system

Abstract

We provide the system. [Solution] An input means for receiving user input, A collection means for collecting data related to the user input, An analysis means for analyzing the collected data and extracting relevant information, A presentation means for presenting the extracted information to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need for a systematic method to efficiently extract information related to specific keywords from a vast amount of market data and news information to assist investors in making immediate decisions. However, conventional technologies have limitations in real-time analysis accuracy and the ability to propose relevant stocks, making it difficult to make appropriate investment judgments in an information overload situation. Therefore, it is an issue to develop a system that can quickly and accurately provide relevant information in response to user input and support investment decisions.

Means for Solving the Problems

[0005] This invention provides an input means for receiving user input and a collection means for collecting data related to this input. The collected data is analyzed by an analysis means using a natural language processing algorithm to extract relevant information. Finally, a presentation means presents the extracted information to the user in real time, thereby constructing a system that supports the user's decision-making. This configuration allows the user to quickly obtain relevant information and make more accurate and efficient investment decisions.

[0006] "User input" refers to data used by system users to provide information.

[0007] "Input means" refers to an interface or device designed to receive user input.

[0008] "Data collection means" refers to a function or method that plays a role in collecting data related to user input.

[0009] "Analysis means" refers to techniques or tools used to analyze collected data and derive specific results or information.

[0010] "Presentation means" refers to a device or method for displaying or providing analyzed information to a user.

[0011] A "natural language processing algorithm" is a computational method that enables computers to understand, process, and generate human language.

[0012] "Related information" refers to data or knowledge that is directly or indirectly related to user input.

[0013] "Real-time" refers to a temporal characteristic where data is processed and results are supplied the moment it is generated. [Brief explanation of the drawing]

[0014] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] The present invention is a system that supports efficient decision-making by users by providing relevant information based on user input. This system is implemented with a configuration that includes input means, collection means, analysis means, and presentation means.

[0036] First, the user enters a specific keyword into an input device using their terminal. This input is transmitted to a server, which then collects data related to that keyword. For this data collection, the server utilizes real-time updates from various online information sources and market databases to obtain highly accurate information.

[0037] Next, the server passes the collected data to an analysis tool, where a natural language processing algorithm is used. This algorithm identifies topics related to keywords within the data and extracts information that may influence investment decisions through sentiment analysis.

[0038] The analyzed information is organized on the server and transmitted to the user's terminal via a presentation mechanism. The terminal receives this information and supports the user's decision-making by displaying relevant stock information and market trends on the user interface.

[0039] For example, if a user enters "LDP presidential election," the server will collect relevant news and analyze it to identify sectors and stocks sensitive to political developments. The information presented will include predictions of stock price fluctuations and trends in potentially affected industries, allowing the user to make quick investment decisions based on this information.

[0040] Thus, this system is designed to allow users to easily obtain the data they need through each stage of information collection, analysis, and presentation, and to directly link it to decision-making. As a result, users can respond quickly to rapid market fluctuations.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user enters a specific keyword through the terminal's user interface. This keyword becomes part of the data sent to the server.

[0044] Step 2:

[0045] User input is sent from the terminal to the server. The server then starts a process to collect relevant data based on the received keywords.

[0046] Step 3:

[0047] The server collects the latest information related to the entered keywords from news sites and market databases on the internet. This collection uses APIs to obtain real-time data.

[0048] Step 4:

[0049] The server passes the collected data to an analysis tool, which then analyzes the data using natural language processing algorithms. This process involves topic extraction and sentiment analysis, identifying potential investment candidates related to keywords.

[0050] Step 5:

[0051] The results of the analysis are returned to the server and organized as relevant information. At this stage, information about specific stocks and their market trends is selected.

[0052] Step 6:

[0053] The server sends the selected information to the terminal. The display format is adjusted so that the information is presented in a way that is easy for the user to understand and process.

[0054] Step 7:

[0055] The terminal displays information received from the server on the user interface. This includes detailed information about relevant stocks and market conditions, which users can use to make investment decisions.

[0056] Step 8:

[0057] Users evaluate the presented information and, if necessary, conduct further research or proceed to actual investment actions. This process enables users to make quick and informed decisions.

[0058] (Example 1)

[0059] 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."

[0060] In today's information-saturated age, users need to efficiently collect, analyze, and provide relevant information in a timely manner in order to make quick and accurate decisions. However, conventional systems have problems such as the information becoming outdated or users becoming confused by excessive information.

[0061] 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.

[0062] In this invention, the server includes an input means for receiving user input, a collection means for collecting relevant information, and an analysis means for analyzing the information and extracting topics. This enables users to quickly obtain relevant information and expedite decision-making.

[0063] "User input" refers to data and information entered by a user through a terminal or computer interface.

[0064] "Collection means" refers to devices or methods that have the function of acquiring data and information related to user input from external sources.

[0065] "Analysis methods" refer to the processes and techniques used to analyze collected information and extract specific topics or relevant information from it.

[0066] "Presentation means" refers to devices or methods for providing analyzed information to users in a visual or other way.

[0067] "Communication methods" refer to technologies, including network interfaces and protocols, that enable data exchange between external information sources and servers, and allow information to be obtained in real time.

[0068] In embodiments of the present invention, a system is configured in which a user, a terminal, and a server cooperate to efficiently collect, analyze, and provide information.

[0069] The user enters specific keywords using a device. A device refers to an information device such as a computer or smartphone, which provides an interface for the user to input information and receive results. Specifically, keywords are entered through a web browser or dedicated application on the device.

[0070] The entered keyword is sent from the terminal to the server. The server is where data collection takes place, and it queries online information sources and market databases. For example, it can use the Google® News API or APIs that provide financial market data to obtain relevant information in real time.

[0071] The collected data is analyzed on the server. This analysis utilizes language analysis techniques such as Python's NLTK library. This process involves extracting relevant information topics and performing sentiment analysis. Through this process, important information related to specific keywords is identified and provided to users for decision-making.

[0072] The analysis results are transmitted to the user's terminal via a presentation device. The terminal receives this data and displays it as visual information on the user interface. This allows the user to immediately access relevant information, for example, to check the trends of related stocks and make quick investment decisions. An example of a specific prompt message is, "Please tell me the latest news regarding the Liberal Democratic Party presidential election and the market trends of related stocks."

[0073] This system enables users to cope with information overload and efficiently utilize relevant information, thereby supporting accurate and rapid decision-making.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] Users enter specific keywords through their device's interface. Specifically, they enter keywords into input forms in their device's web browser or application and then press a "Submit" or "Search" button. The entered data consists of keywords related to topics or events of interest to the user. These keywords are then sent to the server.

[0077] Step 2:

[0078] The terminal sends keywords entered by the user to the server. Based on the received input keywords, the server uses data collection methods to gather relevant data from online information sources and market databases. This data collection utilizes, for example, news APIs and market data APIs. The input is keywords, and the output is a data list of related information and news articles.

[0079] Step 3:

[0080] The server analyzes the collected data. For analysis, it uses the Python NLTK library as a natural language processing technique. The server extracts relevant informational topics from the input data and evaluates the data by performing sentiment analysis. Specifically, it identifies positive, negative, and neutral sentiment tones. The input is the collected data, and the output is the analyzed informational topics and the results of the sentiment analysis.

[0081] Step 4:

[0082] The server organizes the analysis results and sends them to the user's terminal via a presentation method. The server converts the data into a visually easy-to-understand format (e.g., JSON format) before sending it. The input is the analyzed information, and the output is the formatted data.

[0083] Step 5:

[0084] The terminal receives formatted data sent from the server and displays it visually on the user interface. The terminal expands this data on the screen in text or graphical format, allowing the user to view the information at a glance. Specifically, it displays relevant stock trends and news summaries. The input is formatted data, and the output is information that the user can visually review.

[0085] This process allows users to quickly refer to the information provided and make decisions.

[0086] (Application Example 1)

[0087] 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."

[0088] In modern electronic payment services, users are required to make quick decisions based on rapidly changing market information, but conventional systems have the problem of not being able to provide sufficient support to guarantee such immediacy. The present invention aims to solve these problems and provide a system that helps users make quick and accurate decisions based on market trends.

[0089] 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.

[0090] In this invention, the server includes terminal means for receiving user input, data collection means for collecting information related to the user input, data analysis means for analyzing the collected information and extracting relevant data through sentiment analysis, and visualization means for visually presenting the extracted information to the user. This enables the user to immediately understand relevant market trends and make quick decisions.

[0091] A "terminal device" is a device equipped with an interface for user input.

[0092] "Data collection means" refers to functions for obtaining information related to user input from the internet or databases.

[0093] "Data analysis means" refers to a function that processes collected information and extracts relevant data using natural language processing and sentiment analysis.

[0094] "Visualization means" refers to functions such as screen display and graph generation that present extracted information to the user in an easy-to-understand manner.

[0095] In order to implement this invention, it is necessary to construct a system in which a terminal, data collection means, data analysis means, and visualization means function in coordination.

[0096] The user enters specific keywords using a terminal. The terminal sends this input to a data collection system. The data collection system retrieves information related to the user input in real time from internet sources or specific databases. In this case, it is recommended to use an API for data collection.

[0097] Next, the data analysis tools process the information they have acquired. This process uses VADER, a Python natural language processing library, to perform sentiment analysis and extract emotional trends and market developments related to user input. This analysis can uncover hidden relevant data that can aid in user decision-making.

[0098] The server then formats the analyzed data and transmits it to the terminal through a visualization mechanism. The terminal graphically displays the information in its user interface, allowing the user to gain concrete insights to support their own decision-making. Methods such as bar graphs and line graphs are used for visualization.

[0099] For example, if a user enters the keyword "climate change," the system will collect relevant market news and calculate sentiment scores for those headlines. Based on these results, it will show the user financial market trends related to climate change, providing visual information to help them make quick and accurate investment decisions.

[0100] Examples of prompts for a generative AI model:

[0101] Create a Python program that collects relevant market data based on a keyword entered by the user, performs sentiment analysis, and displays the results in an easy-to-understand format. Assume the keyword is "climate change" and use a market data API.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The user enters a specific keyword through the terminal. The entered keyword is transmitted from the terminal's input interface to the data collection means. The input functions as direct information from the user and provides the data that forms the basis for the next processing step.

[0105] Step 2:

[0106] The server's data collection method involves accessing internet-based information sources and specific databases to obtain information relevant to user input in real time. In this step, APIs are called using input keywords to collect relevant news and market data. The input is keywords, and the output is a collection of relevant data.

[0107] Step 3:

[0108] The server's data analysis method receives collected information and performs sentiment analysis on it. Specifically, it uses the Python VADER library to calculate sentiment scores for collected articles and news headlines. The input is a set of related data, and the output is analytical information including sentiment scores.

[0109] Step 4:

[0110] The server formats the analysis results and sends them to the terminal using visualization tools. Here, the organized data is converted into bar graphs and line graphs to make it easier for the user to intuitively understand. The input is the analysis information, and the output is the visualized data.

