system

Abstract

We provide the system. [Solution] A means of collecting past market data, A method for analyzing past market data using a generative AI model to predict future market price movements, A means of visually displaying predicted future market price movements, A means of issuing a warning when a large price movement is predicted, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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] Many individual investors and beginners lack advanced knowledge and experience for making appropriate investment decisions in markets such as stocks, foreign exchange, and virtual currencies. Therefore, it is difficult to conduct accurate market analysis and prediction. As a result, the risk of losses increases while opportunities to maximize profits are often missed. In addition, it is difficult to immediately respond to rapid market fluctuations, which may lead to further asset losses. To solve such problems, there is a demand for a system that enables anyone to easily conduct market analysis and prediction and supports appropriate investment decisions.

Means for Solving the Problems

[0005] This invention provides a system comprising means for collecting historical market data and means for analyzing historical market data using a generative AI model to predict future market price movements. Furthermore, it proposes a system that includes means for visually displaying the predicted future market price movements and means for issuing an alert when a large price movement is predicted. This allows investors to grasp market trends in real time and respond quickly to rapid fluctuations. In addition, by adding an automated trading function, trades based on predictions can be performed automatically, enabling optimal investment actions regardless of individual investment skills. Moreover, by updating the prediction data in real time, it becomes possible to make investment decisions that reflect the latest market conditions.

[0006] "Historical market data" refers to historical data such as trading prices, trading volume, and time periods in the market.

[0007] A "generative AI model" refers to an artificial intelligence algorithm or machine learning model used to analyze past market data and predict future market price movements.

[0008] "Analysis" refers to calculations and processing used to derive specific patterns or predictions based on collected data.

[0009] "Future market price movements" refers to fluctuations in market prices and trading volume from the present to the future.

[0010] "Means of visual display" refers to methods of providing users with predicted market price movements in visual formats such as graphs and charts.

[0011] "Means of issuing warnings" refers to means of alerting or warning users when predicted market fluctuations exceed a certain threshold.

[0012] "Methods for automated trading" refer to methods that automatically execute trades based on predicted future market price movements and according to predetermined conditions.

[0013] "Methods for updating in real time" refers to methods for acquiring the latest market data as it becomes available and immediately updating forecast data based on that data.

[0014] "Predictive data" refers to information about future market price movements derived from generative AI models. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention relates to a system that collects historical market data, analyzes it using a generated AI model, predicts future market price movements, displays them visually, and issues warnings as needed. This system consists of a server and user terminals.

[0037] Server-based processing

[0038] The server first collects historical market data from external market data providers. Generally, this data, including trading prices, volume, and time zones, is obtained via an API (Application Programming Interface). This data is provided in formats such as JSON and is often retrieved using the requests library.

[0039] Next, the server converts the acquired data into a pandas DataFrame and formats it. This formatted data is then input into a generative AI model to predict future price movements. The generative AI model uses advanced algorithms to predict future market trends by analyzing past patterns and trends. These prediction results are stored on the server as prediction data.

[0040] Processing by the user terminal

[0041] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is visually displayed in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[0042] Emergency alert issued

[0043] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. This alert will be displayed as a warning message on the screen, and notifications can also be made via sound and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[0044] Automated trading function

[0045] Furthermore, this system includes an automated trading function. Based on conditions pre-set by the user, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to make optimal trades without missing opportunities, maximizing their profits.

[0046] Specific example

[0047] For example, suppose the server collects JSON data in the following format:

[0048] json

[0049] [

[0050] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0051] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[0052] ...

[0053] ]

[0054] The server analyzes this data and can obtain predictive data from the generative AI model, such as:

[0055] json

[0056] [

[0057] {"time": "2023-10-01 11:00", "price": 110},

[0058] {"time": "2023-10-01 12:00", "price": 115},

[0059] ...

[0060] ]

[0061] The user terminal retrieves this predictive data and displays it visually as follows.

[0062] -------------

[0063] | Future Price Movement |

[0064] Time: 11:00, Price: 110

[0065] | Time: 12:00, Price: 115 |

[0066] -------------

[0067] If a significant price movement is predicted, an alert will be issued and users will be notified.

[0068] Emergency Alert: Large price movement expected!

[0069] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[0070] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[0071] The following describes the processing flow.

[0072] Step 1:

[0073] Data acquisition [server]

[0074] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[0075] python

[0076] response = requests.get("http: / / api.marketdata.com")

[0077] data = response.json()

[0078] Step 2:

[0079] Data formatting [server]

[0080] The acquired data is converted into a pandas DataFrame and formatted. This DataFrame is then modified as needed, including changing column names and data types, to make it suitable for analysis.

[0081] python

[0082] data_df = pd.DataFrame(data)

[0083] Step 3:

[0084] Initialization of the generative AI model [server]

[0085] The server initializes the AI ​​model. This model analyzes historical market data to predict future price movements.

[0086] python

[0087] model = PredictiveModel()

[0088] Step 4:

[0089] Data analysis [server]

[0090] The server inputs the formatted data into a generating AI model for analysis. This analysis predicts future market price movements.

[0091] python

[0092] prediction = model.predict(data_df)

[0093] Step 5:

[0094] Obtaining predictive data [Device]

[0095] The user's terminal sends a request to the server and retrieves the predicted data, which is the result of the analysis.

[0096] python

[0097] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[0098] Step 6:

[0099] Chart display [Terminal]

[0100] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[0101] python

[0102] plt.figure(figsize=(10, 5))

[0103] plt.plot(prediction_data['time'], prediction_data['price'])

[0104] plt.title("Future Price Movement")

[0105] plt.xlabel("Time")

[0106] plt.ylabel("Price")

[0107] plt.show()

[0108] Step 7:

[0109] Detection of large price movements [Terminal]

[0110] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[0111] python

[0112] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[0113] trigger_alert = True

[0114] else:

[0115] trigger_alert = False

[0116] Step 8:

[0117] Emergency alert issued [Terminal]

[0118] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[0119] python

[0120] if trigger_alert:

[0121] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[0122] Step 9:

[0123] Confirmation of automated trading settings [User]

[0124] The system checks if the user has enabled the automated trading function. If enabled, trades will be executed automatically when certain conditions are met.

[0125] python

[0126] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[0127] error_trade()

[0128] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, issues an alert if a large price movement is predicted, and performs automated trading as needed. Through this series of processes, users can grasp market conditions in real time and make quick and appropriate investment decisions.

[0129] (Example 1)

[0130] 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."

