is time-consuming and laborious, and the reliability of the information is inconsistent. Therefore, there is a need for more efficient information delivery methods.

[0580] 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.

[0581] In this invention, the server includes means for receiving requests entered by a user, means for collecting data based on the received requests, means for analyzing the collected data, means for converting the analysis results into answers using generative artificial intelligence, means for formatting the answers into a template format, means for providing the formatted template to the user, means for receiving user input and sending it to a server on the cloud, and means for using natural language processing technology for analyzing the collected data. This makes it possible for users to efficiently and accurately obtain the latest trend information on electronic payments even without specialized knowledge.

[0582] "Means for receiving requests entered by a user" refers to the hardware or software mechanism by which a system receives requests entered by a user to obtain specific information.

[0583] "Means for collecting data based on received requests" refers to a system that automatically collects data corresponding to user requests from the internet or internal databases.

[0584] "Means for analyzing collected data" refers to algorithms and technologies used to analyze collected data and extract necessary information and trends.

[0585] "Means of converting analysis results into answers using generative artificial intelligence" refers to a system that generates actual answers using generative artificial intelligence (for example, natural language processing technology) based on the analyzed data.

[0586] "Methods for formatting responses into a template format" refers to methods for converting generated responses into a template format that is easy for users to understand.

[0587] "Means of providing users with formatted templates" refers to a mechanism that sends formatted information to the user's device, allowing the user to receive and use it.

[0588] "Means of receiving user input and sending it to a server on the cloud" refers to a method of receiving a user's request and sending it to a server on a cloud service.

[0589] "Methods for using natural language processing technology in the analysis of collected data" refers to techniques that use natural language processing technology to automatically extract important information when analyzing collected data.

[0590] The system implementing this invention automatically generates and provides useful information using big data in response to user requests. This system is broadly composed of the following hardware and software elements.

[0591] 1. Hardware and software used

[0592] hardware

[0593] User terminal: A device that can connect to the internet, such as a smartphone or smart glasses, is used.

[0594] Cloud server: A server is required for data collection, analysis, and provision of generated information.

[0595] software

[0596] Flask: Used as an API server on a cloud server.

[0597] Generative AI: Specifically, generative AI models that utilize natural language processing technologies such as OpenAI GPT-3 are used.

[0598] 2. Data Processing and Data Calculation Flow

[0599] Receiving user input

[0600] The user uses a smartphone or smart glasses to input a request for specific information. For example, they might input, "Tell me about the latest cashless payment trends." The user's device sends this request to a cloud server.

[0601] Data collection

[0602] The server collects relevant information from the internet and internal databases based on the received request. This collected data includes the latest news, reports, articles, and user reviews.

[0603] Data Analysis

[0604] The server automatically analyzes the collected data using natural language processing technology. This analysis extracts important keywords and trends related to the requests.

[0605] Answer generation

[0606] Using generative artificial intelligence (GPT-3), specific answers are generated based on the analyzed data. The generated answers are presented in a format that is easy for the user to understand.

[0607] Template formatting

[0608] The server formats the generated responses into a user-friendly template. For example, it might be structured as follows:

[0609] Title: Latest Cashless Payment Trends

[0610] Introduction

[0611] Overview of payment methods

[0612] Details and convenience of each method

[0613] Points to note

[0614] summary

[0615] Providing results

[0616] The server sends a formatted template to the user's terminal, and the user receives and views this information.

[0617] Examples of specific cases and prompt statements

[0618] For example, suppose a user types "Tell me the latest cashless payment trends" into their smartphone. This request is immediately sent to a cloud server, where it undergoes automated analysis and AI generation to produce a detailed and structured report. The user can then receive the information directly in report format.

[0619] Example of a prompt

[0620] "Please tell me about the latest cashless payment trends. Include key points, trends, convenience, and points to note."

[0621] This prompt allows generative artificial intelligence to automatically generate detailed answers, enabling it to respond quickly and accurately to the information the user is seeking.

[0622] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0623] Step 1:

[0624] The user inputs specific information using a smartphone or smart glasses. For example, they might input a request such as, "Tell me about the latest cashless payment trends." The input request is then sent from the device to a server in the cloud.

[0625] Input: User request (e.g., "Tell me about the latest cashless payment trends")

[0626] Output: Request data sent to the cloud server

[0627] Step 2:

[0628] The server receives requests sent by users. Based on the received requests, it collects relevant data. The server collects relevant information from publicly available databases on the internet and from its own internal databases. This includes, for example, the latest news, reports, papers, and user reviews.

[0629] Input: Request data sent to the cloud server

[0630] Output: Collected data (latest news, reports, papers, user reviews, etc.)

[0631] Step 3:

[0632] The server analyzes the collected data. This analysis utilizes natural language processing techniques, including keyword extraction and trend analysis.

[0633] Input: Collected data

[0634] Output: Analysis results (extraction of important keywords and trends)

[0635] Step 4:

[0636] The server generates specific answers using generative artificial intelligence (such as GPT-3) based on the analysis results. A prompt (e.g., "Tell me about the latest cashless payment trends") is input to the generative AI model to obtain a detailed response.

[0637] Input: Analysis result, prompt message

[0638] Output: Generated answer text

[0639] Step 5:

[0640] The server formats the generated response text into a user-friendly template format. For example, it might be structured as follows: Title, Introduction, Overview of Payment Methods, Details and Convenience of Each Method, Points to Note, Summary.

[0641] Input: Generated response text

[0642] Output: Answer text formatted in template format

[0643] Step 6:

[0644] The server provides a formatted template to the user's terminal. The terminal receives the template, and the user views the results on their smartphone or smart glasses.

[0645] Input: Answer text formatted in template format

[0646] Output: Sending to the user's terminal, allowing the user to view the results.

[0647] 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.

[0648] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. In particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to provide even more accurate information. This system automatically performs a series of processes, from receiving the user's request to collecting and analyzing the necessary data, generating the response, formatting it, and providing an emotion-conscious template.

[0649] 1. System Program

[0650] User request input and reception

[0651] The user enters their emotional state (e.g., nervous, relieved, excited) along with the search keyword "latest treatments for heart disease" via their device. Emotions can also be automatically collected through facial recognition or voice analysis.

[0652] The terminal transmits the user's input requests and emotional data to the server via the network.

[0653] Data collection

[0654] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[0655] For example, obtaining the latest medical papers and clinical trial data.

[0656] Data Analysis

[0657] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[0658] The server inputs preprocessed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis and extract knowledge patterns related to user requests.

[0659] Emotional analysis using an emotion engine

[0660] The server uses the user's emotional data to input into the emotion engine, which then analyzes the emotional state.

[0661] For example, if a user is feeling anxious, information to generate a relaxing response should also be considered.

[0662] Answer generation using generative artificial intelligence

[0663] The server uses generative artificial intelligence based on the analysis results and sentiment analysis results to generate specific response text to the user's request.

[0664] For example, it can generate detailed text about "the latest treatments for heart disease" and add content that takes the user's emotions into consideration.

[0665] Template formatting

[0666] The server formats the generated text into a template. It adds headings and descriptions that reflect the user's emotional state.

[0667] For example, include headings, bullet points, charts, and other elements to provide reassuring language and explanations to users.

[0668] Providing results

[0669] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[0670] Users download templates from their devices and use them in their daily work. The provided reports could also be used in treatment plan meetings at medical institutions.

[0671] Specific example

[0672] For example, consider the medical field:

[0673] When a user requests to learn about the latest diabetes treatments, they simultaneously input their emotions at the time of making that request (e.g., anxiety).

[0674] The terminal sends this request to the server.

[0675] The server collects relevant data from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[0676] The server analyzes the collected data using machine learning algorithms to identify important information.

[0677] The server analyzes the user's emotional state (anxiety) using an emotion engine and derives elements that provide a sense of security.

[0678] The server uses generative artificial intelligence to generate a detailed report on the "latest diabetes treatments," adding reassuring content.

[0679] The server formats the report into a template, adding headings, charts, and reassuring explanatory text.

[0680] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[0681] Thus, the present invention is a system that takes user emotions into consideration to realize more personalized and highly accurate information delivery. Users can easily obtain the necessary information even without specialized knowledge and use it in a way that is sensitive to their emotions.

[0682] The following describes the processing flow.

[0683] Step 1:

[0684] The user enters their emotional state (e.g., anxiety, relief) along with the search keyword "latest treatments for heart disease" via their device. Emotions, in particular, can be automatically collected through facial recognition or voice analysis.

[0685] Step 2:

[0686] The terminal transmits the user's input requests and emotional data to the server via the network. This sends the user's specific requests and their emotions at that time to the system.

[0687] Step 3:

[0688] The server receives a user request and generates a search query based on its content. This query is used to collect specific data, such as "the latest treatments for heart disease."

[0689] Step 4:

[0690] The server accesses publicly available databases on the internet and internal databases to collect relevant data. This collected data includes the latest medical papers, research data, and clinical trial results.

[0691] Step 5:

[0692] The server preprocesses the collected data. Data preprocessing includes normalization, imputation of missing data, and standardization of format. This prepares the data in a format that can be analyzed.

[0693] Step 6:

[0694] The server inputs pre-processed data into machine learning algorithms (e.g., clustering or regression analysis) to perform data analysis. The goal of the analysis is to extract the knowledge and patterns most relevant to the user's requirements.

[0695] Step 7:

[0696] The server inputs the user's emotional data into the emotion engine and analyzes their emotional state. Based on the results of the emotion analysis, it identifies the user's current emotional state.

[0697] Step 8:

[0698] The server integrates the analysis results and sentiment analysis results, and uses generative artificial intelligence to generate specific response text to the user's request. For example, if the user is looking for information on "the latest treatments for heart disease," it will generate detailed text in response to that request, and further add content that takes into account the user's emotions (such as anxiety).

[0699] Step 9:

[0700] The server formats the generated text into a template. This formatting process includes adding headings, bullet points, and, if necessary, charts and graphs. It also adds reassuring language and explanations based on the user's emotional state.

[0701] Step 10:

[0702] The server sends a formatted template to the user's terminal. During this process, the necessary information is provided in a format that is easy for the user to understand.

[0703] Step 11:

[0704] Users review and download templates sent via their devices. These templates include reassuring explanations and specific treatment methods, providing the necessary information for practical use. For example, they can be used in treatment planning meetings at medical institutions.

[0705] (Example 2)

[0706] 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".

[0707] In recent years, with the advancement of information technology, users are required to quickly and accurately obtain the information they need from vast amounts of data. However, conventional systems provide information without considering the user's emotional state, resulting in low user satisfaction. Furthermore, the analysis of collected data does not always provide the most optimal information. As a result, the accuracy and personalization of the information users need are insufficient, making it difficult to obtain information, especially in fields requiring specialized knowledge.

[0708] 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.

[0709] In this invention, the server includes means for receiving requests and emotional states entered by the user, means for collecting data from a public database and an internal database based on the received requests, and means for preprocessing and analyzing the collected data. This enables personalized and highly accurate information provision that takes the user's emotional state into consideration.

[0710] A "user" is an entity that uses a system to search for and receive information.

[0711] A "request" refers to the search keys or questions that a user enters into the system.

[0712] "Emotional state" refers to the state of the user's emotions (e.g., tension, relief, excitement), and is data collected through facial recognition, voice analysis, etc.

[0713] A "public database" refers to an information source that exists on the internet and is accessible to anyone (e.g., academic paper databases, open data platforms).

[0714] An "internal database" is a private database managed by the system owner, accessible only to users or specific stakeholders.

[0715] "Preprocessing" refers to the process of preparing collected data into an analyzable format, and specifically includes data normalization, imputation of missing values, and removal of unnecessary information.

[0716] "Analysis" is the process of using collected and pre-processed data to extract knowledge patterns related to user requests using machine learning algorithms or similar methods.

[0717] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state and output the results of that emotional analysis.

[0718] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates appropriate text and responses based on analysis results.

[0719] A "template format" is a visually formatted format that makes generated responses easy for users to understand, and includes headings, paragraphs, bullet points, charts, and other elements.