[0111] Step 5:

[0112] The terminal displays the transmitted visualization data on the user interface. Based on this visual information, users can make quick and accurate decisions. The input is visualized data, and the output is a graphical display viewable by the user.

[0113] 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.

[0114] The present invention is a system that provides relevant information based on user input and further optimizes information presentation by recognizing the user's emotions. This system is implemented with a configuration including input means, collection means, analysis means, presentation means, and an emotion engine.

[0115] First, the user enters a specific keyword using the user interface on their device. The device sends this input to the server. The server collects relevant data based on the received keyword. This data is collected in real time from online information sources and market databases, and then the collected data is analyzed using natural language processing algorithms by an analysis tool.

[0116] Furthermore, this system incorporates an emotion engine that estimates the user's emotional state from their input history and real-time responses. The emotion engine utilizes machine learning models to classify the user's emotions and feeds this information back into the analysis results. This feedback optimizes the content and order of information presentation to match the user's emotional state.

[0117] After the server compiles the relevant information, the presentation device transmits it to the terminal. The terminal displays the information on the user interface in a way that best suits the user's emotional state. The presented information includes relevant stock information and market trends, which the user can use to make decisions.

[0118] For example, if a user enters the keyword "economic crisis," the emotion engine might determine that the user is feeling anxious. In this case, the server would prioritize presenting supplementary information or expert analytics that help alleviate the anxiety.

[0119] This system will allow users not only to receive information, but also to obtain flexible and appropriate information tailored to their individual emotional state. As a result, it is expected that users' decision-making will become more efficient and rational.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The user enters a specific keyword using the terminal's user interface. This input serves as the initial instruction to the system.

[0123] Step 2:

[0124] The terminal sends the entered keyword to the server. The server then starts the process of collecting relevant data based on this information.

[0125] Step 3:

[0126] The server collects information related to the entered keywords from news sites and financial databases on the internet. Collection is performed in real time, ensuring that the latest data is obtained.

[0127] Step 4:

[0128] The server passes the collected data to an analysis tool, which then analyzes the data using natural language processing algorithms. Based on the analysis results, it extracts relevant stocks and market trends.

[0129] Step 5:

[0130] The server uses an emotion engine to estimate the user's emotional state based on direct user input and interaction. This takes into account input history and real-time response data.

[0131] Step 6:

[0132] The emotion engine classifies the user's emotional state and reflects the results in the output of the analysis tool. The information is then re-prioritized in a way that matches the user's emotions.

[0133] Step 7:

[0134] The server sends optimized information to the terminal based on the user's emotional state. The presentation means then displays this information on the user interface.

[0135] Step 8:

[0136] The device presents organized information to the user. This information is tailored to the user's emotions, allowing them to use it to make optimal decisions.

[0137] Step 9:

[0138] Users review the presented information and use it to make investment decisions and take their next actions. In this process, providing information that resonates with the user's emotions supports their decision-making.

[0139] (Example 2)

[0140] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0141] Conventional information systems often fail to consider the user's emotional state when presenting information, resulting in information that is not tailored to individual emotions or needs. Consequently, user decision-making may not always be efficient. There is a growing need for systems that provide optimal information, taking emotions into account, based on the information entered by the user.

[0142] 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.

[0143] In this invention, the server includes a device for receiving user input, a device for estimating the user's emotional state, and a device for optimizing information based on the extracted information and the estimated emotional state, and presenting it to the user. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0144] "User input" refers to the act of a user providing information or instructions to a system through a device.

[0145] A "data collection device" refers to a device that has the function of collecting data from a specific source according to a particular purpose.

[0146] An "analysis device" refers to a device that has the function of analyzing acquired data and extracting necessary information.

[0147] A "device for estimating emotional state" refers to a device that has the function of inferring the emotions of a user and is characterized by using machine learning technology.

[0148] An "information optimization device" refers to a device that has the function of appropriately adjusting the information to be presented based on the extracted information and the user's emotional state.

[0149] A "presentation device" refers to a device that has the function of showing information to a user visually or by other means.

[0150] This system is an information presentation system that provides relevant information based on user input and further optimizes the presentation by recognizing the user's emotions. Its main components consist of a server, terminals, and a user interface.

[0151] The user first enters keywords through the user interface on their device. The device then sends this input to the server. The server collects relevant information based on the received keywords. The server uses various databases and online information platforms as information sources and utilizes programming languages ​​such as Python and Java (registered trademark) to streamline information gathering.

[0152] The collected data is analyzed on the server. Natural language processing tools such as Python's NLTK library and SpaCy are used to extract relevant information. This process narrows down important themes and trends from the vast amount of data.

[0153] The emotion engine estimates the user's emotional state based on their past behavior, input patterns, and real-time responses. Specifically, it uses machine learning models such as TENSORFLOW® and PyTorch to classify the user's emotions into categories such as "excited," "anxious," and "neutral."

[0154] The server integrates analysis results with emotional states to optimize the presentation of information. This ensures that information is presented in a more relevant and useful way for the user.

[0155] For example, if a user enters the keyword "economic crisis," the server analyzes relevant market trends based on collected data, and the emotion engine can infer that the user is feeling anxious. In this case, the server prioritizes presenting the user with examples of economic crisis recovery and expert analyses.

[0156] An example of a prompt to the generating AI model would be, "Please tell me about market trends that may be affected by the economic crisis." In response to this prompt, the system will provide information best suited to the user's situation.

[0157] This system aims to support more efficient decision-making by enabling users not only to acquire information but also to obtain flexible and appropriate information tailored to their individual emotional states.

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

[0159] Step 1:

[0160] The user enters a keyword into the terminal. For example, the user might enter a specific keyword such as "economic forecast." The entered keyword is sent from the terminal to the server. This input acts as a trigger for the server to collect relevant information.

[0161] Step 2:

[0162] The server receives keywords and collects information based on those keywords. The server retrieves relevant data from online databases, news sites, etc., using APIs. The input is keywords, and the output is a collection of related data. The server implements filtering algorithms to maintain the quality and relevance of the data.

[0163] Step 3:

[0164] The server analyzes the collected data. Specifically, it uses Python's NLTK library and natural language processing software to analyze text data. This analysis extracts important contexts and topics. The input is the collected data, and the output is summarized relevant information. The server then uses the data to extract frequently occurring words, etc.

[0165] Step 4:

[0166] The server uses an emotion engine to estimate the user's emotions. In this step, past user activity and real-time responses are fed into a machine learning model to classify emotions as "excited," "anxious," or "neutral." The input is user response data, and the output is the estimated emotion. TensorFlow is used for this classification.

[0167] Step 5:

[0168] The server integrates analysis results and emotional information to optimize the content of the information provided. Specifically, it changes the priority of information based on the emotional state. For example, if anxiety is detected, the system prioritizes displaying information that provides reassurance. The input is the analysis results and emotional information, and the output is a list of optimized information.

[0169] Step 6:

[0170] The server sends optimized information to the terminal. The terminal displays the received information in its user interface. This allows the user to receive information in a way that aligns with their emotional state. The input is optimized information, and the output is a display of information that the user can visually confirm.

[0171] (Application Example 2)

[0172] 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".

[0173] When making electronic payments, users often experience anxiety and hesitation. These emotions can blur decision-making and disrupt the transaction flow. Traditional systems lack the ability to recognize user emotions and optimize information accordingly, making it difficult to provide an appropriate user experience based on those emotions. To address this challenge, a system is needed that presents information in accordance with the user's emotional state, thereby providing a sense of security.

[0174] 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.

[0175] In this invention, the server includes a device for receiving user input, a device for collecting information related to the user input, a device for analyzing the collected information and extracting relevant knowledge, and a device for estimating the user's emotional state and optimizing information presentation. This enables information presentation optimized based on the user's emotions, providing a safe and smooth electronic payment experience.

[0176] "User input" refers to information and commands provided by the user via a terminal or device.

[0177] A "data collection device" refers to a device that has the function of acquiring external information and data related to user input.

[0178] An "analysis device" refers to a device used to analyze collected information and extract relevant knowledge and patterns.

[0179] A "presentation device" refers to a device that displays analyzed knowledge to the user through visual or auditory means.

[0180] An "emotion estimation device" refers to a device that detects the user's emotional state from their input history and real-time responses, and adjusts the information presented based on that state.

[0181] In the system implementing this invention, the user inputs information using a device such as a smartphone. The information entered by the user is received as keywords or requests in natural language. The entered information is sent to a server, which then collects relevant external information and data in real time based on that information.

[0182] The collected information is analyzed using a natural language processing model executed on the server. This analysis utilizes natural language processing libraries such as NLTK and spaCy. Highly relevant knowledge and patterns are extracted from the analysis results.

[0183] Simultaneously, an emotion estimation device estimates the user's emotional state. This device utilizes machine learning model libraries such as Scikit-learn and TensorFlow. Emotions are classified based on the user's input history and physiological responses, and the results are fed back into the information presentation.

[0184] Ultimately, the presentation of information is optimized based on the analysis results and sentiment estimation. The presentation device displays relevant knowledge on the terminal in a way that best suits the user's emotional state. This process allows the user to gain confidence regarding the transaction.

[0185] For example, if a user feels anxious when making their first credit card payment through online shopping, the emotion estimation device will detect this anxiety. In response, the presentation device will reduce the user's anxiety by prioritizing the display of information about past secure transactions and enhanced security.

[0186] An example of a prompt message could be, "If a user feels anxious about making an online payment, how would you present information to alleviate that anxiety?" This allows for the consideration of strategies for presenting information based on emotions.

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

[0188] Step 1:

[0189] The user uses a device to input natural language keywords or requests. The input information is sent to the server through the device's user interface. The input may include specific topics or questions that the user has expressed interest in.

[0190] Step 2:

[0191] The server collects relevant external information and data in real time based on the user input it receives. The collection device retrieves the necessary data from online information sources and databases. The input for this step is the user's keywords, and the output is the retrieved relevant data.

[0192] Step 3:

[0193] The collected data is analyzed using a natural language processing model on the server. The server uses libraries such as NLTK and spaCy to analyze the data and extract relevant knowledge and patterns. The input is the collected data, and the output is the analyzed knowledge.

[0194] Step 4:

[0195] Simultaneously, the server's emotion estimation device infers the user's emotional state. The device uses machine learning models such as Scikit-learn and TensorFlow to classify emotions from the user's input history and physiological responses. In this step, the input is the user's historical data, and the output is the inferred emotional state.

[0196] Step 5:

[0197] The server integrates the analyzed knowledge and inferred emotional state to optimize information presentation. Specifically, it prioritizes relevant information based on the user's emotions and adjusts the content of the presentation. The input to this process is the output from steps 3 and 4, and the output is the optimized presentation information.