[0131] Systems that collect historical market data and use it to predict future market price movements are required to respond immediately to constantly fluctuating market conditions. However, existing systems often lack efficient coordination in the entire process from data collection to analysis and prediction, which can lead to delays, particularly in real-time updates of predicted values ​​and the issuance of emergency alerts. Furthermore, automated trading functions based on user-defined conditions are often insufficient, resulting in missed opportunities and the inability to execute optimal trades.

[0132] 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.

[0133] In this invention, the server includes means for collecting historical market data from an external market data provision service, means for formatting the collected market data and converting it into a data frame, means for inputting the formatted data into a generating AI model to predict future market price movements, means for storing and maintaining the predicted data on the server, means for transmitting the predicted data to a user terminal, means for visually displaying the predicted future market price movements, and means for issuing an alarm when a large price movement is predicted. This enables efficient collection and analysis of historical market data, real-time updates of predictions for future market price movements, and immediate alarms to users in the event of large price movements. Furthermore, an automated trading function based on the predicted data enables the rapid execution of optimal trades according to conditions set by the user.

[0134] "Market data" refers to data that includes information related to trading, such as trading prices, trading volume, and time of day in the market.

[0135] A "data provision service" refers to an external information source that provides market data through APIs or similar means.

[0136] "API" refers to an application programming interface for communicating with external services and databases.

[0137] A "data frame" is a two-dimensional data structure consisting of rows and columns, and is used for organizing and analyzing data.

[0138] A "generative AI model" is a model that uses artificial intelligence algorithms to predict future market price movements.

[0139] "Predictive data" refers to data about future market price movements predicted by generative AI models.

[0140] A "user terminal" is a computing device used by a user that receives and displays information transmitted from a server.

[0141] "Visually displaying" refers to presenting information in an easy-to-understand format, such as graphs or charts.

[0142] An "alert" refers to a notification or warning intended to draw attention in an emergency.

[0143] "Automated trading" is a function in which a system automatically executes trades based on conditions set by the user.

[0144] "Real-time" refers to data processing and updates occurring almost instantly.

[0145] "Conditions" refer to specific criteria or triggers set by the user, and actions such as automated trading are executed based on these.

[0146] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, and predicts future market price movements. This system consists of a server and user terminals.

[0147] The server collects historical market data from external market data providers. Typically, this involves using an API (Application Programming Interface) to send HTTP requests and retrieve data. For example, the requests library can be used to retrieve data. Market data includes information such as trading price, trading volume, and time zone. This data is usually provided in JSON format.

[0148] The server converts the collected market data into a pandas DataFrame and formats it. This formatting involves data processing such as deleting unnecessary columns and imputing missing values. The formatted data is then input into a generative AI model. This generative AI model is built using libraries such as TENSORFLOW® or PyTorch, and has a sophisticated algorithm that predicts future price movements by learning patterns and trends in past market data.

[0149] Predictive data is stored on a server. This can be stored using a database or file system. This predictive data is properly managed so that it can be accessed later by user terminals.

[0150] The user terminal retrieves the latest forecast data from the server. When the user starts the terminal, it sends a request to the server and receives the forecast data in real time. The received forecast data is displayed visually in a user-friendly format. For example, charts and graphs can be created using the matplotlib library to allow users to intuitively understand future market price movements.

[0151] Furthermore, if significant price movements are predicted based on forecast data, the user's terminal will issue an emergency alert. This alert will not only be displayed as a warning message on the screen, but can also be notified by voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[0152] Furthermore, it also features an automated trading function that analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[0153] Specific example

[0154] For example, suppose a server collects the following market data:

[0155] json

[0156] [

[0157] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0158] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103}

[0159] ]

[0160] The server analyzes this data and obtains the following predictive data from the generative AI model:

[0161] json

[0162] [

[0163] {"time": "2023-10-01 11:00", "price": 110},

[0164] {"time": "2023-10-01 12:00", "price": 115}

[0165] ]

[0166] The user terminal retrieves this predictive data and displays it visually in the following format:

[0167] -------------

[0168] | Future Price Movement |

[0169] Time: 11:00, Price: 110

[0170] | Time: 12:00, Price: 115 |

[0171] -------------

[0172] If a significant price movement is detected by the prediction, the user terminal will issue an alert:

[0173] Emergency Alert: Large price movement expected!

[0174] If the conditions are met, automated trading will be executed:

[0175] Executing buy at price 110

[0176] Executing sell at price 115

[0177] Example of a prompt

[0178] Collect market data for this week and use a generated AI model to predict market price movements for next week. Implement a feature to display the prediction results on a chart and issue alerts if significant price movements are predicted. Also, include a system that performs automated trading based on user-defined conditions.

[0179] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[0180] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0181] Step 1: Collect market data

[0182] The server collects historical market data from external market data providers. It uses the API endpoint URL and authentication information as input. The output is in JSON format and includes information such as trading price, trading volume, and time zone. The server retrieves this data using HTTP requests, for example, by using the requests library to collect the data.

[0183] Step 2: Data Formatting and Processing

[0184] The server formats the collected market data and converts it into a pandas DataFrame. It uses JSON-formatted market data as input and outputs a formatted DataFrame. Specific operations include deleting unnecessary columns and imputing missing values. For example, it creates a DataFrame using the pandas library and performs the necessary formatting.

[0185] Step 3: Prediction using a generative AI model

[0186] The server inputs formatted data into a generating AI model to predict future market price movements. It uses a formatted dataframe as input and outputs predicted future price data. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to input historical data into the model and calculate predictions.

[0187] Step 4: Save prediction data

[0188] The server stores the prediction data obtained from the generated AI model. It uses predicted price data as input and stores the output in a database or file system on the server. Specifically, it might save the data to a JSON file, for example, to allow users to access it later.

[0189] Step 5: Obtaining Analysis Results

[0190] The user terminal retrieves the latest prediction data from the server. It uses the server's endpoint URL as input and receives the prediction data in JSON format as output. Specifically, it sends an HTTP request to retrieve data from the server.

[0191] Step 6: Visual representation of data

[0192] The user terminal visually displays the received forecast data. It uses the acquired forecast data as input and displays it as output in chart or graph format. Specifically, it uses the matplotlib library to draw graphs, intuitively showing the user future price movements.

[0193] Step 7: Confirm and issue emergency alerts

[0194] The user terminal issues an emergency alert when a large price movement is expected based on the forecast data. It uses forecast data obtained from the server as input and outputs a warning message and voice notification. Specifically, it compares the forecast value with a certain threshold, displays an alert if the threshold is exceeded, and notifies the user using voice and vibration functions.