[0720] A "server" refers to a computer system that processes data for the entire system, performing the steps of collection, analysis, generation, and delivery.

[0721] "Terminal" refers to a device used by a user to input requests and receive results.

[0722] This invention is a system that provides useful information based on user requests, and in particular, improves the accuracy of information provision by taking into account the user's emotional state. This system consists of a series of processing steps: inputting and receiving requests from the user, collecting data, analyzing data, performing emotional analysis using an emotion engine, generating responses using generative artificial intelligence, formatting templates, and providing results.

[0723] User request input and reception

[0724] The user enters a search key (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) through the device. The user's emotional state can also be automatically collected through facial recognition using the device's camera and microphone, or through voice analysis. The device sends the request and emotional data to the server via a secure communication protocol (e.g., HTTPS).

[0725] Data collection

[0726] After receiving a user request, the server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal databases. The collected data is temporarily stored in storage.

[0727] Data Analysis

[0728] The server preprocesses the collected data, preparing it for analysis. This preprocessing includes data normalization, imputation of missing values, and removal of unnecessary information. The preprocessed data is then fed into machine learning algorithms (e.g., clustering, regression analysis) to extract knowledge patterns that meet the user's requirements. The analysis results are stored as structured data.

[0729] Emotional analysis using an emotion engine

[0730] The server inputs the user's emotional data into the emotion engine, which then analyzes the user's emotional state. For example, if the user is "stressed," the emotion engine generates elements to help the user relax. The results of the emotional analysis are then reflected in the subsequent response generation by the generative artificial intelligence system.

[0731] Answer generation using generative artificial intelligence

[0732] The server integrates the analysis results and sentiment analysis results and generates specific response text using generative artificial intelligence (e.g., GPT models). For example, it generates a response that combines detailed text about "the latest treatments for heart disease" with phrases that alleviate the user's anxiety.

[0733] Template formatting

[0734] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other visual elements to make the information easier for users to understand. Furthermore, it applies templates tailored to the user's emotional state, adding elements that create a sense of security.

[0735] Providing results

[0736] The server sends a formatted template as the final answer to the user's terminal. The user downloads the provided template via their terminal and uses it as actual reference material. If necessary, the template can also be printed or shared with other users.

[0737] Specific example

[0738] A concrete example of a prompt might be, "I want to learn about the latest diabetes treatments. Please also include information that will alleviate my anxieties." Based on this prompt, the system collects medical data and generates information that includes elements to reduce anxiety. The resulting template would include detailed information about the latest diabetes treatments and explanations to alleviate anxiety.

[0739] Thus, the present invention is a system that provides personalized and highly accurate information while taking into consideration the user's emotions. As a result, users can easily obtain the necessary information even without specialized knowledge and use it in a way that is sensitive to their emotions.

[0740] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0741] Step 1: Inputting and receiving requests from the user.

[0742] Users enter search keywords (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) via their device. Emotional states may also be automatically collected using facial recognition or voice analysis via the device's camera and microphone.

[0743] Input: User request (search key) and sentiment state data

[0744] Output: Packetized data of user requests and emotional states

[0745] The terminal sends the generated packetized data to the server using a secure communication protocol (e.g., HTTPS).

[0746] Step 2: Data Collection

[0747] The server analyzes the user's request data and generates queries to collect the requested information.

[0748] Input: User's requested data

[0749] Output: Database query

[0750] The server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal company databases.

[0751] Input: Database query

[0752] Output: Collected data (medical papers, clinical trial data, etc.)

[0753] The server stores the collected data in temporary storage.

[0754] Step 3: Data Analysis

[0755] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data, imputing missing values, and removing unnecessary information.

[0756] Input: Collected data

[0757] Output: Preprocessed data

[0758] The server inputs pre-processed data into machine learning algorithms (e.g., clustering, regression analysis) to extract knowledge patterns that meet the user's requirements.

[0759] Input: Preprocessed data

[0760] Output: Analysis results (structured data)

[0761] Step 4: Emotional analysis using the emotion engine

[0762] The server inputs the user's emotional state data into the emotion engine and analyzes the emotional state.

[0763] Input: User's emotional state data

[0764] Output: Emotion analysis results (identification of emotional state, suggestions for appropriate responses, etc.)

[0765] For example, if a user is feeling "stressed," the emotion engine will generate elements that promote "relaxation."

[0766] Step 5: Generating answers using generative artificial intelligence

[0767] The server uses generative artificial intelligence (e.g., GPT models) to generate specific response text based on the analysis results and sentiment analysis results.

[0768] Input: Analysis results and sentiment analysis results

[0769] Output: Specific answer text

[0770] For example, the system generates responses that combine detailed text about "the latest treatments for heart disease" with phrases designed to ease the user's anxiety.

[0771] Step 6: Template Formatting

[0772] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other elements.

[0773] Input: Generated response text

[0774] Output: Template-formatted answer

[0775] Furthermore, templates tailored to the user's emotional state are applied, and elements that help users feel more secure are added.

[0776] Step 7: Results Provision

[0777] The server sends the formatted template to the user's terminal.

[0778] Input: Template-style answer

[0779] Output: Template-formatted response sent to the user's device.

[0780] Users download templates provided through their devices and use them in their work. They can also print templates or share them with other users as needed.

[0781] (Application Example 2)

[0782] 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."

[0783] Traditional e-commerce sites offer systems that recommend products based on user requests, but these recommendations do not take into account the user's emotional state, making it difficult to improve user psychological satisfaction. Therefore, when a user is stressed or agitated, the system fails to recommend suitable products, hindering the improvement of the user experience. Furthermore, it has not been possible to provide personalized information that reflects the user's emotional state.

[0784] 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.

[0785] In this invention, the server includes means for receiving requests and emotional data entered by the user, means for collecting data based on the received requests and emotional data, and means for preprocessing and analyzing the collected data. This enables product recommendations tailored to the user's emotional state, improves the user's psychological satisfaction, and provides personalized, highly accurate information.

[0786] "Means for receiving user-inputted requests and sentiment data" refers to a function that collects and receives product search requests and sentiment data entered by users through their terminals.

[0787] "Means for collecting data based on received requests and sentiment data" refers to a function that collects relevant product information and data from the internet and internal databases based on the user's search requests and sentiment data.

[0788] "Means for preprocessing and analyzing collected data" refers to functions that perform preprocessing such as normalizing collected data into an analyzable format or imputing missing values, and then performing data analysis.

[0789] "A means of inputting analysis results into a generative artificial intelligence system using a machine learning algorithm to generate a response" refers to a function that applies a machine learning algorithm based on pre-processed results, and uses generative artificial intelligence to generate specific responses and recommendations to the user's requests as text.

[0790] "A means of formatting generated responses into a template and adding emotionally sensitive content" refers to a function that formats the generated response text and adds headings and explanations that are sensitive to the user's emotions.

[0791] "Means of providing formatted templates to users" refers to a function that sends formatted templates to the user's device, making the information easily accessible to the user.

[0792] Modes for carrying out the invention

[0793] This invention provides a product recommendation system for e-commerce sites that takes into account the emotional state of the user. Specific embodiments of this invention will be described in detail below.

[0794] System configuration and programs to be used

[0795] Hardware and software

[0796] 1. Hardware: Smartphone or tablet

[0797] 2. Software:

[0798] Emotion recognition technology: Image recognition technology is used for facial recognition, and speech recognition technology is used for voice analysis. For example, general image recognition APIs and speech recognition APIs are used.

[0799] Data analysis tools: Python and its libraries (pandas, scikit-learn) will be used.

[0800] Generative artificial intelligence: Uses a generative AI model (e.g., GPT-4).

[0801] Backend server: Uses Node.js and Express.

[0802] Database: Use MySQL.

[0803] Processing flow and data calculations

[0804] The server receives requests and emotional data entered by the user. For example, a user inputs their emotional state using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. As a result, the user's request data and emotional data are sent from the device to the server.

[0805] The server collects relevant product information from the internet and internal databases based on received request and sentiment data. The collected data is preprocessed, for example, by imputing missing values ​​and normalizing it.

[0806] After the preprocessing of the collected data is complete, analysis will be performed. The analysis will be carried out using Python and its libraries (pandas, scikit-learn), and related product information will be analyzed using machine learning algorithms such as clustering.

[0807] Next, the analysis results are input into a generative artificial intelligence (generative AI model) to generate product recommendation text, which is a specific response to the user's request. The following example prompt sentences are input into this generative AI model:

[0808] "Please recommend five relaxation products that would be suitable for users who are feeling anxious."

[0809] The generated responses are formatted into a template with added content that takes the user's emotions into consideration. This template includes headings and descriptions that reflect the user's emotions.

[0810] Finally, a formatted template is provided to the user's device, allowing the user to intuitively view product information.

[0811] Adding specific examples

[0812] For example, if a user requests to learn about the latest gadgets and the system recognizes that the user is also experiencing anxiety, the system will collect relevant gadget information from the internet and its internal database. Based on the analyzed data, a generative AI model will generate detailed text about the latest gadgets, and further add explanatory text that helps alleviate the user's anxiety. This allows the user to obtain information while feeling at ease.

[0813] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0814] Step 1:

[0815] The user inputs their emotional data using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. The input includes the user's emotional data (e.g., nervous, relieved, excited) and product search keys (e.g., "latest gadgets"). The output is the device sending this data to a server.

[0816] Step 2:

[0817] The server receives user requests and sentiment data over the network. It takes user sentiment data and product search request data as input and passes that data to the next processing step as output.

[0818] Step 3:

[0819] The server collects relevant product information based on requests received from the internet and internal databases. It uses user search requests (e.g., "latest gadgets") as input and collects and stores relevant data (e.g., product names, specifications, reviews, etc.) as output.

[0820] Step 4:

[0821] The server preprocesses the collected data and prepares it for analysis. It takes the collected raw data as input, performs specific data processing (imputation of missing values, data normalization), and generates a clean, preprocessed dataset as output.

[0822] Step 5:

[0823] The server analyzes the pre-processed data. It takes a clean dataset as input, analyzes the data using machine learning algorithms (e.g., clustering and regression analysis), and outputs the analysis results.

[0824] Step 6:

[0825] The server inputs the analysis results into a generative AI model to generate specific answers (product recommendation text) to the user's request. The generative AI model is fed with the analysis results and a prompt (for example, "Please recommend 5 relaxation products for when the user is feeling anxious") as input, and the generated answer text is obtained as output.

[0826] Step 7:

[0827] The server formats the generated response text into a template and adds headings and descriptions that take into account the user's emotional state. It takes the generated text and user emotional information as input, formats the headings and additional descriptions, and outputs a final document in template format.

[0828] Step 8:

[0829] The server sends a formatted template to the user's terminal and provides it to the user. It takes a final document in template format as input and sends and displays the document on the user's terminal as output.

[0830] This will enable a system that allows users to obtain product information in an intuitive and emotionally resonant way.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] [Third Embodiment]

[0835] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0836] 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.

[0837] 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).

[0838] 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.

[0839] 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.

[0840] 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).

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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".

[0847] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. This system automatically performs a series of processes, from receiving user requests to collecting, analyzing, and generating responses, and then providing formatted templates.

[0848] 1. System Program

[0849] User request input and reception

[0850] The user enters search terms such as "latest treatments for heart disease" using their device.

[0851] The terminal transmits requests to the system by sending user input to the server.

[0852] Data collection

[0853] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[0854] For example, in the medical field, this would involve gathering the latest research papers, research data, and clinical trial results.

[0855] Data Analysis

[0856] The server analyzes the collected data. This analysis utilizes machine learning algorithms (such as clustering and regression analysis).

[0857] For example, we can extract important keywords and trends related to "the latest treatments for heart disease."

[0858] Answer generation using generative artificial intelligence

[0859] The server uses generative artificial intelligence (for example, AI using natural language processing technology) based on the analysis results to generate specific answers.

[0860] For example, it can automatically generate detailed text about "the latest treatments for heart disease."