[0198] Step 6:

[0199] Finally, the optimized information is returned to the device and displayed through the user interface. The device presents the user with emotionally reassuring information and recommendations. In this step, the input is the optimized information from the server, and the output is what is displayed in the user interface.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] [Second Embodiment]

[0204] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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".

[0216] The present invention is a system that supports efficient decision-making by users by providing relevant information based on user input. This system is implemented with a configuration that includes input means, collection means, analysis means, and presentation means.

[0217] First, the user enters a specific keyword into an input device using their terminal. This input is transmitted to a server, which then collects data related to that keyword. For this data collection, the server utilizes real-time updates from various online information sources and market databases to obtain highly accurate information.

[0218] Next, the server passes the collected data to an analysis tool, where a natural language processing algorithm is used. This algorithm identifies topics related to keywords within the data and extracts information that may influence investment decisions through sentiment analysis.

[0219] The analyzed information is organized on the server and transmitted to the user's terminal via a presentation mechanism. The terminal receives this information and supports the user's decision-making by displaying relevant stock information and market trends on the user interface.

[0220] For example, if a user enters "LDP presidential election," the server will collect relevant news and analyze it to identify sectors and stocks sensitive to political developments. The information presented will include predictions of stock price fluctuations and trends in potentially affected industries, allowing the user to make quick investment decisions based on this information.

[0221] Thus, this system is designed to allow users to easily obtain the data they need through each stage of information collection, analysis, and presentation, and to directly link it to decision-making. As a result, users can respond quickly to rapid market fluctuations.

[0222] The following describes the processing flow.

[0223] Step 1:

[0224] The user enters a specific keyword through the terminal's user interface. This keyword becomes part of the data sent to the server.

[0225] Step 2:

[0226] User input is sent from the terminal to the server. The server then starts a process to collect relevant data based on the received keywords.

[0227] Step 3:

[0228] The server collects the latest information related to the entered keywords from news sites and market databases on the internet. This collection uses APIs to obtain real-time data.

[0229] Step 4:

[0230] The server passes the collected data to an analysis tool, which then analyzes the data using natural language processing algorithms. This process involves topic extraction and sentiment analysis, identifying potential investment candidates related to keywords.

[0231] Step 5:

[0232] The results of the analysis are returned to the server and organized as relevant information. At this stage, information about specific stocks and their market trends is selected.

[0233] Step 6:

[0234] The server sends the selected information to the terminal. The display format is adjusted so that the information is presented in a way that is easy for the user to understand and process.

[0235] Step 7:

[0236] The terminal displays information received from the server on the user interface. This includes detailed information about relevant stocks and market conditions, which users can use to make investment decisions.

[0237] Step 8:

[0238] Users evaluate the presented information and, if necessary, conduct further research or proceed to actual investment actions. This process enables users to make quick and informed decisions.

[0239] (Example 1)

[0240] 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."

[0241] In today's information-saturated age, users need to efficiently collect, analyze, and provide relevant information in a timely manner in order to make quick and accurate decisions. However, conventional systems have problems such as the information becoming outdated or users becoming confused by excessive information.

[0242] 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.

[0243] In this invention, the server includes an input means for receiving user input, a collection means for collecting relevant information, and an analysis means for analyzing the information and extracting topics. This enables users to quickly obtain relevant information and expedite decision-making.

[0244] "User input" refers to data and information entered by a user through a terminal or computer interface.

[0245] "Collection means" refers to devices or methods that have the function of acquiring data and information related to user input from external sources.

[0246] "Analysis methods" refer to the processes and techniques used to analyze collected information and extract specific topics or relevant information from it.

[0247] "Presentation means" refers to devices or methods for providing analyzed information to users in a visual or other way.

[0248] "Communication methods" refer to technologies, including network interfaces and protocols, that enable data exchange between external information sources and servers, and allow information to be obtained in real time.

[0249] In embodiments of the present invention, a system is configured in which a user, a terminal, and a server cooperate to efficiently collect, analyze, and provide information.

[0250] The user enters specific keywords using a device. A device refers to an information device such as a computer or smartphone, which provides an interface for the user to input information and receive results. Specifically, keywords are entered through a web browser or dedicated application on the device.

[0251] The entered keyword is sent from the terminal to the server. The server is where data collection takes place, and it queries online information sources and market databases. For example, it can use the Google News API or APIs that provide financial market data to obtain relevant information in real time.

[0252] The collected data is analyzed on the server. This analysis utilizes language analysis techniques such as Python's NLTK library. This process involves extracting relevant information topics and performing sentiment analysis. Through this process, important information related to specific keywords is identified and provided to users for decision-making.

[0253] The analysis results are transmitted to the user's terminal via a presentation device. The terminal receives this data and displays it as visual information on the user interface. This allows the user to immediately access relevant information, for example, to check the trends of related stocks and make quick investment decisions. An example of a specific prompt message is, "Please tell me the latest news regarding the Liberal Democratic Party presidential election and the market trends of related stocks."

[0254] This system enables users to cope with information overload and efficiently utilize relevant information, thereby supporting accurate and rapid decision-making.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] Users enter specific keywords through their device's interface. Specifically, they enter keywords into input forms in their device's web browser or application and then press a "Submit" or "Search" button. The entered data consists of keywords related to topics or events of interest to the user. These keywords are then sent to the server.

[0258] Step 2:

[0259] The terminal sends keywords entered by the user to the server. Based on the received input keywords, the server uses data collection methods to gather relevant data from online information sources and market databases. This data collection utilizes, for example, news APIs and market data APIs. The input is keywords, and the output is a data list of related information and news articles.

[0260] Step 3:

[0261] The server analyzes the collected data. For analysis, it uses the Python NLTK library as a natural language processing technique. The server extracts relevant informational topics from the input data and evaluates the data by performing sentiment analysis. Specifically, it identifies positive, negative, and neutral sentiment tones. The input is the collected data, and the output is the analyzed informational topics and the results of the sentiment analysis.

[0262] Step 4:

[0263] The server organizes the analysis results and sends them to the user's terminal via a presentation method. The server converts the data into a visually easy-to-understand format (e.g., JSON format) before sending it. The input is the analyzed information, and the output is the formatted data.

[0264] Step 5:

[0265] The terminal receives formatted data sent from the server and displays it visually on the user interface. The terminal expands this data on the screen in text or graphical format, allowing the user to view the information at a glance. Specifically, it displays relevant stock trends and news summaries. The input is formatted data, and the output is information that the user can visually review.

[0266] This process allows users to quickly refer to the information provided and make decisions.

[0267] (Application Example 1)

[0268] 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."

[0269] In modern electronic payment services, users are required to make quick decisions based on rapidly changing market information, but conventional systems have the problem of not being able to provide sufficient support to guarantee such immediacy. The present invention aims to solve these problems and provide a system that helps users make quick and accurate decisions based on market trends.

[0270] 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.

[0271] In this invention, the server includes terminal means for receiving user input, data collection means for collecting information related to the user input, data analysis means for analyzing the collected information and extracting relevant data through sentiment analysis, and visualization means for visually presenting the extracted information to the user. This enables the user to immediately understand relevant market trends and make quick decisions.

[0272] A "terminal device" is a device equipped with an interface for user input.

[0273] "Data collection means" refers to functions for obtaining information related to user input from the internet or databases.

[0274] "Data analysis means" refers to a function that processes collected information and extracts relevant data using natural language processing and sentiment analysis.

[0275] "Visualization means" refers to functions such as screen display and graph generation that present extracted information to the user in an easy-to-understand manner.

[0276] In order to implement this invention, it is necessary to construct a system in which a terminal, data collection means, data analysis means, and visualization means function in coordination.

[0277] The user enters specific keywords using a terminal. The terminal sends this input to a data collection system. The data collection system retrieves information related to the user input in real time from internet sources or specific databases. In this case, it is recommended to use an API for data collection.

[0278] Next, the data analysis tools process the information they have acquired. This process uses VADER, a Python natural language processing library, to perform sentiment analysis and extract emotional trends and market developments related to user input. This analysis can uncover hidden relevant data that can aid in user decision-making.

[0279] The server then formats the analyzed data and transmits it to the terminal through a visualization mechanism. The terminal graphically displays the information in its user interface, allowing the user to gain concrete insights to support their own decision-making. Methods such as bar graphs and line graphs are used for visualization.

[0280] For example, when a user inputs the keyword "climate change", the system collects relevant market news and calculates the sentiment scores for their headlines. Based on the results, it shows users the trends in the financial markets related to climate change and provides visual information that is useful for making quick and accurate investment decisions.

[0281] Example of a prompt sentence for the generative AI model:

[0282] "Please create a Python program that collects relevant market data based on the keyword input by the user, performs sentiment analysis, and displays the results in an understandable way. Assume the keyword is 'climate change' and use the API for market data."

[0283] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0284] Step 1:

[0285] The user inputs a specific keyword through the terminal. The input keyword is sent from the input interface of the terminal to the data collection means. The input functions as direct information from the user and provides the data that forms the basis for the next processing step.

[0286] Step 2:

[0287] The data collection means of the server accesses information sources on the Internet and specific databases, and obtains information related to the user input in real time. In this step, the API is called using the input keyword to collect relevant news and market data. The input is the keyword, and the output is a set of relevant data.

[0288] Step 3:

[0289] The server's data analysis method receives collected information and performs sentiment analysis on it. Specifically, it uses the Python VADER library to calculate sentiment scores for collected articles and news headlines. The input is a set of related data, and the output is analytical information including sentiment scores.

[0290] Step 4:

[0291] The server formats the analysis results and sends them to the terminal using visualization tools. Here, the organized data is converted into bar graphs and line graphs to make it easier for the user to intuitively understand. The input is the analysis information, and the output is the visualized data.

[0292] Step 5:

[0293] The terminal displays the transmitted visualization data on the user interface. Based on this visual information, users can make quick and accurate decisions. The input is visualized data, and the output is a graphical display viewable by the user.

[0294] 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.

[0295] The present invention is a system that provides relevant information based on user input and further optimizes information presentation by recognizing the user's emotions. This system is implemented with a configuration including input means, collection means, analysis means, presentation means, and an emotion engine.

[0296] First, the user enters a specific keyword using the user interface on their device. The device sends this input to the server. The server collects relevant data based on the received keyword. This data is collected in real time from online information sources and market databases, and then the collected data is analyzed using natural language processing algorithms by an analysis tool.

[0297] Furthermore, this system incorporates an emotion engine that estimates the user's emotional state from their input history and real-time responses. The emotion engine utilizes machine learning models to classify the user's emotions and feeds this information back into the analysis results. This feedback optimizes the content and order of information presentation to match the user's emotional state.

[0298] After the server compiles the relevant information, the presentation device transmits it to the terminal. The terminal displays the information on the user interface in a way that best suits the user's emotional state. The presented information includes relevant stock information and market trends, which the user can use to make decisions.