[0195] Step 8: Setting up and running automated trading

[0196] The server executes automated trades based on user-defined conditions. It uses user-defined conditions and predicted data as input, and outputs appropriate trade actions. Specifically, it evaluates predicted values ​​based on user conditions, and if the conditions are met, it calls the trading API to execute the trade.

[0197] In this way, the server and user terminal cooperate at each step to collect, analyze, display, issue alerts for, and automate market data, becoming a powerful tool for investors to make appropriate and timely investment decisions.

[0198] (Application Example 1)

[0199] 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."

[0200] Conventional market forecasting systems have low accuracy in predicting future market trends, making it difficult for users to make appropriate investment decisions based on them. Furthermore, they lack features such as alarm functions for large price movements and automated trading functions, often failing to function adequately in market environments where rapid response is required. The present invention aims to solve these problems and realize a system that provides more accurate and reliable market forecasting and responsive investment support.

[0201] 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.

[0202] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model to predict future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for executing automated trading based on user settings. As a result, users can grasp future market trends with high accuracy, respond immediately to large price movements, and trade at the optimal timing through automated trading.

[0203] "Historical market data" refers to information such as the trading price, trading volume, and time of day when actual transactions took place in the financial market in the past.

[0204] A "generative AI model" is a machine learning algorithm trained to identify patterns and trends from large amounts of data and predict future price movements.

[0205] "Future market price movements" refer to trends such as price fluctuations and trading volume fluctuations in future financial markets, as predicted using generative AI models.

[0206] "Visual display" means presenting predicted future market price movements in a format that users can intuitively understand, using display technologies such as graphs and charts.

[0207] "Issuing an alert" means using means such as voice, screen display, or vibration to warn the user when a significant fluctuation is predicted based on anticipated future market price movements.

[0208] "User settings" refer to the conditions and thresholds that users of the market application can individually set, and automated trading is executed based on these settings.

[0209] "Automated trading" refers to a function that automatically executes trades without manual intervention, based on predicted future market price movements and according to conditions pre-set by the user.

[0210] "Real-time updates" means that predicted future market price movements are instantly reflected in a short time whenever new data is acquired.

[0211] The system for implementing this invention consists of two main components: a server and a user terminal. The server collects historical market data from external market data provision services and analyzes it using a generative AI model. The user terminal receives predictive data provided by the server and displays it visually. It also issues an alert when a large price movement is predicted and executes automated trading based on user settings.

[0212] The server first collects market data via an API (Application Programming Interface) using the requests library. This data is provided in JSON format and converted to a DataFrame on the server side using the pandas library. After formatting into a DataFrame, it is input into a generative AI model to predict future market price movements. The generative AI model is trained using machine learning frameworks such as Keras and TensorFlow, and uses advanced algorithms to analyze past patterns and predict future market trends. These prediction results are stored on the server and provided upon request from the user's terminal.

[0213] The user terminal retrieves prediction data, which is the result of analysis, from the server in real time. The retrieved data is visually displayed as graphs and charts using libraries such as matplotlib. This display allows the user to intuitively grasp future market price movements. If a large price movement is predicted based on the prediction data, an alarm message will be displayed on the screen, and notifications can also be made by sound or vibration. This allows the user to take immediate action to respond to sudden market fluctuations.

[0214] Furthermore, this system includes an automated trading function. Based on conditions set by the user in advance, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to trade without missing the optimal trading timing, aiming to maximize profits.

[0215] For example, data collection and analysis can be performed using the following prompt statements:

[0216] "Collect historical market data from market data provision services and use a generated AI model to predict future market price movements."

[0217] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating market data.

[0218] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0219] Step 1:

[0220] The server collects historical market data from an external market data provider service. It retrieves data in JSON format using the requests library via an API (Application Programming Interface). The input is the URL of the API endpoint, and the output is market data in JSON format. In this step, the server performs the following specific actions:

[0221] Send a request to the API endpoint.

[0222] Market data is received as a response.

[0223] Save the received data in JSON format.

[0224] Step 2:

[0225] The server converts the acquired market data into a pandas dataframe and formats it. The input is market data in JSON format, and the output is a formatted dataframe. The specific data processing performed in this step is as follows:

[0226] Read JSON data and convert it to a pandas DataFrame.

[0227] Rename the columns in the dataframe as needed.

[0228] Format the time-series data to standardize the date and time format.

[0229] Step 3:

[0230] The server inputs the formatted dataframe into a generating AI model to predict future market price movements. The input is the processed dataframe, and the output is the predicted data. The data calculations performed in this step are as follows:

[0231] Extract features from a data frame.

[0232] The features are input into the generative AI model.

[0233] The generative AI model makes predictions and outputs them as predicted data.

[0234] Step 4:

[0235] The server holds the prediction data and provides it in response to requests from the user terminal. The input is the prediction data, and the output is the prediction data provided to the user terminal. In this step, the server performs the following actions:

[0236] Save the prediction data to the database.

[0237] It returns predictive data in response to requests from the user's terminal.

[0238] Step 5:

[0239] The user terminal retrieves predicted data, which is the analysis result, from the server and displays it visually. The input is predicted data from the server, and the output is information displayed visually in the form of graphs and charts. The specific actions performed in this step are as follows:

[0240] Send a request for prediction data to the server.

[0241] Analyze the prediction data received from the server.

[0242] Display the results as graphs or charts using the matplotlib library.

[0243] Step 6:

[0244] The user terminal issues an alert when a large price movement is predicted. The input is prediction data, and the output is an alert notification to the user. In this step, the user terminal performs the following specific actions:

[0245] Analyze the forecast data to see if significant price movements are predicted.

[0246] If a large price movement is predicted, an alert message will be displayed on the screen.

[0247] Notifications will be sent via voice or vibration as needed.

[0248] Step 7:

[0249] The user terminal executes automated trading based on user settings. Inputs include user settings and forecast data, while output is the actual execution of trades. The actions performed in this step are as follows:

[0250] Load user settings and check the trading conditions.

[0251] Analyze the predicted data and check if it meets the user-defined conditions.

[0252] If the conditions are met, the transaction will be executed automatically.

[0253] 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.

[0254] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, predicts future market price movements, displays them visually, and issues warnings as needed, further incorporating an emotion engine that recognizes user emotions. This system consists of a server, a user terminal, and an emotion engine.