[0861] Template formatting

[0862] The server formats the generated text into a user-friendly template format.

[0863] For example, if you are creating a report, it should be structured as follows:

[0864] Title: The Latest Treatments for Heart Disease

[0865] Introduction

[0866] Treatment Overview

[0867] Results of clinical trials

[0868] Precautions and side effects

[0869] summary

[0870] Providing results

[0871] The server sends the formatted template to the user's terminal.

[0872] Users download templates sent from their devices and use them in their work.

[0873] Specific example

[0874] For example, consider the medical field:

[0875] The user enters a request stating, "I want to know about the latest diabetes treatments."

[0876] The terminal sends this request to the server.

[0877] The server collects relevant information from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[0878] The server analyzes the collected data using machine learning algorithms to identify important information.

[0879] The server inputs the analysis results into a generative artificial intelligence system, which then generates a detailed report on the "latest diabetes treatments."

[0880] The server formats the report into a template, including headings, figures, tables, bullet points, etc.

[0881] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[0882] Thus, the present invention is a system that processes user requests quickly and accurately, and provides information directly relevant to practical work. Users can easily obtain and utilize the necessary information even without specialized knowledge.

[0883] The following describes the processing flow.

[0884] Step 1:

[0885] The user enters the search key "latest treatments for heart disease" through their device. This allows the user's request to be collected in a specific format.

[0886] Step 2:

[0887] The terminal sends the user's input request to the server via the network. During this process, the system recognizes the user's request.

[0888] Step 3:

[0889] The server analyzes the received request and generates search queries to collect relevant data based on the request. This enables accurate data collection.

[0890] Step 4:

[0891] The server collects relevant data from publicly available databases on the internet and from internal databases. For example, it retrieves the latest medical papers and clinical trial data.

[0892] Step 5:

[0893] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[0894] Step 6:

[0895] The server inputs preprocessed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis and extract knowledge patterns related to user requests.

[0896] Step 7:

[0897] The server inputs the analysis results into a generative artificial intelligence (e.g., natural language processing AI) to generate response text that meets the user's request. For example, it might create detailed text about "the latest treatments for heart disease."

[0898] Step 8:

[0899] The server formats the generated text into a template. Specifically, it adds headings, bullet points, and, if necessary, figures and tables.

[0900] Step 9:

[0901] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[0902] Step 10:

[0903] Users download templates from their devices and use them in their daily work. For example, they might use the provided reports in treatment plan meetings at a medical institution.

[0904] (Example 1)

[0905] 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."

[0906] Conventional information retrieval systems often fail to respond quickly to user requests, and the information provided frequently does not meet the user's specific needs. In particular, the process of generating useful information using big data is complex and requires specialized knowledge, making it difficult for the average user to utilize. Furthermore, there is a need for more efficient methods for pre-processing and analyzing collected data, as well as for formatting the generated information.

[0907] 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.

[0908] In this invention, the server includes means for receiving requests entered by a user, means for collecting relevant data from a database based on the received requests, means for preprocessing the collected data, means for analyzing the preprocessed data with a machine learning algorithm, means for inputting the analysis results into a generating AI model to generate an answer, means for formatting the generated answer into a template format, and means for providing the formatted template to the user. This enables a system that can respond quickly and accurately to user requests and allows users to easily obtain useful information even without specialized knowledge.

[0909] "Means of receiving requests entered by the user" refers to the function by which the server receives requests such as search keys and questions entered by the user through a terminal.

[0910] "Means of collecting relevant data from a database based on received requests" refers to a function in which a server automatically collects relevant information from publicly available databases on the internet or internal databases in response to user requests.

[0911] "Means for pre-processing collected data" refers to the function of the server that performs pre-processing on the collected data, such as cleansing, format conversion, and noise reduction.

[0912] "Means of analyzing pre-processed data with machine learning algorithms" refers to the function of a server that analyzes pre-processed data using machine learning algorithms (for example, clustering or regression analysis).

[0913] "A means of inputting analysis results into a generative AI model to generate answers" refers to a function in which a server automatically generates specific answers using a generative AI model (for example, an AI using natural language processing technology) based on the results analyzed by a machine learning algorithm.

[0914] "Means of formatting generated responses into a template format" refers to a function that allows the server to convert generated responses into a user-friendly template format (for example, a report format).

[0915] "Means of providing formatted templates to users" refers to a function in which the server sends formatted templates to the user's terminal, allowing the user to download and use them.

[0916] "Means of using the internet and internal databases in data collection" refers to the function of obtaining information by using publicly available databases on the internet or dedicated internal databases during the data collection process.

[0917] "Means for creating prompt statements when inputting analysis results into a generating AI model" refers to a function that constructs prompt statements based on analysis results in order to obtain appropriate output from the generating AI model.

[0918] This invention describes a specific embodiment of a system for automating complex information retrieval and analysis processes and providing useful information in response to user requests. This system uses various hardware and software to automatically execute a series of processes from request reception to result provision.

[0919] System Configuration

[0920] This system mainly consists of the following hardware and software:

[0921] Server: Possesses high-performance data collection, analysis, generation, and formatting capabilities.

[0922] Terminal: A device used by a user to input information (e.g., a personal computer, a smartphone).

[0923] Generative AI models: AI that generates answers using natural language processing techniques (e.g., GPT-3).

[0924] Databases: Publicly accessible databases on the internet and internal databases.

[0925] Process details

[0926] User request input and reception

[0927] The user enters a search key through their device's browser or a dedicated application. For example, they might enter "latest treatments for heart disease." The device sends this request to the server, which then communicates the request to the entire system.

[0928] Data collection

[0929] After receiving a user request, the server collects the relevant data. This collection utilizes publicly available internet databases (e.g., PubMed) and internal databases.

[0930] Data preprocessing

[0931] The server preprocesses the collected data. This preprocessing includes data cleansing, format conversion, and noise reduction.

[0932] Data Analysis

[0933] The server performs analysis on the preprocessed data using machine learning algorithms (e.g., clustering, regression analysis). Through this analysis, important keywords and trends are extracted.

[0934] Answer generation using generative artificial intelligence

[0935] The server generates a prompt based on the analysis results and inputs it into the AI ​​model to generate an answer. For example, the prompt might look like this:

[0936] "Provide the latest treatments for heart disease based on these key findings: ..."

[0937] Template formatting

[0938] The generated responses are formatted by the server into a template. This template is in a user-friendly format for reports and presentations. For example, the template format may look like this:

[0939] Title: The Latest Treatments for Heart Disease

[0940] Introduction

[0941] Treatment Overview

[0942] Results of clinical trials

[0943] Precautions and side effects

[0944] summary

[0945] Providing results

[0946] The formatted template is sent from the server to the user's terminal. The user can download this template and use it in their work.

[0947] Specific example

[0948] For example, in the medical field, a user might input a request such as "I want to know about the latest diabetes treatments," and their device sends this request to a server. The server uses the internet and internal databases to collect relevant information and preprocess the data. Using the preprocessed data, it performs analysis using machine learning algorithms and inputs prompts into a generative AI model to generate an answer. The generated answer is formatted into a template and sent to the user's device. The user downloads the template and uses it in their daily work in the medical field.

[0949] Through the above process, the system of the present invention can provide users with information quickly and with high accuracy.

[0950] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0951] Step 1:

[0952] The user enters a search term on their device. For example, they might type "latest treatments for heart disease."

[0953] The terminal receives user input and sends that request to the server. The input data is the user's request, and this becomes the basis for the next step.

[0954] Step 2:

[0955] The server receives user requests and collects relevant data from the internet and internal databases. This collected data may include, for example, publicly available papers, research data, and clinical trial results.

[0956] In practice, the server uses an API to query the database. The input is the user's request, and the output is the relevant raw data.

[0957] Step 3:

[0958] The server preprocesses the collected data. This preprocessing includes data cleansing (deduplication and noise reduction), format conversion, and other steps.

[0959] The input is the collected raw data, and the output is pre-processed, clean data. Specifically, the data cleansing is performed using Python code.

[0960] Step 4:

[0961] The server performs analysis using machine learning algorithms based on preprocessed data. For example, it extracts important keywords and trends using clustering methods and regression analysis.

[0962] The input is pre-processed data, and the output is the analysis result. Specifically, the analysis is performed using libraries such as scikit-learn.

[0963] Step 5:

[0964] The server generates prompt sentences based on the analysis results and inputs them into a generative AI model to generate an answer. Here, for example, an AI (generative AI model) using natural language processing technology is used.

[0965] The input is the analysis result, which is the prompt text to be input into the generating AI model. The output is the generated detailed answer. Examples of specific prompt texts are as follows:

[0966] "Provide the latest treatments for heart disease based on these key findings: ..."

[0967] Step 6:

[0968] The server formats the generated responses into a template format. This is the process of converting them into a user-friendly format for reports and presentation materials.

[0969] The input is the response from a generative AI model, and the output is a document formatted in a template. Examples of specific template formats are as follows:

[0970] Title: The Latest Treatments for Heart Disease

[0971] Introduction

[0972] Treatment Overview

[0973] Results of clinical trials

[0974] Precautions and side effects

[0975] summary

[0976] Step 7:

[0977] The server sends the formatted template to the user's terminal.

[0978] The input is a document formatted into a template, and the output is a formatted template sent to the user's terminal.

[0979] Users can download formatted templates on their devices and use them in their work.

[0980] (Application Example 1)

[0981] 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."

[0982] In today's information society, it is becoming increasingly important for users to access the latest and most useful information. Information regarding electronic payment services, in particular, is evolving rapidly, requiring users to accurately understand trends, convenience, and points to be aware of. However, traditional information gathering methods require users to manually search and analyze large amounts of data, which is time-consuming and laborious, and the reliability of the information is inconsistent. Therefore, there is a need for more efficient information delivery methods.

[0983] 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.

[0984] In this invention, the server includes means for receiving requests entered by a user, means for collecting data based on the received requests, means for analyzing the collected data, means for converting the analysis results into answers using generative artificial intelligence, means for formatting the answers into a template format, means for providing the formatted template to the user, means for receiving user input and sending it to a server on the cloud, and means for using natural language processing technology for analyzing the collected data. This makes it possible for users to efficiently and accurately obtain the latest trend information on electronic payments even without specialized knowledge.

[0985] "Means for receiving requests entered by a user" refers to the hardware or software mechanism by which a system receives requests entered by a user to obtain specific information.

[0986] "Means for collecting data based on received requests" refers to a system that automatically collects data corresponding to user requests from the internet or internal databases.

[0987] "Means for analyzing collected data" refers to algorithms and technologies used to analyze collected data and extract necessary information and trends.

[0988] "Means of converting analysis results into answers using generative artificial intelligence" refers to a system that generates actual answers using generative artificial intelligence (for example, natural language processing technology) based on the analyzed data.

[0989] "Methods for formatting responses into a template format" refers to methods for converting generated responses into a template format that is easy for users to understand.

[0990] "Means of providing users with formatted templates" refers to a mechanism that sends formatted information to the user's device, allowing the user to receive and use it.

[0991] "Means of receiving user input and sending it to a server on the cloud" refers to a method of receiving a user's request and sending it to a server on a cloud service.

[0992] "Methods for using natural language processing technology in the analysis of collected data" refers to techniques that use natural language processing technology to automatically extract important information when analyzing collected data.

[0993] The system implementing this invention automatically generates and provides useful information using big data in response to user requests. This system is broadly composed of the following hardware and software elements.

[0994] 1. Hardware and software used

[0995] hardware

[0996] User terminal: A device that can connect to the internet, such as a smartphone or smart glasses, is used.

[0997] Cloud server: A server is required for data collection, analysis, and provision of generated information.

[0998] software

[0999] Flask: Used as an API server on a cloud server.

[1000] Generative AI: Specifically, generative AI models that utilize natural language processing technologies such as OpenAI GPT-3 are used.

[1001] 2. Data Processing and Data Calculation Flow

[1002] Receiving user input

[1003] The user uses a smartphone or smart glasses to input a request for specific information. For example, they might input, "Tell me about the latest cashless payment trends." The user's device sends this request to a cloud server.