[0299] For example, if a user enters the keyword "economic crisis," the emotion engine might determine that the user is feeling anxious. In this case, the server would prioritize presenting supplementary information or expert analytics that help alleviate the anxiety.

[0300] This system will allow users not only to receive information, but also to obtain flexible and appropriate information tailored to their individual emotional state. As a result, it is expected that users' decision-making will become more efficient and rational.

[0301] The following describes the processing flow.

[0302] Step 1:

[0303] The user inputs specific keywords using the user interface of the terminal. This input functions as the first instruction to the system.

[0304] Step 2:

[0305] The terminal sends the input keywords to the server. The server starts the process of collecting relevant data based on this information.

[0306] Step 3:

[0307] The server collects information related to the input keywords from news sites and financial databases on the Internet. The collection is done in real-time to obtain the latest data.

[0308] Step 4:

[0309] The server passes the collected data to the analysis means and analyzes the data using natural language processing algorithms. Based on the analysis results, relevant stocks and market trends are extracted.

[0310] Step 5:

[0311] The server estimates the user's emotional state using the emotion engine based on the user's direct input and interaction. This takes into account the input history and real-time response data.

[0312] Step 6:

[0313] The emotion engine classifies the user's emotional state and reflects the result in the output of the analysis means. The priority order of the information is reconfigured in a form that matches the user's emotion.

[0314] Step 7:

[0315] The server sends the optimized information based on the user's emotional state to the terminal. The presentation means displays this on the user interface.

[0316] Step 8:

[0317] The device presents organized information to the user. This information is tailored to the user's emotions, allowing them to use it to make optimal decisions.

[0318] Step 9:

[0319] Users review the presented information and use it to make investment decisions and take their next actions. In this process, providing information that resonates with the user's emotions supports their decision-making.

[0320] (Example 2)

[0321] 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".

[0322] Conventional information systems often fail to consider the user's emotional state when presenting information, resulting in information that is not tailored to individual emotions or needs. Consequently, user decision-making may not always be efficient. There is a growing need for systems that provide optimal information, taking emotions into account, based on the information entered by the user.

[0323] 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.

[0324] In this invention, the server includes a device for receiving user input, a device for estimating the user's emotional state, and a device for optimizing information based on the extracted information and the estimated emotional state, and presenting it to the user. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0325] "User input" refers to the act of a user providing information or instructions to a system through a device.

[0326] A "data collection device" refers to a device that has the function of collecting data from a specific source according to a particular purpose.

[0327] An "analysis device" refers to a device that has the function of analyzing acquired data and extracting necessary information.

[0328] A "device for estimating emotional state" refers to a device that has the function of inferring the emotions of a user and is characterized by using machine learning technology.

[0329] An "information optimization device" refers to a device that has the function of appropriately adjusting the information to be presented based on the extracted information and the user's emotional state.

[0330] A "presentation device" refers to a device that has the function of showing information to a user visually or by other means.

[0331] This system is an information presentation system that provides relevant information based on user input and further optimizes the presentation by recognizing the user's emotions. Its main components consist of a server, terminals, and a user interface.

[0332] The user first enters keywords through the user interface on their device. The device then transmits this input to the server. The server collects relevant information based on the received keywords. The server uses various databases and online information platforms as information sources and utilizes programming languages ​​such as Python and Java to streamline information gathering.

[0333] The collected data is analyzed on the server. Natural language processing tools such as Python's NLTK library and SpaCy are used to extract relevant information. This process narrows down important themes and trends from the vast amount of data.

[0334] The emotion engine estimates the user's emotional state based on their past behavior, input patterns, and real-time responses. Specifically, it uses machine learning models such as TensorFlow and PyTorch to classify the user's emotions into categories such as "excited," "anxious," and "neutral."

[0335] The server integrates analysis results with emotional states to optimize the presentation of information. This ensures that information is presented in a more relevant and useful way for the user.

[0336] For example, if a user enters the keyword "economic crisis," the server analyzes relevant market trends based on collected data, and the emotion engine can infer that the user is feeling anxious. In this case, the server prioritizes presenting the user with examples of economic crisis recovery and expert analyses.

[0337] An example of a prompt to the generating AI model would be, "Please tell me about market trends that may be affected by the economic crisis." In response to this prompt, the system will provide information best suited to the user's situation.

[0338] This system aims to support more efficient decision-making by enabling users not only to acquire information but also to obtain flexible and appropriate information tailored to their individual emotional states.

[0339] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0340] Step 1:

[0341] The user enters a keyword into the terminal. For example, the user might enter a specific keyword such as "economic forecast." The entered keyword is sent from the terminal to the server. This input acts as a trigger for the server to collect relevant information.

[0342] Step 2:

[0343] The server receives keywords and collects information based on those keywords. The server retrieves relevant data from online databases, news sites, etc., using APIs. The input is keywords, and the output is a collection of related data. The server implements filtering algorithms to maintain the quality and relevance of the data.

[0344] Step 3:

[0345] The server analyzes the collected data. Specifically, it uses Python's NLTK library and natural language processing software to analyze text data. This analysis extracts important contexts and topics. The input is the collected data, and the output is summarized relevant information. The server then uses the data to extract frequently occurring words, etc.

[0346] Step 4:

[0347] The server uses an emotion engine to estimate the user's emotions. In this step, past user activity and real-time responses are fed into a machine learning model to classify emotions as "excited," "anxious," or "neutral." The input is user response data, and the output is the estimated emotion. TensorFlow is used for this classification.

[0348] Step 5:

[0349] The server integrates analysis results and emotional information to optimize the content of the information provided. Specifically, it changes the priority of information based on the emotional state. For example, if anxiety is detected, the system prioritizes displaying information that provides reassurance. The input is the analysis results and emotional information, and the output is a list of optimized information.

[0350] Step 6:

[0351] The server sends optimized information to the terminal. The terminal displays the received information in its user interface. This allows the user to receive information in a way that aligns with their emotional state. The input is optimized information, and the output is a display of information that the user can visually confirm.

[0352] (Application Example 2)

[0353] 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."

[0354] When making electronic payments, users often experience anxiety and hesitation. These emotions can blur decision-making and disrupt the transaction flow. Traditional systems lack the ability to recognize user emotions and optimize information accordingly, making it difficult to provide an appropriate user experience based on those emotions. To address this challenge, a system is needed that presents information in accordance with the user's emotional state, thereby providing a sense of security.

[0355] 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.

[0356] In this invention, the server includes a device for receiving user input, a device for collecting information related to the user input, a device for analyzing the collected information and extracting relevant knowledge, and a device for estimating the user's emotional state and optimizing information presentation. This enables information presentation optimized based on the user's emotions, providing a safe and smooth electronic payment experience.

[0357] "User input" refers to information and commands provided by the user via a terminal or device.

[0358] A "data collection device" refers to a device that has the function of acquiring external information and data related to user input.

[0359] An "analysis device" refers to a device used to analyze collected information and extract relevant knowledge and patterns.

[0360] A "presentation device" refers to a device that displays analyzed knowledge to the user through visual or auditory means.

[0361] An "emotion estimation device" refers to a device that detects the user's emotional state from their input history and real-time responses, and adjusts the information presented based on that state.

[0362] In the system implementing this invention, the user inputs information using a device such as a smartphone. The information entered by the user is received as keywords or requests in natural language. The entered information is sent to a server, which then collects relevant external information and data in real time based on that information.

[0363] The collected information is analyzed using a natural language processing model executed on the server. This analysis utilizes natural language processing libraries such as NLTK and spaCy. Highly relevant knowledge and patterns are extracted from the analysis results.

[0364] Simultaneously, an emotion estimation device estimates the user's emotional state. This device utilizes machine learning model libraries such as Scikit-learn and TensorFlow. Emotions are classified based on the user's input history and physiological responses, and the results are fed back into the information presentation.

[0365] Ultimately, the presentation of information is optimized based on the analysis results and sentiment estimation. The presentation device displays relevant knowledge on the terminal in a way that best suits the user's emotional state. This process allows the user to gain confidence regarding the transaction.

[0366] For example, if a user feels anxious when making their first credit card payment through online shopping, the emotion estimation device will detect this anxiety. In response, the presentation device will reduce the user's anxiety by prioritizing the display of information about past secure transactions and enhanced security.

[0367] An example of a prompt message could be, "If a user feels anxious about making an online payment, how would you present information to alleviate that anxiety?" This allows for the consideration of strategies for presenting information based on emotions.

[0368] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0369] Step 1:

[0370] The user uses a device to input natural language keywords or requests. The input information is sent to the server through the device's user interface. The input may include specific topics or questions that the user has expressed interest in.

[0371] Step 2:

[0372] The server collects relevant external information and data in real time based on the user input it receives. The collection device retrieves the necessary data from online information sources and databases. The input for this step is the user's keywords, and the output is the retrieved relevant data.

[0373] Step 3:

[0374] The collected data is analyzed using a natural language processing model on the server. The server uses libraries such as NLTK and spaCy to analyze the data and extract relevant knowledge and patterns. The input is the collected data, and the output is the analyzed knowledge.

[0375] Step 4:

[0376] Simultaneously, the server's emotion estimation device infers the user's emotional state. The device uses machine learning models such as Scikit-learn and TensorFlow to classify emotions from the user's input history and physiological responses. In this step, the input is the user's historical data, and the output is the inferred emotional state.

[0377] Step 5:

[0378] The server integrates the analyzed knowledge and inferred emotional state to optimize information presentation. Specifically, it prioritizes relevant information based on the user's emotions and adjusts the content of the presentation. The input to this process is the output from steps 3 and 4, and the output is the optimized presentation information.

[0379] Step 6:

[0380] Finally, the optimized information is returned to the device and displayed through the user interface. The device presents the user with emotionally reassuring information and recommendations. In this step, the input is the optimized information from the server, and the output is what is displayed in the user interface.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Third Embodiment]

[0385] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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".

[0397] The present invention is a system that supports efficient decision-making by users by providing relevant information based on user input. This system is implemented with a configuration that includes input means, collection means, analysis means, and presentation means.

[0398] First, the user enters a specific keyword into an input device using their terminal. This input is transmitted to a server, which then collects data related to that keyword. For this data collection, the server utilizes real-time updates from various online information sources and market databases to obtain highly accurate information.

[0399] Next, the server passes the collected data to an analysis tool, where a natural language processing algorithm is used. This algorithm identifies topics related to keywords within the data and extracts information that may influence investment decisions through sentiment analysis.

[0400] The analyzed information is organized on the server and transmitted to the user's terminal via a presentation mechanism. The terminal receives this information and supports the user's decision-making by displaying relevant stock information and market trends on the user interface.

[0401] For example, if a user enters "LDP presidential election," the server will collect relevant news and analyze it to identify sectors and stocks sensitive to political developments. The information presented will include predictions of stock price fluctuations and trends in potentially affected industries, allowing the user to make quick investment decisions based on this information.