[0255] Server-based processing

[0256] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, it uses the requests library to retrieve data. The retrieved data is converted into a pandas dataframe and formatted. This formatted data is input into a generative AI model, which analyzes the data and predicts future market price movements. The prediction results are stored on the server as prediction data.

[0257] Processing by the user terminal

[0258] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[0259] Emergency alert issued

[0260] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. The alert will not only be displayed as a warning message on the screen, but can also be notified via voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[0261] Automated trading function

[0262] This system also includes an automated trading function, which analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[0263] Introducing an emotional engine

[0264] A distinctive feature of this invention is the addition of an emotion engine. The emotion engine is an element for recognizing and analyzing the user's emotions and is built into the user terminal. The emotion engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc.

[0265] Processing by the emotion engine

[0266] The emotion engine embedded in the user's terminal analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging them to trade cautiously. It can also adjust investment strategies according to the user's emotional state. This allows users to make better investment decisions that take their own emotions into account.

[0267] Specific example

[0268] For example, suppose the server collects JSON data in the following format:

[0269] json

[0270] [

[0271] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0272] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[0273] ...

[0274] ]

[0275] The server can analyze this data and obtain prediction data from the generated AI model as follows:

[0276] json

[0277]

[0278] {"time": "2023-10-01 11:00", "price": 110},

[0279] {"time": "2023-10-01 12:00", "price": 115},

[0280] ...

[0281]

[0282] The user terminal retrieves this prediction data and visually displays it as follows.

[0283] -------------

[0284] | Future Price Movement |

[0285] | Time: 11:00, Price: 110 |

[0286] | Time: 12:00, Price: 115 |

[0287] -------------

[0288] If a large price movement is predicted, an alarm is issued and the user is notified.

[0289] Emergency Alert: Large price movement expected!

[0290] If the emotion engine detects the user's uneasiness, it can display the following additional message. ​​

[0291] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[0292] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[0293] Thus, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and emotion engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[0294] The following describes the processing flow.

[0295] Step 1:

[0296] Data acquisition [server]

[0297] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[0298] python

[0299] response = requests.get("http: / / api.marketdata.com")

[0300] data = response.json()

[0301] Step 2:

[0302] Data formatting [server]

[0303] The server converts the acquired data into a pandas DataFrame. This DataFrame is modified in terms of column names and data types as needed to make it suitable for analysis.

[0304] python

[0305] data_df = pd.DataFrame(data)

[0306] Step 3:

[0307] Initialization of the generative AI model [Server]

[0308] The server initializes the generative AI model. This model analyzes past market data to predict future value movements.

[0309] python

[0310] model = PredictiveModel()

[0311] Step 4:

[0312] Data analysis [Server]

[0313] The server inputs the formatted data into the generative AI model for analysis. This analysis predicts future market value movements and saves the results as prediction data.

[0314] python

[0315] prediction = model.predict(data_df)

[0316] Step 5:

[0317] Obtaining prediction data [Terminal]

[0318] The device sends a request to the server and retrieves prediction data, which is the result of the analysis. When the user starts up the device, it receives the latest prediction data from the server in real time.

[0319] python

[0320] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[0321] Step 6:

[0322] Chart display [Terminal]

[0323] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[0324] python

[0325] plt.figure(figsize=(10, 5))

[0326] plt.plot(prediction_data['time'], prediction_data['price'])

[0327] plt.title("Future Price Movement")

[0328] plt.xlabel("Time")

[0329] plt.ylabel("Price")

[0330] plt.show()

[0331] Step 7:

[0332] Detection of large price movements [Terminal]

[0333] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[0334] python

[0335] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[0336] trigger_alert = True

[0337] else:

[0338] trigger_alert = False

[0339] Step 8:

[0340] Emergency alert issued [Terminal]

[0341] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[0342] python

[0343] if trigger_alert:

[0344] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[0345] Step 9:

[0346] Confirmation of automated trading settings [User]

[0347] The system checks if the user has set up the automated trading function, and if the setting is enabled, it automatically executes trades when certain conditions are met.

[0348] python

[0349] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[0350] error_trade()

[0351] Step 10:

[0352] Emotion engine initialization [Terminal]

[0353] The device initializes the emotion engine and prepares to analyze the user's emotional state in real time. The emotion engine utilizes data from the camera, microphone, keyboard input, and other sources.

[0354] python

[0355] emotion_engine = EmotionEngine()

[0356] emotion_engine.initialize()

[0357] Step 11:

[0358] Sentiment analysis [terminal]

[0359] The device uses an emotion engine to analyze the user's emotions from their facial expressions, voice tone, and input patterns. Based on the analysis results, it adjusts notifications and alerts.

[0360] python

[0361] user_emotion = emotion_engine.analyze()

[0362] Step 12:

[0363] Emotion-based notification adjustments [device]

[0364] The system adjusts the intensity and content of notifications and alerts based on the user's emotional state. For example, if a user is feeling anxious, the system will provide more detailed information to increase their sense of security.

[0365] python

[0366] if user_emotion == "anxious":

[0367] display_message("We noticed you seem anxious. Would you like more detailed analysis before making a decision?")

[0368] Step 13:

[0369] Adjusting investment strategies based on emotions [Terminal]

[0370] Based on the analysis results of the emotion engine, investment strategies based on predictive data will be adjusted. If the emotional state is not calm, countermeasures such as recommending low-risk trades will be taken.

[0371] python

[0372] if user_emotion != "calm":

[0373] adjust_investment_strategy("low-risk")

[0374] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, and the emotion engine analyzes the user's emotions, providing appropriate notifications and adjusting investment strategies. This enables the user to grasp market conditions in real time and make quick and appropriate investment decisions.

[0375] (Example 2)

[0376] 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".

[0377] Traditional market forecasting systems analyze past market data and make future predictions, but this alone is insufficient to accurately support changes in user sentiment and rapid responses to emergencies. Furthermore, warnings to users may be delayed when significant market fluctuations are predicted, and automated trading functions and real-time information updates may not function effectively.

[0378] 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.

[0379] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model and predicting future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for analyzing the user's emotions using an emotion analysis engine and adjusting notifications and actions based on the results. This enables market forecasting that takes into account the user's emotional state and prompt alert issuance, as well as the provision of real-time updated market information and the effective operation of automated trading functions.

[0380] "Historical market data" refers to past trading information and price trends in financial markets, including stock prices, exchange rates, and commodity prices over a specific period.

[0381] A "generative AI model" refers to a computational model that uses artificial intelligence technology to learn from data and predict future price movements and patterns.