[1004] Data collection

[1005] The server collects relevant information from the internet and internal databases based on the received request. This collected data includes the latest news, reports, articles, and user reviews.

[1006] Data Analysis

[1007] The server automatically analyzes the collected data using natural language processing technology. This analysis extracts important keywords and trends related to the requests.

[1008] Answer generation

[1009] Using generative artificial intelligence (GPT-3), specific answers are generated based on the analyzed data. The generated answers are presented in a format that is easy for the user to understand.

[1010] Template formatting

[1011] The server formats the generated responses into a user-friendly template. For example, it might be structured as follows:

[1012] Title: Latest Cashless Payment Trends

[1013] Introduction

[1014] Overview of payment methods

[1015] Details and convenience of each method

[1016] Points to note

[1017] summary

[1018] Providing results

[1019] The server sends a formatted template to the user's terminal, and the user receives and views this information.

[1020] Examples of specific cases and prompt statements

[1021] For example, suppose a user types "Tell me the latest cashless payment trends" into their smartphone. This request is immediately sent to a cloud server, where it undergoes automated analysis and AI generation to produce a detailed and structured report. The user can then receive the information directly in report format.

[1022] Example of a prompt

[1023] "Please tell me about the latest cashless payment trends. Include key points, trends, convenience, and points to note."

[1024] This prompt allows generative artificial intelligence to automatically generate detailed answers, enabling it to respond quickly and accurately to the information the user is seeking.

[1025] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1026] Step 1:

[1027] The user inputs specific information using a smartphone or smart glasses. For example, they might input a request such as, "Tell me about the latest cashless payment trends." The input request is then sent from the device to a server in the cloud.

[1028] Input: User request (e.g., "Tell me about the latest cashless payment trends")

[1029] Output: Request data sent to the cloud server

[1030] Step 2:

[1031] The server receives requests sent by users. Based on the received requests, it collects relevant data. The server collects relevant information from publicly available databases on the internet and from its own internal databases. This includes, for example, the latest news, reports, papers, and user reviews.

[1032] Input: Request data sent to the cloud server

[1033] Output: Collected data (latest news, reports, papers, user reviews, etc.)

[1034] Step 3:

[1035] The server analyzes the collected data. This analysis utilizes natural language processing techniques, including keyword extraction and trend analysis.

[1036] Input: Collected data

[1037] Output: Analysis results (extraction of important keywords and trends)

[1038] Step 4:

[1039] The server generates specific answers using generative artificial intelligence (such as GPT-3) based on the analysis results. A prompt (e.g., "Tell me about the latest cashless payment trends") is input to the generative AI model to obtain a detailed response.

[1040] Input: Analysis result, prompt message

[1041] Output: Generated answer text

[1042] Step 5:

[1043] The server formats the generated response text into a user-friendly template format. For example, it might be structured as follows: Title, Introduction, Overview of Payment Methods, Details and Convenience of Each Method, Points to Note, Summary.

[1044] Input: Generated response text

[1045] Output: Answer text formatted in template format

[1046] Step 6:

[1047] The server provides a formatted template to the user's terminal. The terminal receives the template, and the user views the results on their smartphone or smart glasses.

[1048] Input: Answer text formatted in template format

[1049] Output: Sending to the user's terminal, allowing the user to view the results.

[1050] 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.

[1051] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. In particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to provide even more accurate information. This system automatically performs a series of processes, from receiving the user's request to collecting and analyzing the necessary data, generating the response, formatting it, and providing an emotion-conscious template.

[1052] 1. System Program

[1053] User request input and reception

[1054] The user enters their emotional state (e.g., nervous, relieved, excited) along with the search keyword "latest treatments for heart disease" via their device. Emotions can also be automatically collected through facial recognition or voice analysis.

[1055] The terminal transmits the user's input requests and emotional data to the server via the network.

[1056] Data collection

[1057] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[1058] For example, obtaining the latest medical papers and clinical trial data.

[1059] Data Analysis

[1060] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[1061] The server inputs preprocessed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis and extract knowledge patterns related to user requests.

[1062] Emotional analysis using an emotion engine

[1063] The server uses the user's emotional data to input into the emotion engine, which then analyzes the emotional state.

[1064] For example, if a user is feeling anxious, information to generate a relaxing response should also be considered.

[1065] Answer generation using generative artificial intelligence

[1066] The server uses generative artificial intelligence based on the analysis results and sentiment analysis results to generate specific response text to the user's request.

[1067] For example, it can generate detailed text about "the latest treatments for heart disease" and add content that takes the user's emotions into consideration.

[1068] Template formatting

[1069] The server formats the generated text into a template. It adds headings and descriptions that reflect the user's emotional state.

[1070] For example, include headings, bullet points, charts, and other elements to provide reassuring language and explanations to users.

[1071] Providing results

[1072] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[1073] Users download templates from their devices and use them in their daily work. The provided reports could also be used in treatment plan meetings at medical institutions.

[1074] Specific example

[1075] For example, consider the medical field:

[1076] When a user requests to learn about the latest diabetes treatments, they simultaneously input their emotions at the time of making that request (e.g., anxiety).

[1077] The terminal sends this request to the server.

[1078] The server collects relevant data from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[1079] The server analyzes the collected data using machine learning algorithms to identify important information.

[1080] The server analyzes the user's emotional state (anxiety) using an emotion engine and derives elements that provide a sense of security.

[1081] The server uses generative artificial intelligence to generate a detailed report on the "latest diabetes treatments," adding reassuring content.

[1082] The server formats the report into a template, adding headings, charts, and reassuring explanatory text.

[1083] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[1084] Thus, the present invention is a system that takes user emotions into consideration to realize more personalized and highly accurate information delivery. Users can easily obtain the necessary information even without specialized knowledge and use it in a way that is sensitive to their emotions.

[1085] The following describes the processing flow.

[1086] Step 1:

[1087] The user enters their emotional state (e.g., anxiety, relief) along with the search keyword "latest treatments for heart disease" via their device. Emotions, in particular, can be automatically collected through facial recognition or voice analysis.

[1088] Step 2:

[1089] The terminal transmits the user's input requests and emotional data to the server via the network. This sends the user's specific requests and their emotions at that time to the system.

[1090] Step 3:

[1091] The server receives a user request and generates a search query based on its content. This query is used to collect specific data, such as "the latest treatments for heart disease."

[1092] Step 4:

[1093] The server accesses publicly available databases on the internet and internal databases to collect relevant data. This collected data includes the latest medical papers, research data, and clinical trial results.

[1094] Step 5:

[1095] The server preprocesses the collected data. Data preprocessing includes normalization, imputation of missing data, and standardization of format. This prepares the data in a format that can be analyzed.

[1096] Step 6:

[1097] The server inputs pre-processed data into machine learning algorithms (e.g., clustering or regression analysis) to perform data analysis. The goal of the analysis is to extract the knowledge and patterns most relevant to the user's requirements.

[1098] Step 7:

[1099] The server inputs the user's emotional data into the emotion engine and analyzes their emotional state. Based on the results of the emotion analysis, it identifies the user's current emotional state.

[1100] Step 8:

[1101] The server integrates the analysis results and sentiment analysis results, and uses generative artificial intelligence to generate specific response text to the user's request. For example, if the user is looking for information on "the latest treatments for heart disease," it will generate detailed text in response to that request, and further add content that takes into account the user's emotions (such as anxiety).

[1102] Step 9:

[1103] The server formats the generated text into a template. This formatting process includes adding headings, bullet points, and, if necessary, charts and graphs. It also adds reassuring language and explanations based on the user's emotional state.

[1104] Step 10:

[1105] The server sends a formatted template to the user's terminal. During this process, the necessary information is provided in a format that is easy for the user to understand.

[1106] Step 11:

[1107] Users review and download templates sent via their devices. These templates include reassuring explanations and specific treatment methods, providing the necessary information for practical use. For example, they can be used in treatment planning meetings at medical institutions.

[1108] (Example 2)

[1109] 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."

[1110] In recent years, with the advancement of information technology, users are required to quickly and accurately obtain the information they need from vast amounts of data. However, conventional systems provide information without considering the user's emotional state, resulting in low user satisfaction. Furthermore, the analysis of collected data does not always provide the most optimal information. As a result, the accuracy and personalization of the information users need are insufficient, making it difficult to obtain information, especially in fields requiring specialized knowledge.

[1111] 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.

[1112] In this invention, the server includes means for receiving requests and emotional states entered by the user, means for collecting data from a public database and an internal database based on the received requests, and means for preprocessing and analyzing the collected data. This enables personalized and highly accurate information provision that takes the user's emotional state into consideration.

[1113] A "user" is an entity that uses a system to search for and receive information.

[1114] A "request" refers to the search keys or questions that a user enters into the system.

[1115] "Emotional state" refers to the state of the user's emotions (e.g., tension, relief, excitement), and is data collected through facial recognition, voice analysis, etc.

[1116] A "public database" refers to an information source that exists on the internet and is accessible to anyone (e.g., academic paper databases, open data platforms).

[1117] An "internal database" is a private database managed by the system owner, accessible only to users or specific stakeholders.

[1118] "Preprocessing" refers to the process of preparing collected data into an analyzable format, and specifically includes data normalization, imputation of missing values, and removal of unnecessary information.

[1119] "Analysis" is the process of using collected and pre-processed data to extract knowledge patterns related to user requests using machine learning algorithms or similar methods.

[1120] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state and output the results of that emotional analysis.

[1121] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates appropriate text and responses based on analysis results.

[1122] A "template format" is a visually formatted format that makes generated responses easy for users to understand, and includes headings, paragraphs, bullet points, charts, and other elements.

[1123] A "server" refers to a computer system that processes data for the entire system, performing the steps of collection, analysis, generation, and delivery.

[1124] "Terminal" refers to a device used by a user to input requests and receive results.

[1125] This invention is a system that provides useful information based on user requests, and in particular, improves the accuracy of information provision by taking into account the user's emotional state. This system consists of a series of processing steps: inputting and receiving requests from the user, collecting data, analyzing data, performing emotional analysis using an emotion engine, generating responses using generative artificial intelligence, formatting templates, and providing results.

[1126] User request input and reception

[1127] The user enters a search key (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) through the device. The user's emotional state can also be automatically collected through facial recognition using the device's camera and microphone, or through voice analysis. The device sends the request and emotional data to the server via a secure communication protocol (e.g., HTTPS).

[1128] Data collection

[1129] After receiving a user request, the server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal databases. The collected data is temporarily stored in storage.

[1130] Data Analysis

[1131] The server preprocesses the collected data, preparing it for analysis. This preprocessing includes data normalization, imputation of missing values, and removal of unnecessary information. The preprocessed data is then fed into machine learning algorithms (e.g., clustering, regression analysis) to extract knowledge patterns that meet the user's requirements. The analysis results are stored as structured data.

[1132] Emotional analysis using an emotion engine

[1133] The server inputs the user's emotional data into the emotion engine, which then analyzes the user's emotional state. For example, if the user is "stressed," the emotion engine generates elements to help the user relax. The results of the emotional analysis are then reflected in the subsequent response generation by the generative artificial intelligence system.

[1134] Answer generation using generative artificial intelligence

[1135] The server integrates the analysis results and sentiment analysis results and generates specific response text using generative artificial intelligence (e.g., GPT models). For example, it generates a response that combines detailed text about "the latest treatments for heart disease" with phrases that alleviate the user's anxiety.

[1136] Template formatting

[1137] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other visual elements to make the information easier for users to understand. Furthermore, it applies templates tailored to the user's emotional state, adding elements that create a sense of security.

[1138] Providing results

[1139] The server sends a formatted template as the final answer to the user's terminal. The user downloads the provided template via their terminal and uses it as actual reference material. If necessary, the template can also be printed or shared with other users.

[1140] Specific example

[1141] A concrete example of a prompt might be, "I want to learn about the latest diabetes treatments. Please also include information that will alleviate my anxieties." Based on this prompt, the system collects medical data and generates information that includes elements to reduce anxiety. The resulting template would include detailed information about the latest diabetes treatments and explanations to alleviate anxiety.