[0402] Thus, this system is designed to allow users to easily obtain the data they need through each stage of information collection, analysis, and presentation, and to directly link it to decision-making. As a result, users can respond quickly to rapid market fluctuations.

[0403] The following describes the processing flow.

[0404] Step 1:

[0405] The user enters a specific keyword through the terminal's user interface. This keyword becomes part of the data sent to the server.

[0406] Step 2:

[0407] User input is sent from the terminal to the server. The server then starts a process to collect relevant data based on the received keywords.

[0408] Step 3:

[0409] The server collects the latest information related to the entered keywords from news sites and market databases on the internet. This collection uses APIs to obtain real-time data.

[0410] Step 4:

[0411] The server passes the collected data to an analysis tool, which then analyzes the data using natural language processing algorithms. This process involves topic extraction and sentiment analysis, identifying potential investment candidates related to keywords.

[0412] Step 5:

[0413] The results of the analysis are returned to the server and organized as relevant information. At this stage, information about specific stocks and their market trends is selected.

[0414] Step 6:

[0415] The server sends the selected information to the terminal. The display format is adjusted so that the information is presented in a way that is easy for the user to understand and process.

[0416] Step 7:

[0417] The terminal displays information received from the server on the user interface. This includes detailed information about relevant stocks and market conditions, which users can use to make investment decisions.

[0418] Step 8:

[0419] Users evaluate the presented information and, if necessary, conduct further research or proceed to actual investment actions. This process enables users to make quick and informed decisions.

[0420] (Example 1)

[0421] 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."

[0422] In today's information-saturated age, users need to efficiently collect, analyze, and provide relevant information in a timely manner in order to make quick and accurate decisions. However, conventional systems have problems such as the information becoming outdated or users becoming confused by excessive information.

[0423] 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.

[0424] In this invention, the server includes an input means for receiving user input, a collection means for collecting relevant information, and an analysis means for analyzing the information and extracting topics. This enables users to quickly obtain relevant information and expedite decision-making.

[0425] "User input" refers to data and information entered by a user through a terminal or computer interface.

[0426] "Collection means" refers to devices or methods that have the function of acquiring data and information related to user input from external sources.

[0427] "Analysis methods" refer to the processes and techniques used to analyze collected information and extract specific topics or relevant information from it.

[0428] "Presentation means" refers to devices or methods for providing analyzed information to users in a visual or other way.

[0429] "Communication methods" refer to technologies, including network interfaces and protocols, that enable data exchange between external information sources and servers, and allow information to be obtained in real time.

[0430] In embodiments of the present invention, a system is configured in which a user, a terminal, and a server cooperate to efficiently collect, analyze, and provide information.

[0431] The user enters specific keywords using a device. A device refers to an information device such as a computer or smartphone, which provides an interface for the user to input information and receive results. Specifically, keywords are entered through a web browser or dedicated application on the device.

[0432] The entered keyword is sent from the terminal to the server. The server is where data collection takes place, and it queries online information sources and market databases. For example, it can use the Google News API or APIs that provide financial market data to obtain relevant information in real time.

[0433] The collected data is analyzed on the server. This analysis utilizes language analysis techniques such as Python's NLTK library. This process involves extracting relevant information topics and performing sentiment analysis. Through this process, important information related to specific keywords is identified and provided to users for decision-making.

[0434] The analysis results are transmitted to the user's terminal via a presentation device. The terminal receives this data and displays it as visual information on the user interface. This allows the user to immediately access relevant information, for example, to check the trends of related stocks and make quick investment decisions. An example of a specific prompt message is, "Please tell me the latest news regarding the Liberal Democratic Party presidential election and the market trends of related stocks."

[0435] This system enables users to cope with information overload and efficiently utilize relevant information, thereby supporting accurate and rapid decision-making.

[0436] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0437] Step 1:

[0438] Users enter specific keywords through their device's interface. Specifically, they enter keywords into input forms in their device's web browser or application and then press a "Submit" or "Search" button. The entered data consists of keywords related to topics or events of interest to the user. These keywords are then sent to the server.

[0439] Step 2:

[0440] The terminal sends keywords entered by the user to the server. Based on the received input keywords, the server uses data collection methods to gather relevant data from online information sources and market databases. This data collection utilizes, for example, news APIs and market data APIs. The input is keywords, and the output is a data list of related information and news articles.

[0441] Step 3:

[0442] The server analyzes the collected data. For analysis, it uses the Python NLTK library as a natural language processing technique. The server extracts relevant informational topics from the input data and evaluates the data by performing sentiment analysis. Specifically, it identifies positive, negative, and neutral sentiment tones. The input is the collected data, and the output is the analyzed informational topics and the results of the sentiment analysis.

[0443] Step 4:

[0444] The server organizes the analysis results and sends them to the user's terminal via a presentation method. The server converts the data into a visually easy-to-understand format (e.g., JSON format) before sending it. The input is the analyzed information, and the output is the formatted data.

[0445] Step 5:

[0446] The terminal receives formatted data sent from the server and displays it visually on the user interface. The terminal expands this data on the screen in text or graphical format, allowing the user to view the information at a glance. Specifically, it displays relevant stock trends and news summaries. The input is formatted data, and the output is information that the user can visually review.

[0447] This process allows users to quickly refer to the information provided and make decisions.

[0448] (Application Example 1)

[0449] 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."

[0450] In modern electronic payment services, users are required to make quick decisions based on rapidly changing market information, but conventional systems have the problem of not being able to provide sufficient support to guarantee such immediacy. The present invention aims to solve these problems and provide a system that helps users make quick and accurate decisions based on market trends.

[0451] 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.

[0452] In this invention, the server includes terminal means for receiving user input, data collection means for collecting information related to the user input, data analysis means for analyzing the collected information and extracting relevant data through sentiment analysis, and visualization means for visually presenting the extracted information to the user. This enables the user to immediately understand relevant market trends and make quick decisions.

[0453] A "terminal device" is a device equipped with an interface for user input.

[0454] "Data collection means" refers to functions for obtaining information related to user input from the internet or databases.

[0455] "Data analysis means" refers to a function that processes collected information and extracts relevant data using natural language processing and sentiment analysis.

[0456] "Visualization means" refers to functions such as screen display and graph generation that present extracted information to the user in an easy-to-understand manner.

[0457] In order to implement this invention, it is necessary to construct a system in which a terminal, data collection means, data analysis means, and visualization means function in coordination.

[0458] The user enters specific keywords using a terminal. The terminal sends this input to a data collection system. The data collection system retrieves information related to the user input in real time from internet sources or specific databases. In this case, it is recommended to use an API for data collection.

[0459] Next, the data analysis tools process the information they have acquired. This process uses VADER, a Python natural language processing library, to perform sentiment analysis and extract emotional trends and market developments related to user input. This analysis can uncover hidden relevant data that can aid in user decision-making.

[0460] The server then formats the analyzed data and transmits it to the terminal through a visualization mechanism. The terminal graphically displays the information in its user interface, allowing the user to gain concrete insights to support their own decision-making. Methods such as bar graphs and line graphs are used for visualization.

[0461] For example, if a user enters the keyword "climate change," the system will collect relevant market news and calculate sentiment scores for those headlines. Based on these results, it will show the user financial market trends related to climate change, providing visual information to help them make quick and accurate investment decisions.

[0462] Examples of prompts for a generative AI model:

[0463] Create a Python program that collects relevant market data based on a keyword entered by the user, performs sentiment analysis, and displays the results in an easy-to-understand format. Assume the keyword is "climate change" and use a market data API.

[0464] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0465] Step 1:

[0466] The user enters a specific keyword through the terminal. The entered keyword is transmitted from the terminal's input interface to the data collection means. The input functions as direct information from the user and provides the data that forms the basis for the next processing step.

[0467] Step 2:

[0468] The server's data collection method involves accessing internet-based information sources and specific databases to obtain information relevant to user input in real time. In this step, APIs are called using input keywords to collect relevant news and market data. The input is keywords, and the output is a collection of relevant data.

[0469] Step 3:

[0470] The server's data analysis method receives collected information and performs sentiment analysis on it. Specifically, it uses the Python VADER library to calculate sentiment scores for collected articles and news headlines. The input is a set of related data, and the output is analytical information including sentiment scores.

[0471] Step 4:

[0472] The server formats the analysis results and sends them to the terminal using visualization tools. Here, the organized data is converted into bar graphs and line graphs to make it easier for the user to intuitively understand. The input is the analysis information, and the output is the visualized data.

[0473] Step 5:

[0474] The terminal displays the transmitted visualization data on the user interface. Based on this visual information, users can make quick and accurate decisions. The input is visualized data, and the output is a graphical display viewable by the user.

[0475] 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.

[0476] The present invention is a system that provides relevant information based on user input and further optimizes information presentation by recognizing the user's emotions. This system is implemented with a configuration including input means, collection means, analysis means, presentation means, and an emotion engine.

[0477] First, the user enters a specific keyword using the user interface on their device. The device sends this input to the server. The server collects relevant data based on the received keyword. This data is collected in real time from online information sources and market databases, and then the collected data is analyzed using natural language processing algorithms by an analysis tool.

[0478] Furthermore, this system incorporates an emotion engine that estimates the user's emotional state from their input history and real-time responses. The emotion engine utilizes machine learning models to classify the user's emotions and feeds this information back into the analysis results. This feedback optimizes the content and order of information presentation to match the user's emotional state.

[0479] After the server compiles the relevant information, the presentation device transmits it to the terminal. The terminal displays the information on the user interface in a way that best suits the user's emotional state. The presented information includes relevant stock information and market trends, which the user can use to make decisions.

[0480] For example, if a user enters the keyword "economic crisis," the emotion engine might determine that the user is feeling anxious. In this case, the server would prioritize presenting supplementary information or expert analytics that help alleviate the anxiety.

[0481] This system will allow users not only to receive information, but also to obtain flexible and appropriate information tailored to their individual emotional state. As a result, it is expected that users' decision-making will become more efficient and rational.

[0482] The following describes the processing flow.

[0483] Step 1:

[0484] The user enters a specific keyword using the terminal's user interface. This input serves as the initial instruction to the system.

[0485] Step 2:

[0486] The terminal sends the entered keyword to the server. The server then starts the process of collecting relevant data based on this information.

[0487] Step 3:

[0488] The server collects information related to the entered keywords from news sites and financial databases on the internet. Collection is performed in real time, ensuring that the latest data is obtained.

[0489] Step 4:

[0490] The server passes the collected data to an analysis tool, which then analyzes the data using natural language processing algorithms. Based on the analysis results, it extracts relevant stocks and market trends.

[0491] Step 5:

[0492] The server uses an emotion engine to estimate the user's emotional state based on direct user input and interaction. This takes into account input history and real-time response data.

[0493] Step 6:

[0494] The emotion engine classifies the user's emotional state and reflects the results in the output of the analysis tool. The information is then re-prioritized in a way that matches the user's emotions.