[0382] "Future market price movements" refer to price fluctuations and trends in future financial markets predicted based on current data.

[0383] "Visual display methods" refer to ways of displaying predicted market data in an easy-to-understand format for users, such as using graphs, charts, and dashboards.

[0384] "Means of issuing warnings" refers to methods of notifying or alerting users when significant market fluctuations are anticipated, and these include voice notifications, pop-up messages, and vibrations.

[0385] An "emotion analysis engine" refers to technology for detecting and analyzing a user's emotional state, and this includes systems that recognize emotions using data from cameras, microphones, keyboard input, and other sources.

[0386] "Means of adjusting notifications and actions" refers to methods of adjusting the information displayed and the content of warnings issued based on the user's emotional state obtained by the emotion analysis engine.

[0387] "Methods for automated trading" refers to systems that automatically execute trades based on predicted market data and according to pre-set conditions.

[0388] "Real-time updates" refers to methods of continuously acquiring the latest market data and forecast results and keeping them immediately accessible to users.

[0389] A "user terminal" refers to a device used by a user to view or manipulate information, and this includes personal computers, smartphones, tablets, and other similar devices.

[0390] This invention is a system that collects market data, analyzes it using a generative AI model, predicts future market price movements, visually displays the results, and issues warnings as needed. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, more advanced investment support becomes possible. This system consists of a server, a user terminal, and an emotion analysis engine.

[0391] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The data is retrieved using the requests library, converted into a pandas DataFrame, and formatted. The formatted data is then input into a generating AI model for analysis and prediction of future market price movements. These prediction results are stored on the server and provided to the user's terminal.

[0392] The user terminal retrieves forecast data from the server and displays it visually as charts and graphs using libraries such as matplotlib. This allows users to intuitively grasp future market price movements. Furthermore, if a large price movement is predicted based on the forecast data, the user terminal will issue an alert. The alert can be notified not only as a warning message on the screen, but also by sound and vibration. This allows users to respond immediately to sudden market fluctuations.

[0393] Furthermore, this system includes an automated trading function, which automatically executes trades when specific triggers occur based on conditions pre-set by the user. This function allows users to trade at the optimal time and maximize their profits.

[0394] A distinctive feature of this invention is the incorporation of an emotion analysis engine. The emotion analysis engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc. The emotion analysis engine, which is embedded in the user terminal, analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging the user to proceed with the transaction cautiously.

[0395] As a specific example, the data collected by the server is in the following format:

[0396] [

[0397] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0398] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[0399] ...

[0400] ]

[0401] The analyzed prediction data is expressed as follows:

[0402] [

[0403] {"time": "2023-10-01 11:00", "price": 110},

[0404] {"time": "2023-10-01 12:00", "price": 115},

[0405] ...

[0406] ]

[0407] The following is an example of how a user terminal can acquire and visually display this predictive data:

[0408] -------------

[0409] | Future Price Movement |

[0410] Time: 11:00, Price: 110

[0411] | Time: 12:00, Price: 115 |

[0412] -------------

[0413] The following warning will be displayed when a large price movement is expected:

[0414] Emergency Alert: Large price movement expected!

[0415] If the emotion analysis engine detects user anxiety, it will display a message like the following:

[0416] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[0417] Examples of prompt statements that can be used include the following:

[0418] "Provide a detailed prediction for the market prices based on the following past data: {past_data}. Consider factors such as {factors} and provide predictions for the next 24 hours."

[0419] As described above, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and sentiment analysis engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[0420] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0421] Step 1:

[0422] The server collects market data.

[0423] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The input is the API endpoint, and the output is the retrieved market data in JSON format. Specifically, the server uses the requests library to retrieve data from the API endpoint.

[0424] Step 2:

[0425] The server formats the data it has collected.

[0426] The acquired market data is converted into a pandas DataFrame and formatted. The input is the market data acquired in the previous step in JSON format, and the output is a formatted pandas DataFrame. Specifically, the server uses the pandas library to convert the JSON data into a DataFrame format.

[0427] Step 3:

[0428] The server analyzes the data and predicts future market price movements.

[0429] The system inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted pandas dataframe, and the output is data representing predicted market price movements. Specifically, the server uses a generative AI model in TensorFlow or PyTorch to perform data analysis and prediction.

[0430] Step 4:

[0431] The server stores the prediction data and provides it to the user's terminal.

[0432] The generated prediction data is stored on the server and provided as needed upon request from the user's terminal. The input is the prediction data, and the output is the stored data and the data provided to the user's terminal. Specifically, the server stores the data in the file system and provides the data to the user's terminal via an API.

[0433] Step 5:

[0434] The user's terminal acquires predictive data and displays it visually.

[0435] The user terminal sends a request to the server to retrieve prediction data. The retrieved data is then displayed in charts or graphs using visualization libraries such as matplotlib. The input is the prediction data retrieved from the server, and the output is the displayed chart or graph. Specifically, the user terminal sends an HTTP request, receives the data, and then generates the graph.

[0436] Step 6:

[0437] The user terminal will issue an alert if a large price movement is predicted.

[0438] The system analyzes forecast data and issues an alert if a large price movement is predicted. The input is forecast data, and the output is an alert message, voice notification, and vibration notification. Specifically, the user terminal calculates the maximum and minimum values ​​of the data, and displays and issues an alert if there is a large difference.

[0439] Step 7:

[0440] The user's terminal performs automated trading.

[0441] Buying and selling are performed automatically based on conditions set by the user. The inputs are the set conditions and predicted data, and the output is the result of the executed trades. Specifically, the user terminal checks the set values ​​and executes trades via the API if the conditions are met.

[0442] Step 8:

[0443] The emotion analysis engine analyzes the user's emotions and adjusts notifications and actions accordingly.

[0444] The system analyzes user emotions in real time using camera, microphone, and keyboard input, and adjusts notifications and alerts based on the results. The input is user emotion data, and the output is the adjusted notifications and actions. Specifically, the emotion analysis engine uses an emotion recognition algorithm to analyze the user's emotions and dynamically changes the system's response based on the results.

[0445] (Application Example 2)

[0446] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0447] There is a need to improve the accuracy of market price movement predictions and provide users with information to make more informed investment decisions. However, current systems have limitations in providing investment advice that takes emotions into account and in notifying users of sudden market changes in a timely manner. In particular, a lack of safe and efficient ways for users to obtain market information while in autonomous vehicles is a challenge.

[0448] 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.