[1142] Thus, the present invention is a system that provides personalized and highly accurate information while taking into consideration the user's emotions. As a result, users can easily obtain the necessary information even without specialized knowledge and use it in a way that is sensitive to their emotions.

[1143] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1144] Step 1: Inputting and receiving requests from the user.

[1145] Users enter search keywords (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) via their device. Emotional states may also be automatically collected using facial recognition or voice analysis via the device's camera and microphone.

[1146] Input: User request (search key) and sentiment state data

[1147] Output: Packetized data of user requests and emotional states

[1148] The terminal sends the generated packetized data to the server using a secure communication protocol (e.g., HTTPS).

[1149] Step 2: Data Collection

[1150] The server analyzes the user's request data and generates queries to collect the requested information.

[1151] Input: User's requested data

[1152] Output: Database query

[1153] The server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal company databases.

[1154] Input: Database query

[1155] Output: Collected data (medical papers, clinical trial data, etc.)

[1156] The server stores the collected data in temporary storage.

[1157] Step 3: Data Analysis

[1158] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data, imputing missing values, and removing unnecessary information.

[1159] Input: Collected data

[1160] Output: Preprocessed data

[1161] The server inputs pre-processed data into machine learning algorithms (e.g., clustering, regression analysis) to extract knowledge patterns that meet the user's requirements.

[1162] Input: Preprocessed data

[1163] Output: Analysis results (structured data)

[1164] Step 4: Emotional analysis using the emotion engine

[1165] The server inputs the user's emotional state data into the emotion engine and analyzes the emotional state.

[1166] Input: User's emotional state data

[1167] Output: Emotion analysis results (identification of emotional state, suggestions for appropriate responses, etc.)

[1168] For example, if a user is feeling "stressed," the emotion engine will generate elements that promote "relaxation."

[1169] Step 5: Generating answers using generative artificial intelligence

[1170] The server uses generative artificial intelligence (e.g., GPT models) to generate specific response text based on the analysis results and sentiment analysis results.

[1171] Input: Analysis results and sentiment analysis results

[1172] Output: Specific answer text

[1173] For example, the system generates responses that combine detailed text about "the latest treatments for heart disease" with phrases designed to ease the user's anxiety.

[1174] Step 6: Template Formatting

[1175] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other elements.

[1176] Input: Generated response text

[1177] Output: Template-formatted answer

[1178] Furthermore, templates tailored to the user's emotional state are applied, and elements that help users feel more secure are added.

[1179] Step 7: Results Provision

[1180] The server sends the formatted template to the user's terminal.

[1181] Input: Template-style answer

[1182] Output: Template-formatted response sent to the user's device.

[1183] Users download templates provided through their devices and use them in their work. They can also print templates or share them with other users as needed.

[1184] (Application Example 2)

[1185] 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."

[1186] Traditional e-commerce sites offer systems that recommend products based on user requests, but these recommendations do not take into account the user's emotional state, making it difficult to improve user psychological satisfaction. Therefore, when a user is stressed or agitated, the system fails to recommend suitable products, hindering the improvement of the user experience. Furthermore, it has not been possible to provide personalized information that reflects the user's emotional state.

[1187] 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.

[1188] In this invention, the server includes means for receiving requests and emotional data entered by the user, means for collecting data based on the received requests and emotional data, and means for preprocessing and analyzing the collected data. This enables product recommendations tailored to the user's emotional state, improves the user's psychological satisfaction, and provides personalized, highly accurate information.

[1189] "Means for receiving user-inputted requests and sentiment data" refers to a function that collects and receives product search requests and sentiment data entered by users through their terminals.

[1190] "Means for collecting data based on received requests and sentiment data" refers to a function that collects relevant product information and data from the internet and internal databases based on the user's search requests and sentiment data.

[1191] "Means for preprocessing and analyzing collected data" refers to functions that perform preprocessing such as normalizing collected data into an analyzable format or imputing missing values, and then performing data analysis.

[1192] "A means of inputting analysis results into a generative artificial intelligence system using a machine learning algorithm to generate a response" refers to a function that applies a machine learning algorithm based on pre-processed results, and uses generative artificial intelligence to generate specific responses and recommendations to the user's requests as text.

[1193] "A means of formatting generated responses into a template and adding emotionally sensitive content" refers to a function that formats the generated response text and adds headings and explanations that are sensitive to the user's emotions.

[1194] "Means of providing formatted templates to users" refers to a function that sends formatted templates to the user's device, making the information easily accessible to the user.

[1195] Modes for carrying out the invention

[1196] This invention provides a product recommendation system for e-commerce sites that takes into account the emotional state of the user. Specific embodiments of this invention will be described in detail below.

[1197] System configuration and programs to be used

[1198] Hardware and software

[1199] 1. Hardware: Smartphone or tablet

[1200] 2. Software:

[1201] Emotion recognition technology: Image recognition technology is used for facial recognition, and speech recognition technology is used for voice analysis. For example, general image recognition APIs and speech recognition APIs are used.

[1202] Data analysis tools: Python and its libraries (pandas, scikit-learn) will be used.

[1203] Generative artificial intelligence: Uses a generative AI model (e.g., GPT-4).

[1204] Backend server: Uses Node.js and Express.

[1205] Database: Use MySQL.

[1206] Processing flow and data calculations

[1207] The server receives requests and emotional data entered by the user. For example, a user inputs their emotional state using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. As a result, the user's request data and emotional data are sent from the device to the server.

[1208] The server collects relevant product information from the internet and internal databases based on received request and sentiment data. The collected data is preprocessed, for example, by imputing missing values ​​and normalizing it.

[1209] After the preprocessing of the collected data is complete, analysis will be performed. The analysis will be carried out using Python and its libraries (pandas, scikit-learn), and related product information will be analyzed using machine learning algorithms such as clustering.

[1210] Next, the analysis results are input into a generative artificial intelligence (generative AI model) to generate product recommendation text, which is a specific response to the user's request. The following example prompt sentences are input into this generative AI model:

[1211] "Please recommend five relaxation products that would be suitable for users who are feeling anxious."

[1212] The generated responses are formatted into a template with added content that takes the user's emotions into consideration. This template includes headings and descriptions that reflect the user's emotions.

[1213] Finally, a formatted template is provided to the user's device, allowing the user to intuitively view product information.

[1214] Adding specific examples

[1215] For example, if a user requests to learn about the latest gadgets and the system recognizes that the user is also experiencing anxiety, the system will collect relevant gadget information from the internet and its internal database. Based on the analyzed data, a generative AI model will generate detailed text about the latest gadgets, and further add explanatory text that helps alleviate the user's anxiety. This allows the user to obtain information while feeling at ease.

[1216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1217] Step 1:

[1218] The user inputs their emotional data using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. The input includes the user's emotional data (e.g., nervous, relieved, excited) and product search keys (e.g., "latest gadgets"). The output is the device sending this data to a server.

[1219] Step 2:

[1220] The server receives user requests and sentiment data over the network. It takes user sentiment data and product search request data as input and passes that data to the next processing step as output.

[1221] Step 3:

[1222] The server collects relevant product information based on requests received from the internet and internal databases. It uses user search requests (e.g., "latest gadgets") as input and collects and stores relevant data (e.g., product names, specifications, reviews, etc.) as output.

[1223] Step 4:

[1224] The server preprocesses the collected data and prepares it for analysis. It takes the collected raw data as input, performs specific data processing (imputation of missing values, data normalization), and generates a clean, preprocessed dataset as output.

[1225] Step 5:

[1226] The server analyzes the pre-processed data. It takes a clean dataset as input, analyzes the data using machine learning algorithms (e.g., clustering and regression analysis), and outputs the analysis results.

[1227] Step 6:

[1228] The server inputs the analysis results into a generative AI model to generate specific answers (product recommendation text) to the user's request. The generative AI model is fed with the analysis results and a prompt (for example, "Please recommend 5 relaxation products for when the user is feeling anxious") as input, and the generated answer text is obtained as output.

[1229] Step 7:

[1230] The server formats the generated response text into a template and adds headings and descriptions that take into account the user's emotional state. It takes the generated text and user emotional information as input, formats the headings and additional descriptions, and outputs a final document in template format.

[1231] Step 8:

[1232] The server sends a formatted template to the user's terminal and provides it to the user. It takes a final document in template format as input and sends and displays the document on the user's terminal as output.

[1233] This will enable a system that allows users to obtain product information in an intuitive and emotionally resonant way.

[1234] 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.

[1235] 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.

[1236] 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.

[1237] [Fourth Embodiment]

[1238] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1239] 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.

[1240] 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).

[1241] 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.

[1242] 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.

[1243] 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).

[1244] 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.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] 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.

[1249] 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.

[1250] 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".

[1251] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. This system automatically performs a series of processes, from receiving user requests to collecting, analyzing, and generating responses, and then providing formatted templates.

[1252] 1. System Program

[1253] User request input and reception

[1254] The user enters search terms such as "latest treatments for heart disease" using their device.

[1255] The terminal transmits requests to the system by sending user input to the server.

[1256] Data collection

[1257] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[1258] For example, in the medical field, this would involve gathering the latest research papers, research data, and clinical trial results.

[1259] Data Analysis

[1260] The server analyzes the collected data. This analysis utilizes machine learning algorithms (such as clustering and regression analysis).

[1261] For example, we can extract important keywords and trends related to "the latest treatments for heart disease."

[1262] Answer generation using generative artificial intelligence

[1263] The server uses generative artificial intelligence (for example, AI using natural language processing technology) based on the analysis results to generate specific answers.

[1264] For example, it can automatically generate detailed text about "the latest treatments for heart disease."

[1265] Template formatting

[1266] The server formats the generated text into a user-friendly template format.

[1267] For example, if you are creating a report, it should be structured as follows:

[1268] Title: The Latest Treatments for Heart Disease

[1269] Introduction

[1270] Treatment Overview

[1271] Results of clinical trials

[1272] Precautions and side effects

[1273] summary

[1274] Providing results

[1275] The server sends the formatted template to the user's terminal.

[1276] Users download templates sent from their devices and use them in their work.

[1277] Specific example

[1278] For example, consider the medical field:

[1279] The user enters a request stating, "I want to know about the latest diabetes treatments."

[1280] The terminal sends this request to the server.

[1281] The server collects relevant information from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[1282] The server analyzes the collected data using machine learning algorithms to identify important information.

[1283] The server inputs the analysis results into a generative artificial intelligence system, which then generates a detailed report on the "latest diabetes treatments."

[1284] The server formats the report into a template, including headings, figures, tables, bullet points, etc.

[1285] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[1286] Thus, the present invention is a system that processes user requests quickly and accurately, and provides information directly relevant to practical work. Users can easily obtain and utilize the necessary information even without specialized knowledge.

[1287] The following describes the processing flow.

[1288] Step 1:

[1289] The user enters the search key "latest treatments for heart disease" through their device. This allows the user's request to be collected in a specific format.

[1290] Step 2:

[1291] The terminal sends the user's input request to the server via the network. During this process, the system recognizes the user's request.

[1292] Step 3:

[1293] The server analyzes the received request and generates search queries to collect relevant data based on the request. This enables accurate data collection.

[1294] Step 4:

[1295] The server collects relevant data from publicly available databases on the internet and from internal databases. For example, it retrieves the latest medical papers and clinical trial data.

[1296] Step 5:

[1297] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[1298] Step 6:

[1299] The server inputs preprocessed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis and extract knowledge patterns related to user requests.

[1300] Step 7:

[1301] The server inputs the analysis results into a generative artificial intelligence (e.g., natural language processing AI) to generate response text that meets the user's request. For example, it might create detailed text about "the latest treatments for heart disease."

[1302] Step 8:

[1303] The server formats the generated text into a template. Specifically, it adds headings, bullet points, and, if necessary, figures and tables.

[1304] Step 9:

[1305] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[1306] Step 10:

[1307] Users download templates from their devices and use them in their daily work. For example, they might use the provided reports in treatment plan meetings at a medical institution.