[0495] Step 7:

[0496] The server sends optimized information to the terminal based on the user's emotional state. The presentation means then displays this information on the user interface.

[0497] Step 8:

[0498] The device presents organized information to the user. This information is tailored to the user's emotions, allowing them to use it to make optimal decisions.

[0499] Step 9:

[0500] Users review the presented information and use it to make investment decisions and take their next actions. In this process, providing information that resonates with the user's emotions supports their decision-making.

[0501] (Example 2)

[0502] 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."

[0503] Conventional information systems often fail to consider the user's emotional state when presenting information, resulting in information that is not tailored to individual emotions or needs. Consequently, user decision-making may not always be efficient. There is a growing need for systems that provide optimal information, taking emotions into account, based on the information entered by the user.

[0504] 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.

[0505] In this invention, the server includes a device for receiving user input, a device for estimating the user's emotional state, and a device for optimizing information based on the extracted information and the estimated emotional state, and presenting it to the user. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0506] "User input" refers to the act of a user providing information or instructions to a system through a device.

[0507] A "data collection device" refers to a device that has the function of collecting data from a specific source according to a particular purpose.

[0508] An "analysis device" refers to a device that has the function of analyzing acquired data and extracting necessary information.

[0509] A "device for estimating emotional state" refers to a device that has the function of inferring the emotions of a user and is characterized by using machine learning technology.

[0510] An "information optimization device" refers to a device that has the function of appropriately adjusting the information to be presented based on the extracted information and the user's emotional state.

[0511] A "presentation device" refers to a device that has the function of showing information to a user visually or by other means.

[0512] This system is an information presentation system that provides relevant information based on user input and further optimizes the presentation by recognizing the user's emotions. Its main components consist of a server, terminals, and a user interface.

[0513] The user first enters keywords through the user interface on their device. The device then transmits this input to the server. The server collects relevant information based on the received keywords. The server uses various databases and online information platforms as information sources and utilizes programming languages ​​such as Python and Java to streamline information gathering.

[0514] The collected data is analyzed on the server. Natural language processing tools such as Python's NLTK library and SpaCy are used to extract relevant information. This process narrows down important themes and trends from the vast amount of data.

[0515] The emotion engine estimates the user's emotional state based on their past behavior, input patterns, and real-time responses. Specifically, it uses machine learning models such as TensorFlow and PyTorch to classify the user's emotions into categories such as "excited," "anxious," and "neutral."

[0516] The server integrates analysis results with emotional states to optimize the presentation of information. This ensures that information is presented in a more relevant and useful way for the user.

[0517] For example, if a user enters the keyword "economic crisis," the server analyzes relevant market trends based on collected data, and the emotion engine can infer that the user is feeling anxious. In this case, the server prioritizes presenting the user with examples of economic crisis recovery and expert analyses.

[0518] An example of a prompt to the generating AI model would be, "Please tell me about market trends that may be affected by the economic crisis." In response to this prompt, the system will provide information best suited to the user's situation.

[0519] This system aims to support more efficient decision-making by enabling users not only to acquire information but also to obtain flexible and appropriate information tailored to their individual emotional states.

[0520] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0521] Step 1:

[0522] The user enters a keyword into the terminal. For example, the user might enter a specific keyword such as "economic forecast." The entered keyword is sent from the terminal to the server. This input acts as a trigger for the server to collect relevant information.

[0523] Step 2:

[0524] The server receives keywords and collects information based on those keywords. The server retrieves relevant data from online databases, news sites, etc., using APIs. The input is keywords, and the output is a collection of related data. The server implements filtering algorithms to maintain the quality and relevance of the data.

[0525] Step 3:

[0526] The server analyzes the collected data. Specifically, it uses Python's NLTK library and natural language processing software to analyze text data. This analysis extracts important contexts and topics. The input is the collected data, and the output is summarized relevant information. The server then uses the data to extract frequently occurring words, etc.

[0527] Step 4:

[0528] The server uses an emotion engine to estimate the user's emotions. In this step, past user activity and real-time responses are fed into a machine learning model to classify emotions as "excited," "anxious," or "neutral." The input is user response data, and the output is the estimated emotion. TensorFlow is used for this classification.

[0529] Step 5:

[0530] The server integrates analysis results and emotional information to optimize the content of the information provided. Specifically, it changes the priority of information based on the emotional state. For example, if anxiety is detected, the system prioritizes displaying information that provides reassurance. The input is the analysis results and emotional information, and the output is a list of optimized information.

[0531] Step 6:

[0532] The server sends optimized information to the terminal. The terminal displays the received information in its user interface. This allows the user to receive information in a way that aligns with their emotional state. The input is optimized information, and the output is a display of information that the user can visually confirm.

[0533] (Application Example 2)

[0534] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0535] When making electronic payments, users often experience anxiety and hesitation. These emotions can blur decision-making and disrupt the transaction flow. Traditional systems lack the ability to recognize user emotions and optimize information accordingly, making it difficult to provide an appropriate user experience based on those emotions. To address this challenge, a system is needed that presents information in accordance with the user's emotional state, thereby providing a sense of security.

[0536] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0537] In this invention, the server includes a device for receiving user input, a device for collecting information related to the user input, a device for analyzing the collected information and extracting relevant knowledge, and a device for estimating the user's emotional state and optimizing information presentation. This enables information presentation optimized based on the user's emotions, providing a safe and smooth electronic payment experience.

[0538] "User input" refers to information and commands provided by the user via a terminal or device.

[0539] A "data collection device" refers to a device that has the function of acquiring external information and data related to user input.

[0540] An "analysis device" refers to a device used to analyze collected information and extract relevant knowledge and patterns.

[0541] A "presentation device" refers to a device that displays analyzed knowledge to the user through visual or auditory means.

[0542] An "emotion estimation device" refers to a device that detects the user's emotional state from their input history and real-time responses, and adjusts the information presented based on that state.

[0543] In the system implementing this invention, the user inputs information using a device such as a smartphone. The information entered by the user is received as keywords or requests in natural language. The entered information is sent to a server, which then collects relevant external information and data in real time based on that information.

[0544] The collected information is analyzed using a natural language processing model executed on the server. This analysis utilizes natural language processing libraries such as NLTK and spaCy. Highly relevant knowledge and patterns are extracted from the analysis results.

[0545] Simultaneously, an emotion estimation device estimates the user's emotional state. This device utilizes machine learning model libraries such as Scikit-learn and TensorFlow. Emotions are classified based on the user's input history and physiological responses, and the results are fed back into the information presentation.

[0546] Ultimately, the presentation of information is optimized based on the analysis results and sentiment estimation. The presentation device displays relevant knowledge on the terminal in a way that best suits the user's emotional state. This process allows the user to gain confidence regarding the transaction.

[0547] For example, if a user feels anxious when making their first credit card payment through online shopping, the emotion estimation device will detect this anxiety. In response, the presentation device will reduce the user's anxiety by prioritizing the display of information about past secure transactions and enhanced security.

[0548] An example of a prompt message could be, "If a user feels anxious about making an online payment, how would you present information to alleviate that anxiety?" This allows for the consideration of strategies for presenting information based on emotions.

[0549] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0550] Step 1:

[0551] The user uses a device to input natural language keywords or requests. The input information is sent to the server through the device's user interface. The input may include specific topics or questions that the user has expressed interest in.

[0552] Step 2:

[0553] The server collects relevant external information and data in real time based on the user input it receives. The collection device retrieves the necessary data from online information sources and databases. The input for this step is the user's keywords, and the output is the retrieved relevant data.

[0554] Step 3:

[0555] The collected data is analyzed using a natural language processing model on the server. The server uses libraries such as NLTK and spaCy to analyze the data and extract relevant knowledge and patterns. The input is the collected data, and the output is the analyzed knowledge.

[0556] Step 4:

[0557] Simultaneously, the server's emotion estimation device infers the user's emotional state. The device uses machine learning models such as Scikit-learn and TensorFlow to classify emotions from the user's input history and physiological responses. In this step, the input is the user's historical data, and the output is the inferred emotional state.

[0558] Step 5:

[0559] The server integrates the analyzed knowledge and inferred emotional state to optimize information presentation. Specifically, it prioritizes relevant information based on the user's emotions and adjusts the content of the presentation. The input to this process is the output from steps 3 and 4, and the output is the optimized presentation information.

[0560] Step 6:

[0561] Finally, the optimized information is returned to the device and displayed through the user interface. The device presents the user with emotionally reassuring information and recommendations. In this step, the input is the optimized information from the server, and the output is what is displayed in the user interface.

[0562] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0563] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0564] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0565] [Fourth Embodiment]

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

[0567] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0568] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0569] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0570] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0571] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0572] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0573] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0574] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0575] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0576] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0577] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0578] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0579] The present invention is a system that supports efficient decision-making by users by providing relevant information based on user input. This system is implemented with a configuration that includes input means, collection means, analysis means, and presentation means.

[0580] First, the user enters a specific keyword into an input device using their terminal. This input is transmitted to a server, which then collects data related to that keyword. For this data collection, the server utilizes real-time updates from various online information sources and market databases to obtain highly accurate information.

[0581] Next, the server passes the collected data to an analysis tool, where a natural language processing algorithm is used. This algorithm identifies topics related to keywords within the data and extracts information that may influence investment decisions through sentiment analysis.

[0582] The analyzed information is organized on the server and transmitted to the user's terminal via a presentation mechanism. The terminal receives this information and supports the user's decision-making by displaying relevant stock information and market trends on the user interface.

[0583] For example, if a user enters "LDP presidential election," the server will collect relevant news and analyze it to identify sectors and stocks sensitive to political developments. The information presented will include predictions of stock price fluctuations and trends in potentially affected industries, allowing the user to make quick investment decisions based on this information.

[0584] Thus, this system is designed to allow users to easily obtain the data they need through each stage of information collection, analysis, and presentation, and to directly link it to decision-making. As a result, users can respond quickly to rapid market fluctuations.

[0585] The following describes the processing flow.

[0586] Step 1:

[0587] The user enters a specific keyword through the terminal's user interface. This keyword becomes part of the data sent to the server.

[0588] Step 2:

[0589] User input is sent from the terminal to the server. The server then starts a process to collect relevant data based on the received keywords.

[0590] Step 3:

[0591] The server collects the latest information related to the entered keywords from news sites and market databases on the internet. This collection uses APIs to obtain real-time data.

[0592] Step 4:

[0593] The server passes the collected data to an analysis tool, which then analyzes the data using natural language processing algorithms. This process involves topic extraction and sentiment analysis, identifying potential investment candidates related to keywords.

[0594] Step 5:

[0595] The results of the analysis are returned to the server and organized as relevant information. At this stage, information about specific stocks and their market trends is selected.

[0596] Step 6:

[0597] The server sends the selected information to the terminal. The display format is adjusted so that the information is presented in a way that is easy for the user to understand and process.