[0449] In this invention, the server includes means for collecting historical data, means for analyzing historical data using a generative AI model to predict future price movements, and means for visually displaying the predicted future price movements. This enables means for issuing an alarm when a large price movement is predicted, and means for recognizing and analyzing user emotions to adjust notifications and alerts.

[0450] "Historical data" refers to various numerical data and information collected prior to the present. It is fundamental data for understanding market trends and predicting future developments.

[0451] A "generative AI model" refers to an artificial intelligence algorithm that learns patterns from large amounts of data to make new predictions and classifications. It is a machine learning model trained for a specific purpose.

[0452] "Future price movements" refers to predictions of fluctuations in the price or value of a market or a specific object at a future point in time.

[0453] "Visual display methods" refer to ways of making data and information visible in visual formats such as graphs and charts. These are display methods designed to make information easy for users to understand intuitively.

[0454] "Means of issuing warnings" refers to a system that notifies users of warnings when large price movements or anomalies are detected. These warnings are issued through methods such as sound, vibration, and screen displays.

[0455] "Means of recognizing and analyzing user emotions" refers to technologies that use devices such as cameras and microphones to detect emotions from a user's facial expressions and voice, and then analyze that information to understand the user's emotional state.

[0456] "Methods for automated trading" refer to systems that automatically execute buy and sell orders based on set conditions and predictive data. These functions aim to minimize user intervention and enable efficient trading.

[0457] "Real-time" means that data and information are processed and updated instantly. It refers to a state where the latest information is always provided without any time lag.

[0458] This invention relates to a system for predicting future market price movements in autonomous vehicles and providing investment support to users. This system consists of a server, a user terminal, and an emotion engine.

[0459] Server-based processing

[0460] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The retrieved data is converted into a pandas dataframe and formatted. The formatted data is input into a generative AI model, which performs data analysis and predicts future market price movements. The prediction results are stored on the server as prediction data.

[0461] Specifically, the server performs the following processes:

[0462] 1. Collect market data: Collect historical market data and convert it into a pandas dataframe.

[0463] 2. Data Analysis: The collected data is input into a generating AI model for analysis, and future market price movements are predicted.

[0464] 3. Saving prediction data: The analyzed prediction data is saved to the server.

[0465] Processing by the user terminal

[0466] The user terminal retrieves prediction data, which is the result of the analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs.

[0467] Specifically, the user terminal performs the following actions:

[0468] 1. Obtaining forecast data: Request and obtain the latest forecast data from the server.

[0469] 2. Visual display of data: The acquired data will be displayed to the user in the form of graphs and charts, allowing for intuitive understanding.

[0470] 3. Emotional Response: The emotion engine analyzes the user's emotions and, if they are feeling anxious, displays additional detailed information and advice.

[0471] Processing by the emotion engine

[0472] The emotion engine detects emotions from the user's facial expressions, voice tone, and input patterns through the camera, microphone, and keyboard input. If the user is feeling anxious, the system will provide more detailed information or display messages urging them to proceed cautiously. This allows users to make better investment decisions by taking their own emotions into consideration.

[0473] System Features

[0474] This system is particularly useful when users conduct investment activities within autonomous vehicles and offers the following advantages:

[0475] 1. Immediately notify users of sudden market fluctuations and prompt them to take action.

[0476] 2. Analyze the user's emotions and provide appropriate advice regarding anxiety and fear.

[0477] 3. Automated trading is executed based on predictive data to ensure optimal trading timing and avoid missing opportunities.

[0478] As a concrete example, imagine a scenario where, while traveling in an autonomous vehicle, a user can anticipate sudden market fluctuations based on predictive data and receive advice from an emotional engine to "avoid intuitive trading."

[0479] Examples of prompts to input into a generative AI model:

[0480] Based on historical market data, predict future market price movements. If the user is feeling anxious, display additional support messages. Make predictions based on the following data and output the results in JSON format.

[0481] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0482] Step 1:

[0483] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The input is the API endpoint URL, and the output is the retrieved raw data.

[0484] Step 2:

[0485] The server retrieves data and converts it into a pandas DataFrame, then formats it. The input is raw data, and the output is a formatted pandas DataFrame. The data converted into a DataFrame is in a format suitable for analysis.

[0486] Step 3:

[0487] The server inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted data frame, and the output is predicted data. The generative AI model analyzes future market trends based on the input data.

[0488] Step 4:

[0489] The server stores the prediction data. The input is the prediction data from the generative AI model, and the output is the stored prediction data. The stored prediction data is later retrieved from the user's terminal.

[0490] Step 5:

[0491] The user terminal sends a request to the server and receives the latest forecast data in real time. The input is the request to the server, and the output is the forecast data. The user terminal receives this data and uses it in the next step.

[0492] Step 6:

[0493] The system visually displays the forecast data received by the user's terminal in a user-friendly format as graphs and charts. The input is forecast data, and the output is the visually displayed data. This allows users to intuitively grasp future market trends.

[0494] Step 7:

[0495] The emotion engine analyzes the user's emotions using input from the camera and microphone. The input is the user's facial expressions and voice data, and the output is the analyzed emotion data. The emotion engine detects whether the user is feeling anxious.

[0496] Step 8:

[0497] The user's device adjusts notifications and alerts based on the analysis results of the emotion engine. The input is emotion data, and the output is adjusted notifications and alerts. If the user is feeling anxious, more detailed information and advice will be displayed.

[0498] Step 9:

[0499] The user terminal automatically executes trades based on predicted future price movements. Inputs consist of predicted data and pre-set trading conditions, while output is the executed trades. This allows the user to make optimal trades in response to market trends.

[0500] Step 10:

[0501] The user terminal continuously updates market price movements in real time, periodically sending requests to the server to receive new forecast data. The input is a request to the server, and the output is the latest forecast data. This allows users to always make investment decisions based on the most up-to-date information.

[0502] 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.

[0503] 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.

[0504] 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.

[0505] [Second Embodiment]

[0506] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0507] 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.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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).

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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".

[0518] This invention relates to a system that collects historical market data, analyzes it using a generated AI model, predicts future market price movements, displays them visually, and issues warnings as needed. This system consists of a server and user terminals.

[0519] Server-based processing

[0520] The server first collects historical market data from external market data providers. Generally, this data, including trading prices, volume, and time zones, is obtained via an API (Application Programming Interface). This data is provided in formats such as JSON and is often retrieved using the requests library.

[0521] Next, the server converts the acquired data into a pandas DataFrame and formats it. This formatted data is then input into a generative AI model to predict future price movements. The generative AI model uses advanced algorithms to predict future market trends by analyzing past patterns and trends. These prediction results are stored on the server as prediction data.