[1308] (Example 1)

[1309] 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".

[1310] Conventional information retrieval systems often fail to respond quickly to user requests, and the information provided frequently does not meet the user's specific needs. In particular, the process of generating useful information using big data is complex and requires specialized knowledge, making it difficult for the average user to utilize. Furthermore, there is a need for more efficient methods for pre-processing and analyzing collected data, as well as for formatting the generated information.

[1311] 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.

[1312] In this invention, the server includes means for receiving requests entered by a user, means for collecting relevant data from a database based on the received requests, means for preprocessing the collected data, means for analyzing the preprocessed data with a machine learning algorithm, means for inputting the analysis results into a generating AI model to generate an answer, means for formatting the generated answer into a template format, and means for providing the formatted template to the user. This enables a system that can respond quickly and accurately to user requests and allows users to easily obtain useful information even without specialized knowledge.

[1313] "Means of receiving requests entered by the user" refers to the function by which the server receives requests such as search keys and questions entered by the user through a terminal.

[1314] "Means of collecting relevant data from a database based on received requests" refers to a function in which a server automatically collects relevant information from publicly available databases on the internet or internal databases in response to user requests.

[1315] "Means for pre-processing collected data" refers to the function of the server that performs pre-processing on the collected data, such as cleansing, format conversion, and noise reduction.

[1316] "Means of analyzing pre-processed data with machine learning algorithms" refers to the function of a server that analyzes pre-processed data using machine learning algorithms (for example, clustering or regression analysis).

[1317] "A means of inputting analysis results into a generative AI model to generate answers" refers to a function in which a server automatically generates specific answers using a generative AI model (for example, an AI using natural language processing technology) based on the results analyzed by a machine learning algorithm.

[1318] "Means of formatting generated responses into a template format" refers to a function that allows the server to convert generated responses into a user-friendly template format (for example, a report format).

[1319] "Means of providing formatted templates to users" refers to a function in which the server sends formatted templates to the user's terminal, allowing the user to download and use them.

[1320] "Means of using the internet and internal databases in data collection" refers to the function of obtaining information by using publicly available databases on the internet or dedicated internal databases during the data collection process.

[1321] "Means for creating prompt statements when inputting analysis results into a generating AI model" refers to a function that constructs prompt statements based on analysis results in order to obtain appropriate output from the generating AI model.

[1322] This invention describes a specific embodiment of a system for automating complex information retrieval and analysis processes and providing useful information in response to user requests. This system uses various hardware and software to automatically execute a series of processes from request reception to result provision.

[1323] System Configuration

[1324] This system mainly consists of the following hardware and software:

[1325] Server: Possesses high-performance data collection, analysis, generation, and formatting capabilities.

[1326] Terminal: A device used by a user to input information (e.g., a personal computer, a smartphone).

[1327] Generative AI models: AI that generates answers using natural language processing techniques (e.g., GPT-3).

[1328] Databases: Publicly accessible databases on the internet and internal databases.

[1329] Process details

[1330] User request input and reception

[1331] The user enters a search key through their device's browser or a dedicated application. For example, they might enter "latest treatments for heart disease." The device sends this request to the server, which then communicates the request to the entire system.

[1332] Data collection

[1333] After receiving a user request, the server collects the relevant data. This collection utilizes publicly available internet databases (e.g., PubMed) and internal databases.

[1334] Data preprocessing

[1335] The server preprocesses the collected data. This preprocessing includes data cleansing, format conversion, and noise reduction.

[1336] Data Analysis

[1337] The server performs analysis on the preprocessed data using machine learning algorithms (e.g., clustering, regression analysis). Through this analysis, important keywords and trends are extracted.

[1338] Answer generation using generative artificial intelligence

[1339] The server generates a prompt based on the analysis results and inputs it into the AI ​​model to generate an answer. For example, the prompt might look like this:

[1340] "Provide the latest treatments for heart disease based on these key findings: ..."

[1341] Template formatting

[1342] The generated responses are formatted by the server into a template. This template is in a user-friendly format for reports and presentations. For example, the template format may look like this:

[1343] Title: The Latest Treatments for Heart Disease

[1344] Introduction

[1345] Treatment Overview

[1346] Results of clinical trials

[1347] Precautions and side effects

[1348] summary

[1349] Providing results

[1350] The formatted template is sent from the server to the user's terminal. The user can download this template and use it in their work.

[1351] Specific example

[1352] For example, in the medical field, a user might input a request such as "I want to know about the latest diabetes treatments," and their device sends this request to a server. The server uses the internet and internal databases to collect relevant information and preprocess the data. Using the preprocessed data, it performs analysis using machine learning algorithms and inputs prompts into a generative AI model to generate an answer. The generated answer is formatted into a template and sent to the user's device. The user downloads the template and uses it in their daily work in the medical field.

[1353] Through the above process, the system of the present invention can provide users with information quickly and with high accuracy.

[1354] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1355] Step 1:

[1356] The user enters a search term on their device. For example, they might type "latest treatments for heart disease."

[1357] The terminal receives user input and sends that request to the server. The input data is the user's request, and this becomes the basis for the next step.

[1358] Step 2:

[1359] The server receives user requests and collects relevant data from the internet and internal databases. This collected data may include, for example, publicly available papers, research data, and clinical trial results.

[1360] In practice, the server uses an API to query the database. The input is the user's request, and the output is the relevant raw data.

[1361] Step 3:

[1362] The server preprocesses the collected data. This preprocessing includes data cleansing (deduplication and noise reduction), format conversion, and other steps.

[1363] The input is the collected raw data, and the output is pre-processed, clean data. Specifically, the data cleansing is performed using Python code.

[1364] Step 4:

[1365] The server performs analysis using machine learning algorithms based on preprocessed data. For example, it extracts important keywords and trends using clustering methods and regression analysis.

[1366] The input is pre-processed data, and the output is the analysis result. Specifically, the analysis is performed using libraries such as scikit-learn.

[1367] Step 5:

[1368] The server generates prompt sentences based on the analysis results and inputs them into a generative AI model to generate an answer. Here, for example, an AI (generative AI model) using natural language processing technology is used.

[1369] The input is the analysis result, which is the prompt text to be input into the generating AI model. The output is the generated detailed answer. Examples of specific prompt texts are as follows:

[1370] "Provide the latest treatments for heart disease based on these key findings: ..."

[1371] Step 6:

[1372] The server formats the generated responses into a template format. This is the process of converting them into a user-friendly format for reports and presentation materials.

[1373] The input is the response from a generative AI model, and the output is a document formatted in a template. Examples of specific template formats are as follows:

[1374] Title: The Latest Treatments for Heart Disease

[1375] Introduction

[1376] Treatment Overview

[1377] Results of clinical trials

[1378] Precautions and side effects

[1379] summary

[1380] Step 7:

[1381] The server sends the formatted template to the user's terminal.

[1382] The input is a document formatted into a template, and the output is a formatted template sent to the user's terminal.

[1383] Users can download formatted templates on their devices and use them in their work.

[1384] (Application Example 1)

[1385] 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".

[1386] In today's information society, it is becoming increasingly important for users to access the latest and most useful information. Information regarding electronic payment services, in particular, is evolving rapidly, requiring users to accurately understand trends, convenience, and points to be aware of. However, traditional information gathering methods require users to manually search and analyze large amounts of data, which is time-consuming and laborious, and the reliability of the information is inconsistent. Therefore, there is a need for more efficient information delivery methods.

[1387] 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.

[1388] In this invention, the server includes means for receiving requests entered by a user, means for collecting data based on the received requests, means for analyzing the collected data, means for converting the analysis results into answers using generative artificial intelligence, means for formatting the answers into a template format, means for providing the formatted template to the user, means for receiving user input and sending it to a server on the cloud, and means for using natural language processing technology for analyzing the collected data. This makes it possible for users to efficiently and accurately obtain the latest trend information on electronic payments even without specialized knowledge.

[1389] "Means for receiving requests entered by a user" refers to the hardware or software mechanism by which a system receives requests entered by a user to obtain specific information.

[1390] "Means for collecting data based on received requests" refers to a system that automatically collects data corresponding to user requests from the internet or internal databases.

[1391] "Means for analyzing collected data" refers to algorithms and technologies used to analyze collected data and extract necessary information and trends.

[1392] "Means of converting analysis results into answers using generative artificial intelligence" refers to a system that generates actual answers using generative artificial intelligence (for example, natural language processing technology) based on the analyzed data.

[1393] "Methods for formatting responses into a template format" refers to methods for converting generated responses into a template format that is easy for users to understand.

[1394] "Means of providing users with formatted templates" refers to a mechanism that sends formatted information to the user's device, allowing the user to receive and use it.

[1395] "Means of receiving user input and sending it to a server on the cloud" refers to a method of receiving a user's request and sending it to a server on a cloud service.

[1396] "Methods for using natural language processing technology in the analysis of collected data" refers to techniques that use natural language processing technology to automatically extract important information when analyzing collected data.

[1397] The system implementing this invention automatically generates and provides useful information using big data in response to user requests. This system is broadly composed of the following hardware and software elements.

[1398] 1. Hardware and software used

[1399] hardware

[1400] User terminal: A device that can connect to the internet, such as a smartphone or smart glasses, is used.

[1401] Cloud server: A server is required for data collection, analysis, and provision of generated information.

[1402] software

[1403] Flask: Used as an API server on a cloud server.

[1404] Generative AI: Specifically, generative AI models that utilize natural language processing technologies such as OpenAI GPT-3 are used.

[1405] 2. Data Processing and Data Calculation Flow

[1406] Receiving user input

[1407] The user uses a smartphone or smart glasses to input a request for specific information. For example, they might input, "Tell me about the latest cashless payment trends." The user's device sends this request to a cloud server.

[1408] Data collection

[1409] The server collects relevant information from the internet and internal databases based on the received request. This collected data includes the latest news, reports, articles, and user reviews.

[1410] Data Analysis

[1411] The server automatically analyzes the collected data using natural language processing technology. This analysis extracts important keywords and trends related to the requests.

[1412] Answer generation

[1413] Using generative artificial intelligence (GPT-3), specific answers are generated based on the analyzed data. The generated answers are presented in a format that is easy for the user to understand.

[1414] Template formatting

[1415] The server formats the generated responses into a user-friendly template. For example, it might be structured as follows:

[1416] Title: Latest Cashless Payment Trends

[1417] Introduction

[1418] Overview of payment methods

[1419] Details and convenience of each method

[1420] Points to note

[1421] summary

[1422] Providing results

[1423] The server sends a formatted template to the user's terminal, and the user receives and views this information.

[1424] Examples of specific cases and prompt statements

[1425] For example, suppose a user types "Tell me the latest cashless payment trends" into their smartphone. This request is immediately sent to a cloud server, where it undergoes automated analysis and AI generation to produce a detailed and structured report. The user can then receive the information directly in report format.

[1426] Example of a prompt

[1427] "Please tell me about the latest cashless payment trends. Include key points, trends, convenience, and points to note."

[1428] This prompt allows generative artificial intelligence to automatically generate detailed answers, enabling it to respond quickly and accurately to the information the user is seeking.

[1429] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1430] Step 1:

[1431] The user inputs specific information using a smartphone or smart glasses. For example, they might input a request such as, "Tell me about the latest cashless payment trends." The input request is then sent from the device to a server in the cloud.

[1432] Input: User request (e.g., "Tell me about the latest cashless payment trends")

[1433] Output: Request data sent to the cloud server

[1434] Step 2:

[1435] The server receives requests sent by users. Based on the received requests, it collects relevant data. The server collects relevant information from publicly available databases on the internet and from its own internal databases. This includes, for example, the latest news, reports, papers, and user reviews.

[1436] Input: Request data sent to the cloud server

[1437] Output: Collected data (latest news, reports, papers, user reviews, etc.)

[1438] Step 3:

[1439] The server analyzes the collected data. This analysis utilizes natural language processing techniques, including keyword extraction and trend analysis.