[0598] Step 7:

[0599] The terminal displays information received from the server on the user interface. This includes detailed information about relevant stocks and market conditions, which users can use to make investment decisions.

[0600] Step 8:

[0601] Users evaluate the presented information and, if necessary, conduct further research or proceed to actual investment actions. This process enables users to make quick and informed decisions.

[0602] (Example 1)

[0603] 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".

[0604] In today's information-saturated age, users need to efficiently collect, analyze, and provide relevant information in a timely manner in order to make quick and accurate decisions. However, conventional systems have problems such as the information becoming outdated or users becoming confused by excessive information.

[0605] 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.

[0606] In this invention, the server includes an input means for receiving user input, a collection means for collecting relevant information, and an analysis means for analyzing the information and extracting topics. This enables users to quickly obtain relevant information and expedite decision-making.

[0607] "User input" refers to data and information entered by a user through a terminal or computer interface.

[0608] "Collection means" refers to devices or methods that have the function of acquiring data and information related to user input from external sources.

[0609] "Analysis methods" refer to the processes and techniques used to analyze collected information and extract specific topics or relevant information from it.

[0610] "Presentation means" refers to devices or methods for providing analyzed information to users in a visual or other way.

[0611] "Communication methods" refer to technologies, including network interfaces and protocols, that enable data exchange between external information sources and servers, and allow information to be obtained in real time.

[0612] In embodiments of the present invention, a system is configured in which a user, a terminal, and a server cooperate to efficiently collect, analyze, and provide information.

[0613] The user enters specific keywords using a device. A device refers to an information device such as a computer or smartphone, which provides an interface for the user to input information and receive results. Specifically, keywords are entered through a web browser or dedicated application on the device.

[0614] The entered keyword is sent from the terminal to the server. The server is where data collection takes place, and it queries online information sources and market databases. For example, it can use the Google News API or APIs that provide financial market data to obtain relevant information in real time.

[0615] The collected data is analyzed on the server. This analysis utilizes language analysis techniques such as Python's NLTK library. This process involves extracting relevant information topics and performing sentiment analysis. Through this process, important information related to specific keywords is identified and provided to users for decision-making.

[0616] The analysis results are transmitted to the user's terminal via a presentation device. The terminal receives this data and displays it as visual information on the user interface. This allows the user to immediately access relevant information, for example, to check the trends of related stocks and make quick investment decisions. An example of a specific prompt message is, "Please tell me the latest news regarding the Liberal Democratic Party presidential election and the market trends of related stocks."

[0617] This system enables users to cope with information overload and efficiently utilize relevant information, thereby supporting accurate and rapid decision-making.

[0618] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0619] Step 1:

[0620] Users enter specific keywords through their device's interface. Specifically, they enter keywords into input forms in their device's web browser or application and then press a "Submit" or "Search" button. The entered data consists of keywords related to topics or events of interest to the user. These keywords are then sent to the server.

[0621] Step 2:

[0622] The terminal sends keywords entered by the user to the server. Based on the received input keywords, the server uses data collection methods to gather relevant data from online information sources and market databases. This data collection utilizes, for example, news APIs and market data APIs. The input is keywords, and the output is a data list of related information and news articles.

[0623] Step 3:

[0624] The server analyzes the collected data. For analysis, it uses the Python NLTK library as a natural language processing technique. The server extracts relevant informational topics from the input data and evaluates the data by performing sentiment analysis. Specifically, it identifies positive, negative, and neutral sentiment tones. The input is the collected data, and the output is the analyzed informational topics and the results of the sentiment analysis.

[0625] Step 4:

[0626] The server organizes the analysis results and sends them to the user's terminal via a presentation method. The server converts the data into a visually easy-to-understand format (e.g., JSON format) before sending it. The input is the analyzed information, and the output is the formatted data.

[0627] Step 5:

[0628] The terminal receives formatted data sent from the server and displays it visually on the user interface. The terminal expands this data on the screen in text or graphical format, allowing the user to view the information at a glance. Specifically, it displays relevant stock trends and news summaries. The input is formatted data, and the output is information that the user can visually review.

[0629] This process allows users to quickly refer to the information provided and make decisions.

[0630] (Application Example 1)

[0631] 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".

[0632] In modern electronic payment services, users are required to make quick decisions based on rapidly changing market information, but conventional systems have the problem of not being able to provide sufficient support to guarantee such immediacy. The present invention aims to solve these problems and provide a system that helps users make quick and accurate decisions based on market trends.

[0633] 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.

[0634] In this invention, the server includes terminal means for receiving user input, data collection means for collecting information related to the user input, data analysis means for analyzing the collected information and extracting relevant data through sentiment analysis, and visualization means for visually presenting the extracted information to the user. This enables the user to immediately understand relevant market trends and make quick decisions.

[0635] A "terminal device" is a device equipped with an interface for user input.

[0636] "Data collection means" refers to functions for obtaining information related to user input from the internet or databases.

[0637] "Data analysis means" refers to a function that processes collected information and extracts relevant data using natural language processing and sentiment analysis.

[0638] "Visualization means" refers to functions such as screen display and graph generation that present extracted information to the user in an easy-to-understand manner.

[0639] In order to implement this invention, it is necessary to construct a system in which a terminal, data collection means, data analysis means, and visualization means function in coordination.

[0640] The user enters specific keywords using a terminal. The terminal sends this input to a data collection system. The data collection system retrieves information related to the user input in real time from internet sources or specific databases. In this case, it is recommended to use an API for data collection.

[0641] Next, the data analysis tools process the information they have acquired. This process uses VADER, a Python natural language processing library, to perform sentiment analysis and extract emotional trends and market developments related to user input. This analysis can uncover hidden relevant data that can aid in user decision-making.

[0642] The server then formats the analyzed data and transmits it to the terminal through a visualization mechanism. The terminal graphically displays the information in its user interface, allowing the user to gain concrete insights to support their own decision-making. Methods such as bar graphs and line graphs are used for visualization.

[0643] For example, if a user enters the keyword "climate change," the system will collect relevant market news and calculate sentiment scores for those headlines. Based on these results, it will show the user financial market trends related to climate change, providing visual information to help them make quick and accurate investment decisions.

[0644] Examples of prompts for a generative AI model:

[0645] Create a Python program that collects relevant market data based on a keyword entered by the user, performs sentiment analysis, and displays the results in an easy-to-understand format. Assume the keyword is "climate change" and use a market data API.

[0646] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0647] Step 1:

[0648] The user enters a specific keyword through the terminal. The entered keyword is transmitted from the terminal's input interface to the data collection means. The input functions as direct information from the user and provides the data that forms the basis for the next processing step.

[0649] Step 2:

[0650] The server's data collection method involves accessing internet-based information sources and specific databases to obtain information relevant to user input in real time. In this step, APIs are called using input keywords to collect relevant news and market data. The input is keywords, and the output is a collection of relevant data.

[0651] Step 3:

[0652] The server's data analysis method receives collected information and performs sentiment analysis on it. Specifically, it uses the Python VADER library to calculate sentiment scores for collected articles and news headlines. The input is a set of related data, and the output is analytical information including sentiment scores.

[0653] Step 4:

[0654] The server formats the analysis results and sends them to the terminal using visualization tools. Here, the organized data is converted into bar graphs and line graphs to make it easier for the user to intuitively understand. The input is the analysis information, and the output is the visualized data.

[0655] Step 5:

[0656] The terminal displays the transmitted visualization data on the user interface. Based on this visual information, users can make quick and accurate decisions. The input is visualized data, and the output is a graphical display viewable by the user.

[0657] 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.

[0658] The present invention is a system that provides relevant information based on user input and further optimizes information presentation by recognizing the user's emotions. This system is implemented with a configuration including input means, collection means, analysis means, presentation means, and an emotion engine.

[0659] First, the user enters a specific keyword using the user interface on their device. The device sends this input to the server. The server collects relevant data based on the received keyword. This data is collected in real time from online information sources and market databases, and then the collected data is analyzed using natural language processing algorithms by an analysis tool.

[0660] Furthermore, this system incorporates an emotion engine that estimates the user's emotional state from their input history and real-time responses. The emotion engine utilizes machine learning models to classify the user's emotions and feeds this information back into the analysis results. This feedback optimizes the content and order of information presentation to match the user's emotional state.

[0661] After the server compiles the relevant information, the presentation device transmits it to the terminal. The terminal displays the information on the user interface in a way that best suits the user's emotional state. The presented information includes relevant stock information and market trends, which the user can use to make decisions.

[0662] For example, if a user enters the keyword "economic crisis," the emotion engine might determine that the user is feeling anxious. In this case, the server would prioritize presenting supplementary information or expert analytics that help alleviate the anxiety.

[0663] This system will allow users not only to receive information, but also to obtain flexible and appropriate information tailored to their individual emotional state. As a result, it is expected that users' decision-making will become more efficient and rational.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] The user enters a specific keyword using the terminal's user interface. This input serves as the initial instruction to the system.

[0667] Step 2:

[0668] The terminal sends the entered keyword to the server. The server then starts the process of collecting relevant data based on this information.

[0669] Step 3:

[0670] The server collects information related to the entered keywords from news sites and financial databases on the internet. Collection is performed in real time, ensuring that the latest data is obtained.

[0671] Step 4:

[0672] The server passes the collected data to an analysis tool, which then analyzes the data using natural language processing algorithms. Based on the analysis results, it extracts relevant stocks and market trends.

[0673] Step 5:

[0674] The server uses an emotion engine to estimate the user's emotional state based on direct user input and interaction. This takes into account input history and real-time response data.

[0675] Step 6:

[0676] The emotion engine classifies the user's emotional state and reflects the results in the output of the analysis tool. The information is then re-prioritized in a way that matches the user's emotions.

[0677] Step 7:

[0678] The server sends optimized information to the terminal based on the user's emotional state. The presentation means then displays this information on the user interface.

[0679] Step 8:

[0680] The device presents organized information to the user. This information is tailored to the user's emotions, allowing them to use it to make optimal decisions.

[0681] Step 9:

[0682] Users review the presented information and use it to make investment decisions and take their next actions. In this process, providing information that resonates with the user's emotions supports their decision-making.

[0683] (Example 2)

[0684] 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".

[0685] Conventional information systems often fail to consider the user's emotional state when presenting information, resulting in information that is not tailored to individual emotions or needs. Consequently, user decision-making may not always be efficient. There is a growing need for systems that provide optimal information, taking emotions into account, based on the information entered by the user.

[0686] 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.

[0687] In this invention, the server includes a device for receiving user input, a device for estimating the user's emotional state, and a device for optimizing information based on the extracted information and the estimated emotional state, and presenting it to the user. This enables flexible and appropriate information provision that takes the user's emotions into consideration.

[0688] "User input" refers to the act of a user providing information or instructions to a system through a device.

[0689] A "data collection device" refers to a device that has the function of collecting data from a specific source according to a particular purpose.