[0522] Processing by the user terminal

[0523] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is visually displayed in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[0524] Emergency alert issued

[0525] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. This alert will be displayed as a warning message on the screen, and notifications can also be made via sound and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[0526] Automated trading function

[0527] Furthermore, this system includes an automated trading function. Based on conditions pre-set by the user, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to make optimal trades without missing opportunities, maximizing their profits.

[0528] Specific example

[0529] For example, suppose the server collects JSON data in the following format:

[0530] json

[0531] [

[0532] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0533] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[0534] ...

[0535] ]

[0536] The server analyzes this data and can obtain predictive data from the generative AI model, such as:

[0537] json

[0538] [

[0539] {"time": "2023-10-01 11:00", "price": 110},

[0540] {"time": "2023-10-01 12:00", "price": 115},

[0541] ...

[0542] ]

[0543] The user terminal retrieves this predictive data and displays it visually as follows.

[0544] -------------

[0545] | Future Price Movement |

[0546] Time: 11:00, Price: 110

[0547] | Time: 12:00, Price: 115 |

[0548] -------------

[0549] If a significant price movement is predicted, an alert will be issued and users will be notified.

[0550] Emergency Alert: Large price movement expected!

[0551] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[0552] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[0553] The following describes the processing flow.

[0554] Step 1:

[0555] Data acquisition [server]

[0556] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[0557] Python

[0558] response = requests.get("http: / / api.marketdata.com")

[0559] data = response.json()

[0560] Step 2:

[0561] Data formatting [server]

[0562] The acquired data is converted into a pandas DataFrame and formatted. This DataFrame is then modified as needed, including changing column names and data types, to make it suitable for analysis.

[0563] Python

[0564] data_df = pd.DataFrame(data)

[0565] Step 3:

[0566] Initialization of the generative AI model [server]

[0567] The server initializes the AI ​​model. This model analyzes historical market data to predict future price movements.

[0568] Python

[0569] model = PredictiveModel()

[0570] Step 4:

[0571] Data analysis [server]

[0572] The server inputs the formatted data into a generating AI model for analysis. This analysis predicts future market price movements.

[0573] Python

[0574] prediction = model.predict(data_df)

[0575] Step 5:

[0576] Obtaining predictive data [Device]

[0577] The user's terminal sends a request to the server and retrieves the predicted data, which is the result of the analysis.

[0578] Python

[0579] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[0580] Step 6:

[0581] Chart display [Terminal]

[0582] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[0583] Python

[0584] plt.figure(figsize=(10, 5))

[0585] plt.plot(prediction_data['time'], prediction_data['price'])

[0586] plt.title("Future Price Movement")

[0587] plt.xlabel("Time")

[0588] plt.ylabel("Price")

[0589] plt.show()

[0590] Step 7:

[0591] Detection of large price movements [Terminal]

[0592] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[0593] Python

[0594] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[0595] trigger_alert = True

[0596] else:

[0597] trigger_alert = False

[0598] Step 8:

[0599] Emergency alert issued [Terminal]

[0600] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[0601] Python

[0602] if trigger_alert:

[0603] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[0604] Step 9:

[0605] Confirmation of automated trading settings [User]

[0606] The system checks if the user has enabled the automated trading function. If enabled, trades will be executed automatically when certain conditions are met.

[0607] Python

[0608] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[0609] error_trade()

[0610] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, issues an alert if a large price movement is predicted, and performs automated trading as needed. Through this series of processes, users can grasp market conditions in real time and make quick and appropriate investment decisions.

[0611] (Example 1)

[0612] 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."

[0613] Systems that collect historical market data and use it to predict future market price movements are required to respond immediately to constantly fluctuating market conditions. However, existing systems often lack efficient coordination in the entire process from data collection to analysis and prediction, which can lead to delays, particularly in real-time updates of predicted values ​​and the issuance of emergency alerts. Furthermore, automated trading functions based on user-defined conditions are often insufficient, resulting in missed opportunities and the inability to execute optimal trades.

[0614] 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.

[0615] In this invention, the server includes means for collecting historical market data from an external market data provision service, means for formatting the collected market data and converting it into a data frame, means for inputting the formatted data into a generating AI model to predict future market price movements, means for storing and maintaining the predicted data on the server, means for transmitting the predicted data to a user terminal, means for visually displaying the predicted future market price movements, and means for issuing an alarm when a large price movement is predicted. This enables efficient collection and analysis of historical market data, real-time updates of predictions for future market price movements, and immediate alarms to users in the event of large price movements. Furthermore, an automated trading function based on the predicted data enables the rapid execution of optimal trades according to conditions set by the user.

[0616] "Market data" refers to data that includes information related to trading, such as trading prices, trading volume, and time of day in the market.

[0617] A "data provision service" refers to an external information source that provides market data through APIs or similar means.

[0618] "API" refers to an application programming interface for communicating with external services and databases.

[0619] A "data frame" is a two-dimensional data structure consisting of rows and columns, and is used for organizing and analyzing data.

[0620] A "generative AI model" is a model that uses artificial intelligence algorithms to predict future market price movements.

[0621] "Predictive data" refers to data about future market price movements predicted by generative AI models.

[0622] A "user terminal" is a computing device used by a user that receives and displays information transmitted from a server.

[0623] "Visually displaying" refers to presenting information in an easy-to-understand format, such as graphs or charts.

[0624] An "alert" refers to a notification or warning intended to draw attention in an emergency.

[0625] "Automated trading" is a function in which a system automatically executes trades based on conditions set by the user.

[0626] "Real-time" refers to data processing and updates occurring almost instantly.

[0627] "Conditions" refer to specific criteria or triggers set by the user, and actions such as automated trading are executed based on these.

[0628] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, and predicts future market price movements. This system consists of a server and user terminals.

[0629] The server collects historical market data from external market data providers. Typically, this involves using an API (Application Programming Interface) to send HTTP requests and retrieve data. For example, the requests library can be used to retrieve data. Market data includes information such as trading price, trading volume, and time zone. This data is usually provided in JSON format.

[0630] The server converts the collected market data into a pandas DataFrame and formats it. This formatting involves data processing such as removing unnecessary columns and imputing missing values. The formatted data is then input into a generative AI model. This generative AI model is built using libraries such as TensorFlow or PyTorch, and has a sophisticated algorithm that predicts future price movements by learning patterns and trends from past market data.