[1440] Input: Collected data

[1441] Output: Analysis results (extraction of important keywords and trends)

[1442] Step 4:

[1443] The server generates specific answers using generative artificial intelligence (such as GPT-3) based on the analysis results. A prompt (e.g., "Tell me about the latest cashless payment trends") is input to the generative AI model to obtain a detailed response.

[1444] Input: Analysis result, prompt message

[1445] Output: Generated answer text

[1446] Step 5:

[1447] The server formats the generated response text into a user-friendly template format. For example, it might be structured as follows: Title, Introduction, Overview of Payment Methods, Details and Convenience of Each Method, Points to Note, Summary.

[1448] Input: Generated response text

[1449] Output: Answer text formatted in template format

[1450] Step 6:

[1451] The server provides a formatted template to the user's terminal. The terminal receives the template, and the user views the results on their smartphone or smart glasses.

[1452] Input: Answer text formatted in template format

[1453] Output: Sending to the user's terminal, allowing the user to view the results.

[1454] 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.

[1455] Specific embodiments of the present invention will now be described. The present invention is a system that uses big data to generate useful information in response to user requests and provides it to the user. In particular, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to provide even more accurate information. This system automatically performs a series of processes, from receiving the user's request to collecting and analyzing the necessary data, generating the response, formatting it, and providing an emotion-conscious template.

[1456] 1. System Program

[1457] User request input and reception

[1458] The user enters their emotional state (e.g., nervous, relieved, excited) along with the search keyword "latest treatments for heart disease" via their device. Emotions can also be automatically collected through facial recognition or voice analysis.

[1459] The terminal transmits the user's input requests and emotional data to the server via the network.

[1460] Data collection

[1461] When the server receives a user request, it first consults publicly available databases on the internet and its internal databases to collect relevant data.

[1462] For example, obtaining the latest medical papers and clinical trial data.

[1463] Data Analysis

[1464] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data and imputing missing values.

[1465] The server inputs preprocessed data into machine learning algorithms (e.g., clustering and regression analysis) to perform data analysis and extract knowledge patterns related to user requests.

[1466] Emotional analysis using an emotion engine

[1467] The server uses the user's emotional data to input into the emotion engine, which then analyzes the emotional state.

[1468] For example, if a user is feeling anxious, information to generate a relaxing response should also be considered.

[1469] Answer generation using generative artificial intelligence

[1470] The server uses generative artificial intelligence based on the analysis results and sentiment analysis results to generate specific response text to the user's request.

[1471] For example, it can generate detailed text about "the latest treatments for heart disease" and add content that takes the user's emotions into consideration.

[1472] Template formatting

[1473] The server formats the generated text into a template. It adds headings and descriptions that reflect the user's emotional state.

[1474] For example, include headings, bullet points, charts, and other elements to provide reassuring language and explanations to users.

[1475] Providing results

[1476] The server sends a formatted template to the user's terminal. In this process, the information the user needs is provided in an easy-to-understand format.

[1477] Users download templates from their devices and use them in their daily work. The provided reports could also be used in treatment plan meetings at medical institutions.

[1478] Specific example

[1479] For example, consider the medical field:

[1480] When a user requests to learn about the latest diabetes treatments, they simultaneously input their emotions at the time of making that request (e.g., anxiety).

[1481] The terminal sends this request to the server.

[1482] The server collects relevant data from the internet and internal databases, obtaining the latest research papers, treatment guidelines, clinical trial data, and more.

[1483] The server analyzes the collected data using machine learning algorithms to identify important information.

[1484] The server analyzes the user's emotional state (anxiety) using an emotion engine and derives elements that provide a sense of security.

[1485] The server uses generative artificial intelligence to generate a detailed report on the "latest diabetes treatments," adding reassuring content.

[1486] The server formats the report into a template, adding headings, charts, and reassuring explanatory text.

[1487] The server sends a formatted template to the user's terminal, which the user then downloads and uses for practical work in the medical institution.

[1488] Thus, the present invention is a system that takes user emotions into consideration to realize more personalized and highly accurate information delivery. Users can easily obtain the necessary information even without specialized knowledge and use it in a way that is sensitive to their emotions.

[1489] The following describes the processing flow.

[1490] Step 1:

[1491] The user enters their emotional state (e.g., anxiety, relief) along with the search keyword "latest treatments for heart disease" via their device. Emotions, in particular, can be automatically collected through facial recognition or voice analysis.

[1492] Step 2:

[1493] The terminal transmits the user's input requests and emotional data to the server via the network. This sends the user's specific requests and their emotions at that time to the system.

[1494] Step 3:

[1495] The server receives a user request and generates a search query based on its content. This query is used to collect specific data, such as "the latest treatments for heart disease."

[1496] Step 4:

[1497] The server accesses publicly available databases on the internet and internal databases to collect relevant data. This collected data includes the latest medical papers, research data, and clinical trial results.

[1498] Step 5:

[1499] The server preprocesses the collected data. Data preprocessing includes normalization, imputation of missing data, and standardization of format. This prepares the data in a format that can be analyzed.

[1500] Step 6:

[1501] The server inputs pre-processed data into machine learning algorithms (e.g., clustering or regression analysis) to perform data analysis. The goal of the analysis is to extract the knowledge and patterns most relevant to the user's requirements.

[1502] Step 7:

[1503] The server inputs the user's emotional data into the emotion engine and analyzes their emotional state. Based on the results of the emotion analysis, it identifies the user's current emotional state.

[1504] Step 8:

[1505] The server integrates the analysis results and sentiment analysis results, and uses generative artificial intelligence to generate specific response text to the user's request. For example, if the user is looking for information on "the latest treatments for heart disease," it will generate detailed text in response to that request, and further add content that takes into account the user's emotions (such as anxiety).

[1506] Step 9:

[1507] The server formats the generated text into a template. This formatting process includes adding headings, bullet points, and, if necessary, charts and graphs. It also adds reassuring language and explanations based on the user's emotional state.

[1508] Step 10:

[1509] The server sends a formatted template to the user's terminal. During this process, the necessary information is provided in a format that is easy for the user to understand.

[1510] Step 11:

[1511] Users review and download templates sent via their devices. These templates include reassuring explanations and specific treatment methods, providing the necessary information for practical use. For example, they can be used in treatment planning meetings at medical institutions.

[1512] (Example 2)

[1513] 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".

[1514] In recent years, with the advancement of information technology, users are required to quickly and accurately obtain the information they need from vast amounts of data. However, conventional systems provide information without considering the user's emotional state, resulting in low user satisfaction. Furthermore, the analysis of collected data does not always provide the most optimal information. As a result, the accuracy and personalization of the information users need are insufficient, making it difficult to obtain information, especially in fields requiring specialized knowledge.

[1515] 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.

[1516] In this invention, the server includes means for receiving requests and emotional states entered by the user, means for collecting data from a public database and an internal database based on the received requests, and means for preprocessing and analyzing the collected data. This enables personalized and highly accurate information provision that takes the user's emotional state into consideration.

[1517] A "user" is an entity that uses a system to search for and receive information.

[1518] A "request" refers to the search keys or questions that a user enters into the system.

[1519] "Emotional state" refers to the state of the user's emotions (e.g., tension, relief, excitement), and is data collected through facial recognition, voice analysis, etc.

[1520] A "public database" refers to an information source that exists on the internet and is accessible to anyone (e.g., academic paper databases, open data platforms).

[1521] An "internal database" is a private database managed by the system owner, accessible only to users or specific stakeholders.

[1522] "Preprocessing" refers to the process of preparing collected data into an analyzable format, and specifically includes data normalization, imputation of missing values, and removal of unnecessary information.

[1523] "Analysis" is the process of using collected and pre-processed data to extract knowledge patterns related to user requests using machine learning algorithms or similar methods.

[1524] An "emotion engine" refers to software or algorithms used to analyze a user's emotional state and output the results of that emotional analysis.

[1525] "Generative artificial intelligence" refers to artificial intelligence technology that automatically generates appropriate text and responses based on analysis results.

[1526] A "template format" is a visually formatted format that makes generated responses easy for users to understand, and includes headings, paragraphs, bullet points, charts, and other elements.

[1527] A "server" refers to a computer system that processes data for the entire system, performing the steps of collection, analysis, generation, and delivery.

[1528] "Terminal" refers to a device used by a user to input requests and receive results.

[1529] This invention is a system that provides useful information based on user requests, and in particular, improves the accuracy of information provision by taking into account the user's emotional state. This system consists of a series of processing steps: inputting and receiving requests from the user, collecting data, analyzing data, performing emotional analysis using an emotion engine, generating responses using generative artificial intelligence, formatting templates, and providing results.

[1530] User request input and reception

[1531] The user enters a search key (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) through the device. The user's emotional state can also be automatically collected through facial recognition using the device's camera and microphone, or through voice analysis. The device sends the request and emotional data to the server via a secure communication protocol (e.g., HTTPS).

[1532] Data collection

[1533] After receiving a user request, the server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal databases. The collected data is temporarily stored in storage.

[1534] Data Analysis

[1535] The server preprocesses the collected data, preparing it for analysis. This preprocessing includes data normalization, imputation of missing values, and removal of unnecessary information. The preprocessed data is then fed into machine learning algorithms (e.g., clustering, regression analysis) to extract knowledge patterns that meet the user's requirements. The analysis results are stored as structured data.

[1536] Emotional analysis using an emotion engine

[1537] The server inputs the user's emotional data into the emotion engine, which then analyzes the user's emotional state. For example, if the user is "stressed," the emotion engine generates elements to help the user relax. The results of the emotional analysis are then reflected in the subsequent response generation by the generative artificial intelligence system.

[1538] Answer generation using generative artificial intelligence

[1539] The server integrates the analysis results and sentiment analysis results and generates specific response text using generative artificial intelligence (e.g., GPT models). For example, it generates a response that combines detailed text about "the latest treatments for heart disease" with phrases that alleviate the user's anxiety.

[1540] Template formatting

[1541] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other visual elements to make the information easier for users to understand. Furthermore, it applies templates tailored to the user's emotional state, adding elements that create a sense of security.

[1542] Providing results

[1543] The server sends a formatted template as the final answer to the user's terminal. The user downloads the provided template via their terminal and uses it as actual reference material. If necessary, the template can also be printed or shared with other users.

[1544] Specific example

[1545] A concrete example of a prompt might be, "I want to learn about the latest diabetes treatments. Please also include information that will alleviate my anxieties." Based on this prompt, the system collects medical data and generates information that includes elements to reduce anxiety. The resulting template would include detailed information about the latest diabetes treatments and explanations to alleviate anxiety.

[1546] Thus, the present invention is a system that provides personalized and highly accurate information while taking into consideration the user's emotions. As a result, users can easily obtain the necessary information even without specialized knowledge and use it in a way that is sensitive to their emotions.

[1547] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1548] Step 1: Inputting and receiving requests from the user.

[1549] Users enter search keywords (e.g., "latest treatments for heart disease") and their emotional state (e.g., nervous, relieved, excited) via their device. Emotional states may also be automatically collected using facial recognition or voice analysis via the device's camera and microphone.

[1550] Input: User request (search key) and sentiment state data

[1551] Output: Packetized data of user requests and emotional states

[1552] The terminal sends the generated packetized data to the server using a secure communication protocol (e.g., HTTPS).

[1553] Step 2: Data Collection

[1554] The server analyzes the user's request data and generates queries to collect the requested information.

[1555] Input: User's requested data

[1556] Output: Database query

[1557] The server collects relevant data from publicly available databases on the internet (e.g., academic paper databases) and internal company databases.

[1558] Input: Database query

[1559] Output: Collected data (medical papers, clinical trial data, etc.)

[1560] The server stores the collected data in temporary storage.

[1561] Step 3: Data Analysis

[1562] The server preprocesses the collected data to prepare it for analysis. This includes normalizing the data, imputing missing values, and removing unnecessary information.

[1563] Input: Collected data

[1564] Output: Preprocessed data

[1565] The server inputs pre-processed data into machine learning algorithms (e.g., clustering, regression analysis) to extract knowledge patterns that meet the user's requirements.