[0690] An "analysis device" refers to a device that has the function of analyzing acquired data and extracting necessary information.

[0691] A "device for estimating emotional state" refers to a device that has the function of inferring the emotions of a user and is characterized by using machine learning technology.

[0692] An "information optimization device" refers to a device that has the function of appropriately adjusting the information to be presented based on the extracted information and the user's emotional state.

[0693] A "presentation device" refers to a device that has the function of showing information to a user visually or by other means.

[0694] This system is an information presentation system that provides relevant information based on user input and further optimizes the presentation by recognizing the user's emotions. Its main components consist of a server, terminals, and a user interface.

[0695] The user first enters keywords through the user interface on their device. The device then transmits this input to the server. The server collects relevant information based on the received keywords. The server uses various databases and online information platforms as information sources and utilizes programming languages ​​such as Python and Java to streamline information gathering.

[0696] The collected data is analyzed on the server. Natural language processing tools such as Python's NLTK library and SpaCy are used to extract relevant information. This process narrows down important themes and trends from the vast amount of data.

[0697] The emotion engine estimates the user's emotional state based on their past behavior, input patterns, and real-time responses. Specifically, it uses machine learning models such as TensorFlow and PyTorch to classify the user's emotions into categories such as "excited," "anxious," and "neutral."

[0698] The server integrates analysis results with emotional states to optimize the presentation of information. This ensures that information is presented in a more relevant and useful way for the user.

[0699] For example, if a user enters the keyword "economic crisis," the server analyzes relevant market trends based on collected data, and the emotion engine can infer that the user is feeling anxious. In this case, the server prioritizes presenting the user with examples of economic crisis recovery and expert analyses.

[0700] An example of a prompt to the generating AI model would be, "Please tell me about market trends that may be affected by the economic crisis." In response to this prompt, the system will provide information best suited to the user's situation.

[0701] This system aims to support more efficient decision-making by enabling users not only to acquire information but also to obtain flexible and appropriate information tailored to their individual emotional states.

[0702] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0703] Step 1:

[0704] The user enters a keyword into the terminal. For example, the user might enter a specific keyword such as "economic forecast." The entered keyword is sent from the terminal to the server. This input acts as a trigger for the server to collect relevant information.

[0705] Step 2:

[0706] The server receives keywords and collects information based on those keywords. The server retrieves relevant data from online databases, news sites, etc., using APIs. The input is keywords, and the output is a collection of related data. The server implements filtering algorithms to maintain the quality and relevance of the data.

[0707] Step 3:

[0708] The server analyzes the collected data. Specifically, it uses Python's NLTK library and natural language processing software to analyze text data. This analysis extracts important contexts and topics. The input is the collected data, and the output is summarized relevant information. The server then uses the data to extract frequently occurring words, etc.

[0709] Step 4:

[0710] The server uses an emotion engine to estimate the user's emotions. In this step, past user activity and real-time responses are fed into a machine learning model to classify emotions as "excited," "anxious," or "neutral." The input is user response data, and the output is the estimated emotion. TensorFlow is used for this classification.

[0711] Step 5:

[0712] The server integrates analysis results and emotional information to optimize the content of the information provided. Specifically, it changes the priority of information based on the emotional state. For example, if anxiety is detected, the system prioritizes displaying information that provides reassurance. The input is the analysis results and emotional information, and the output is a list of optimized information.

[0713] Step 6:

[0714] The server sends optimized information to the terminal. The terminal displays the received information in its user interface. This allows the user to receive information in a way that aligns with their emotional state. The input is optimized information, and the output is a display of information that the user can visually confirm.

[0715] (Application Example 2)

[0716] 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".

[0717] When making electronic payments, users often experience anxiety and hesitation. These emotions can blur decision-making and disrupt the transaction flow. Traditional systems lack the ability to recognize user emotions and optimize information accordingly, making it difficult to provide an appropriate user experience based on those emotions. To address this challenge, a system is needed that presents information in accordance with the user's emotional state, thereby providing a sense of security.

[0718] 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.

[0719] In this invention, the server includes a device for receiving user input, a device for collecting information related to the user input, a device for analyzing the collected information and extracting relevant knowledge, and a device for estimating the user's emotional state and optimizing information presentation. This enables information presentation optimized based on the user's emotions, providing a safe and smooth electronic payment experience.

[0720] "User input" refers to information and commands provided by the user via a terminal or device.

[0721] A "data collection device" refers to a device that has the function of acquiring external information and data related to user input.

[0722] An "analysis device" refers to a device used to analyze collected information and extract relevant knowledge and patterns.

[0723] A "presentation device" refers to a device that displays analyzed knowledge to the user through visual or auditory means.

[0724] An "emotion estimation device" refers to a device that detects the user's emotional state from their input history and real-time responses, and adjusts the information presented based on that state.

[0725] In the system implementing this invention, the user inputs information using a device such as a smartphone. The information entered by the user is received as keywords or requests in natural language. The entered information is sent to a server, which then collects relevant external information and data in real time based on that information.

[0726] The collected information is analyzed using a natural language processing model executed on the server. This analysis utilizes natural language processing libraries such as NLTK and spaCy. Highly relevant knowledge and patterns are extracted from the analysis results.

[0727] Simultaneously, an emotion estimation device estimates the user's emotional state. This device utilizes machine learning model libraries such as Scikit-learn and TensorFlow. Emotions are classified based on the user's input history and physiological responses, and the results are fed back into the information presentation.

[0728] Ultimately, the presentation of information is optimized based on the analysis results and sentiment estimation. The presentation device displays relevant knowledge on the terminal in a way that best suits the user's emotional state. This process allows the user to gain confidence regarding the transaction.

[0729] For example, if a user feels anxious when making their first credit card payment through online shopping, the emotion estimation device will detect this anxiety. In response, the presentation device will reduce the user's anxiety by prioritizing the display of information about past secure transactions and enhanced security.

[0730] An example of a prompt message could be, "If a user feels anxious about making an online payment, how would you present information to alleviate that anxiety?" This allows for the consideration of strategies for presenting information based on emotions.

[0731] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0732] Step 1:

[0733] The user uses a device to input natural language keywords or requests. The input information is sent to the server through the device's user interface. The input may include specific topics or questions that the user has expressed interest in.

[0734] Step 2:

[0735] The server collects relevant external information and data in real time based on the user input it receives. The collection device retrieves the necessary data from online information sources and databases. The input for this step is the user's keywords, and the output is the retrieved relevant data.

[0736] Step 3:

[0737] The collected data is analyzed using a natural language processing model on the server. The server uses libraries such as NLTK and spaCy to analyze the data and extract relevant knowledge and patterns. The input is the collected data, and the output is the analyzed knowledge.

[0738] Step 4:

[0739] Simultaneously, the server's emotion estimation device infers the user's emotional state. The device uses machine learning models such as Scikit-learn and TensorFlow to classify emotions from the user's input history and physiological responses. In this step, the input is the user's historical data, and the output is the inferred emotional state.

[0740] Step 5:

[0741] The server integrates the analyzed knowledge and inferred emotional state to optimize information presentation. Specifically, it prioritizes relevant information based on the user's emotions and adjusts the content of the presentation. The input to this process is the output from steps 3 and 4, and the output is the optimized presentation information.

[0742] Step 6:

[0743] Finally, the optimized information is returned to the device and displayed through the user interface. The device presents the user with emotionally reassuring information and recommendations. In this step, the input is the optimized information from the server, and the output is what is displayed in the user interface.

[0744] 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.

[0745] 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.

[0746] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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."

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] The following is further disclosed regarding the embodiments described above.

[0766] (Claim 1)

[0767] An input means for receiving user input,

[0768] A collection means for collecting data related to the user input,

[0769] An analysis means for analyzing the collected data and extracting relevant information,

[0770] A presentation means for presenting the extracted information to the user,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, wherein the analysis means analyzes relevant information using a natural language processing algorithm.

[0774] (Claim 3)

[0775] The system according to claim 1, wherein the presentation means provides relevant information to the user in real time.

[0776] "Example 1"

[0777] (Claim 1)

[0778] An input means for receiving user input,

[0779] A collection means for collecting relevant information based on the user input,

[0780] An analysis means for analyzing the collected information and extracting relevant information topics,

[0781] A presentation means that transmits and displays the extracted information on the user's device,

[0782] Communication means for obtaining information from real-time information sources,

[0783] An information processing system that includes this.

[0784] (Claim 2)

[0785] The information processing system according to claim 1, wherein the analysis means analyzes relevant information using a language analysis method, performs sentiment analysis, and identifies important information.

[0786] (Claim 3)

[0787] The information processing system according to claim 1, wherein the presentation means provides relevant information to the user immediately through a display device.

[0788] "Application Example 1"

[0789] (Claim 1)

[0790] A terminal means for receiving user input,

[0791] A data collection means for collecting information related to the user input,

[0792] A data analysis means that analyzes the collected information and extracts relevant data through sentiment analysis,

[0793] A visualization means for visually presenting the extracted information to the user,

[0794] A system that includes this.

[0795] (Claim 2)

[0796] The system according to claim 1, wherein the data analysis means analyzes the relevant data using a natural language processing method.

[0797] (Claim 3)

[0798] The system according to claim 1, wherein the visualization means provides the user with relevant information immediately.

[0799] "Example 2 of combining an emotion engine"

[0800] (Claim 1)

[0801] A device that receives user input,

[0802] A device for collecting information related to the user input,

[0803] A device for analyzing the collected information and extracting relevant information,

[0804] A device that estimates the user's emotional state,

[0805] A device that optimizes information based on the extracted information and estimated emotional state, and presents it to the user,

[0806] A system that includes this.

[0807] (Claim 2)

[0808] The system according to claim 1, wherein the analysis device analyzes relevant information using natural language processing technology.

[0809] (Claim 3)

[0810] The system according to claim 1, wherein the estimation device classifies the user's emotions using a machine learning model.

[0811] "Application example 2 when combining with an emotional engine"

[0812] (Claim 1)

[0813] A device that receives user input,

[0814] A device for collecting information related to the user input,

[0815] A device for analyzing the collected information and extracting relevant knowledge,

[0816] A device that presents the extracted knowledge to the user,

[0817] A device for estimating the user's emotional state and optimizing information presentation,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, wherein the analysis device analyzes relevant knowledge using a natural language processing model, and further adjusts the priority of information according to the user's emotions.

[0821] (Claim 3)

[0822] The system according to claim 1, wherein the presentation device provides the user with relevant knowledge in real time and presents information based on emotion. [Explanation of Symbols]

[0823] 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. An input means for receiving user input, A collection means for collecting data related to the user input, An analysis means for analyzing the collected data and extracting relevant information, A presentation means for presenting the extracted information to the user, A system that includes this.

2. The system according to claim 1, wherein the analysis means analyzes relevant information using a natural language processing algorithm.

3. The system according to claim 1, wherein the presentation means provides relevant information to the user in real time.

Images