[1566] Input: Preprocessed data

[1567] Output: Analysis results (structured data)

[1568] Step 4: Emotional analysis using the emotion engine

[1569] The server inputs the user's emotional state data into the emotion engine and analyzes the emotional state.

[1570] Input: User's emotional state data

[1571] Output: Emotion analysis results (identification of emotional state, suggestions for appropriate responses, etc.)

[1572] For example, if a user is feeling "stressed," the emotion engine will generate elements that promote "relaxation."

[1573] Step 5: Generating answers using generative artificial intelligence

[1574] The server uses generative artificial intelligence (e.g., GPT models) to generate specific response text based on the analysis results and sentiment analysis results.

[1575] Input: Analysis results and sentiment analysis results

[1576] Output: Specific answer text

[1577] For example, the system generates responses that combine detailed text about "the latest treatments for heart disease" with phrases designed to ease the user's anxiety.

[1578] Step 6: Template Formatting

[1579] The server formats the generated text into a template. The template includes headings, paragraphs, bullet points, charts, and other elements.

[1580] Input: Generated response text

[1581] Output: Template-formatted answer

[1582] Furthermore, templates tailored to the user's emotional state are applied, and elements that help users feel more secure are added.

[1583] Step 7: Results Provision

[1584] The server sends the formatted template to the user's terminal.

[1585] Input: Template-style answer

[1586] Output: Template-formatted response sent to the user's device.

[1587] Users download templates provided through their devices and use them in their work. They can also print templates or share them with other users as needed.

[1588] (Application Example 2)

[1589] 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".

[1590] Traditional e-commerce sites offer systems that recommend products based on user requests, but these recommendations do not take into account the user's emotional state, making it difficult to improve user psychological satisfaction. Therefore, when a user is stressed or agitated, the system fails to recommend suitable products, hindering the improvement of the user experience. Furthermore, it has not been possible to provide personalized information that reflects the user's emotional state.

[1591] 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.

[1592] In this invention, the server includes means for receiving requests and emotional data entered by the user, means for collecting data based on the received requests and emotional data, and means for preprocessing and analyzing the collected data. This enables product recommendations tailored to the user's emotional state, improves the user's psychological satisfaction, and provides personalized, highly accurate information.

[1593] "Means for receiving user-inputted requests and sentiment data" refers to a function that collects and receives product search requests and sentiment data entered by users through their terminals.

[1594] "Means for collecting data based on received requests and sentiment data" refers to a function that collects relevant product information and data from the internet and internal databases based on the user's search requests and sentiment data.

[1595] "Means for preprocessing and analyzing collected data" refers to functions that perform preprocessing such as normalizing collected data into an analyzable format or imputing missing values, and then performing data analysis.

[1596] "A means of inputting analysis results into a generative artificial intelligence system using a machine learning algorithm to generate a response" refers to a function that applies a machine learning algorithm based on pre-processed results, and uses generative artificial intelligence to generate specific responses and recommendations to the user's requests as text.

[1597] "A means of formatting generated responses into a template and adding emotionally sensitive content" refers to a function that formats the generated response text and adds headings and explanations that are sensitive to the user's emotions.

[1598] "Means of providing formatted templates to users" refers to a function that sends formatted templates to the user's device, making the information easily accessible to the user.

[1599] Modes for carrying out the invention

[1600] This invention provides a product recommendation system for e-commerce sites that takes into account the emotional state of the user. Specific embodiments of this invention will be described in detail below.

[1601] System configuration and programs to be used

[1602] Hardware and software

[1603] 1. Hardware: Smartphone or tablet

[1604] 2. Software:

[1605] Emotion recognition technology: Image recognition technology is used for facial recognition, and speech recognition technology is used for voice analysis. For example, general image recognition APIs and speech recognition APIs are used.

[1606] Data analysis tools: Python and its libraries (pandas, scikit-learn) will be used.

[1607] Generative artificial intelligence: Uses a generative AI model (e.g., GPT-4).

[1608] Backend server: Uses Node.js and Express.

[1609] Database: Use MySQL.

[1610] Processing flow and data calculations

[1611] The server receives requests and emotional data entered by the user. For example, a user inputs their emotional state using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. As a result, the user's request data and emotional data are sent from the device to the server.

[1612] The server collects relevant product information from the internet and internal databases based on received request and sentiment data. The collected data is preprocessed, for example, by imputing missing values ​​and normalizing it.

[1613] After the preprocessing of the collected data is complete, analysis will be performed. The analysis will be carried out using Python and its libraries (pandas, scikit-learn), and related product information will be analyzed using machine learning algorithms such as clustering.

[1614] Next, the analysis results are input into a generative artificial intelligence (generative AI model) to generate product recommendation text, which is a specific response to the user's request. The following example prompt sentences are input into this generative AI model:

[1615] "Please recommend five relaxation products that would be suitable for users who are feeling anxious."

[1616] The generated responses are formatted into a template with added content that takes the user's emotions into consideration. This template includes headings and descriptions that reflect the user's emotions.

[1617] Finally, a formatted template is provided to the user's device, allowing the user to intuitively view product information.

[1618] Adding specific examples

[1619] For example, if a user requests to learn about the latest gadgets and the system recognizes that the user is also experiencing anxiety, the system will collect relevant gadget information from the internet and its internal database. Based on the analyzed data, a generative AI model will generate detailed text about the latest gadgets, and further add explanatory text that helps alleviate the user's anxiety. This allows the user to obtain information while feeling at ease.

[1620] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1621] Step 1:

[1622] The user inputs their emotional data using facial recognition and voice analysis via their smartphone's camera and microphone, and also inputs a product search request. The input includes the user's emotional data (e.g., nervous, relieved, excited) and product search keys (e.g., "latest gadgets"). The output is the device sending this data to a server.

[1623] Step 2:

[1624] The server receives user requests and sentiment data over the network. It takes user sentiment data and product search request data as input and passes that data to the next processing step as output.

[1625] Step 3:

[1626] The server collects relevant product information based on requests received from the internet and internal databases. It uses user search requests (e.g., "latest gadgets") as input and collects and stores relevant data (e.g., product names, specifications, reviews, etc.) as output.

[1627] Step 4:

[1628] The server preprocesses the collected data and prepares it for analysis. It takes the collected raw data as input, performs specific data processing (imputation of missing values, data normalization), and generates a clean, preprocessed dataset as output.

[1629] Step 5:

[1630] The server analyzes the pre-processed data. It takes a clean dataset as input, analyzes the data using machine learning algorithms (e.g., clustering and regression analysis), and outputs the analysis results.

[1631] Step 6:

[1632] The server inputs the analysis results into a generative AI model to generate specific answers (product recommendation text) to the user's request. The generative AI model is fed with the analysis results and a prompt (for example, "Please recommend 5 relaxation products for when the user is feeling anxious") as input, and the generated answer text is obtained as output.

[1633] Step 7:

[1634] The server formats the generated response text into a template and adds headings and descriptions that take into account the user's emotional state. It takes the generated text and user emotional information as input, formats the headings and additional descriptions, and outputs a final document in template format.

[1635] Step 8:

[1636] The server sends a formatted template to the user's terminal and provides it to the user. It takes a final document in template format as input and sends and displays the document on the user's terminal as output.

[1637] This will enable a system that allows users to obtain product information in an intuitive and emotionally resonant way.

[1638] 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.

[1639] 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.

[1640] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1641] 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.

[1642] 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.

[1643] 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.

[1644] 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.

[1645] 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.

[1646] 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."

[1647] 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.

[1648] 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.

[1649] 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.

[1650] 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.

[1651] 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.

[1652] 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.

[1653] 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.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] The following is further disclosed regarding the embodiments described above.

[1660] (Claim 1)

[1661] [Means for receiving requests entered by the user,

[1662] [Means for collecting data based on received requests,

[1663] [Means for analyzing the collected data,

[1664] [Methods for converting analysis results into answers using generative artificial intelligence,

[1665] [Methods for formatting answers into a template format,

[1666] [Means of providing users with formatted templates,

[1667] A system that includes this.

[1668] (Claim 2)

[1669] [The system according to claim 1, which includes means for using the Internet and an internal database in data collection.

[1670] (Claim 3)

[1671] The system according to claim 1, further comprising means for inputting the analysis results into a generative artificial intelligence system using a machine learning algorithm.

[1672] "Example 1"

[1673] (Claim 1)

[1674] [Means for receiving requests entered by the user,

[1675] [Means for collecting relevant data from a database based on a received request,

[1676] [Means for preprocessing the collected data,

[1677] [Methods for analyzing pre-processed data using machine learning algorithms,

[1678] [Methods for inputting analysis results into an AI model to generate answers,

[1679] [Methods for formatting the generated response into a template format,

[1680] [Means of providing users with formatted templates,

[1681] A system that includes this.

[1682] (Claim 2)

[1683] [The system according to claim 1, which includes means for using the Internet and an internal database in data collection.

[1684] (Claim 3)

[1685] The system according to claim 1, which includes means for creating prompt statements when inputting analysis results into an AI model.

[1686] "Application Example 1"

[1687] (Claim 1)

[1688] [Means for receiving requests entered by the user,

[1689] [Means for collecting data based on received requests,

[1690] [Means for analyzing the collected data,

[1691] [Methods for converting analysis results into answers using generative artificial intelligence,

[1692] [Methods for formatting answers into a template format,

[1693] [Means of providing users with formatted templates,

[1694] [Means of receiving user input and sending it to a server in the cloud,

[1695] [Methods that use natural language processing techniques to analyze collected data,

[1696] A system that includes this.

[1697] (Claim 2)

[1698] [The system according to claim 1, which includes means for using the Internet and an internal database in data collection.

[1699] (Claim 3)

[1700] The system according to claim 1, further comprising means for inputting the analysis results into a generative artificial intelligence system using a machine learning algorithm.

[1701] "Example 2 of combining an emotion engine"

[1702] (Claim 1)

[1703] [Means for receiving requests and emotional states entered by the user,

[1704] [Means for collecting data from public and internal databases based on received requests,

[1705] [Means for preprocessing and analyzing the collected data,

[1706] [Methods for analyzing a user's emotional state using an emotion engine,

[1707] [Methods for integrating analysis results and emotion analysis results to generate answers using generative artificial intelligence,

[1708] [Methods for formatting the generated response into a template format,

[1709] [Means of providing users with formatted templates,

[1710] A system that includes this.

[1711] (Claim 2)

[1712] [The system according to claim 1, which utilizes the internet and an internal database for data collection.]

[1713] (Claim 3)

[1714] [The system according to claim 1, which inputs the analysis results and emotion analysis results into a generative artificial intelligence system using a machine learning algorithm.

[1715] "Application example 2 when combining with an emotional engine"

[1716] (Claim 1)

[1717] [Means for receiving requests and sentiment data entered by the user,

[1718] [Means for collecting data based on received request and sentiment data,

[1719] [Means for preprocessing and analyzing the collected data,

[1720] [A means of inputting the analysis results into a generative artificial intelligence using a machine learning algorithm to generate an answer,

[1721] [Methods for formatting the generated responses into a template and adding emotionally sensitive content,

[1722] [Means of providing users with formatted templates,

[1723] A system that includes this.

[1724] (Claim 2)

[1725] [The system according to claim 1, which uses the internet and an internal database to collect data and analyzes user sentiment data.]

[1726] (Claim 3)

[1727] [The system according to claim 1, which generates responses based on analysis results as product recommendation text based on the user's emotions. [Explanation of symbols]

[1728] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving requests entered by the user, Means for collecting data based on received requests, Means for analyzing the collected data, A means of converting analysis results into answers using generative artificial intelligence, Methods for formatting answers into a template, A means of providing users with formatted templates, A system that includes this.

2. The system according to claim 1, comprising means for using the internet and an internal database in data collection.

3. The system according to claim 1, further comprising means for inputting the analysis results into a generative artificial intelligence system using a machine learning algorithm.

Images