[0631] Predictive data is stored on a server. This can be stored using a database or file system. This predictive data is properly managed so that it can be accessed later by user terminals.

[0632] The user terminal retrieves the latest forecast data from the server. When the user starts the terminal, it sends a request to the server and receives the forecast data in real time. The received forecast data is displayed visually in a user-friendly format. For example, charts and graphs can be created using the matplotlib library to allow users to intuitively understand future market price movements.

[0633] Furthermore, if significant price movements are predicted based on forecast data, the user's terminal will issue an emergency alert. This alert will not only be displayed as a warning message on the screen, but can also be notified by voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[0634] Furthermore, it also features an automated trading function that analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[0635] Specific example

[0636] For example, suppose a server collects the following market data:

[0637] json

[0638] [

[0639] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0640] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103}

[0641] ]

[0642] The server analyzes this data and obtains the following predictive data from the generative AI model:

[0643] json

[0644] [

[0645] {"time": "2023-10-01 11:00", "price": 110},

[0646] {"time": "2023-10-01 12:00", "price": 115}

[0647] ]

[0648] The user terminal retrieves this predictive data and displays it visually in the following format:

[0649] -------------

[0650] | Future Price Movement |

[0651] Time: 11:00, Price: 110

[0652] | Time: 12:00, Price: 115 |

[0653] -------------

[0654] If a significant price movement is detected by the prediction, the user terminal will issue an alert:

[0655] Emergency Alert: Large price movement expected!

[0656] If the conditions are met, automated trading will be executed:

[0657] Executing buy at price 110

[0658] Executing sell at price 115

[0659] Example of a prompt

[0660] Collect market data for this week and use a generative AI model to predict market price movements for next week. Display the prediction results on a chart and implement a feature to issue alerts if significant price movements are predicted. Also, include a system that performs automated trading based on user-defined conditions.

[0661] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[0662] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0663] Step 1: Collect market data

[0664] The server collects historical market data from external market data providers. It uses the API endpoint URL and authentication information as input. The output is in JSON format and includes information such as trading price, trading volume, and time zone. The server retrieves this data using HTTP requests, for example, by using the requests library to collect the data.

[0665] Step 2: Data Formatting and Processing

[0666] The server formats the collected market data and converts it into a pandas DataFrame. It uses JSON-formatted market data as input and outputs a formatted DataFrame. Specific operations include deleting unnecessary columns and imputing missing values. For example, it creates a DataFrame using the pandas library and performs the necessary formatting.

[0667] Step 3: Prediction using a generative AI model

[0668] The server inputs formatted data into a generating AI model to predict future market price movements. It uses a formatted dataframe as input and outputs predicted future price data. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to input historical data into the model and calculate predictions.

[0669] Step 4: Save prediction data

[0670] The server stores the prediction data obtained from the generated AI model. It uses predicted price data as input and stores the output in a database or file system on the server. Specifically, it might save the data to a JSON file, for example, to allow users to access it later.

[0671] Step 5: Obtaining Analysis Results

[0672] The user terminal retrieves the latest prediction data from the server. It uses the server's endpoint URL as input and receives the prediction data in JSON format as output. Specifically, it sends an HTTP request to retrieve data from the server.

[0673] Step 6: Visual representation of data

[0674] The user terminal visually displays the received forecast data. It uses the acquired forecast data as input and displays it as output in chart or graph format. Specifically, it uses the matplotlib library to draw graphs, intuitively showing the user future price movements.

[0675] Step 7: Confirm and issue emergency alerts

[0676] The user terminal issues an emergency alert when a large price movement is expected based on the forecast data. It uses forecast data obtained from the server as input and outputs a warning message and voice notification. Specifically, it compares the forecast value with a certain threshold, displays an alert if the threshold is exceeded, and notifies the user using voice and vibration functions.

[0677] Step 8: Setting up and running automated trading

[0678] The server executes automated trades based on user-defined conditions. It uses user-defined conditions and predicted data as input, and outputs appropriate trade actions. Specifically, it evaluates predicted values ​​based on user conditions, and if the conditions are met, it calls the trading API to execute the trade.

[0679] In this way, the server and user terminal cooperate at each step to collect, analyze, display, issue alerts for, and automate market data, becoming a powerful tool for investors to make appropriate and rapid investment decisions.

[0680] (Application Example 1)

[0681] 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."

[0682] Conventional market forecasting systems have low accuracy in predicting future market trends, making it difficult for users to make appropriate investment decisions based on them. Furthermore, they lack features such as alarm functions for large price movements and automated trading functions, often failing to function adequately in market environments where rapid response is required. The present invention aims to solve these problems and realize a system that provides more accurate and reliable market forecasting and responsive investment support.

[0683] 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.

[0684] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model to predict future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for executing automated trading based on user settings. As a result, users can grasp future market trends with high accuracy, respond immediately to large price movements, and trade at the optimal timing through automated trading.

[0685] "Historical market data" refers to information such as the trading price, trading volume, and time of day when actual transactions took place in the financial market in the past.

[0686] A "generative AI model" is a machine learning algorithm trained to identify patterns and trends from large amounts of data and predict future price movements.

[0687] "Future market price movements" refer to trends such as price fluctuations and trading volume fluctuations in future financial markets, as predicted using generative AI models.

[0688] "Visual display" means presenting predicted future market price movements in a format that users can intuitively understand, using display technologies such as graphs and charts.

[0689] "Issuing an alert" means using means such as voice, screen display, or vibration to warn the user when a significant fluctuation is predicted based on anticipated future market price movements.

[0690] "User settings" refer to the conditions and thresholds that users of the market application can individually set, and automated trading is executed based on these settings.

[0691] "Automated trading" refers to a function that automatically executes trades without manual intervention, based on predicted future market price movements and according to conditions pre-set by the user.

[0692] "Real-time updates" means that predicted future market price movements are instantly reflected in a short time whenever new data is acquired.

[0693] The system for implementing this invention consists of two main components: a server and a user terminal. The server collects historical market data from external market data provision services and analyzes it using a generative AI model. The user terminal receives predictive data provided by the server and displays it visually. It also issues an alert when a large price movement is predicted and executes automated trading based on user settings.

[0694] The server first collects market data via an API (Application Programming Interface) using the requests library. This data is provided in JSON format and converted to a DataFrame on the server side using the pandas library. After formatting into a DataFrame, it is input into a generative AI model to predict future market price movements. The generative AI model is trained using machine learning frameworks such as Keras and TensorFlow, and uses advanced algorithms to analyze past patterns and predict future market trends. These prediction results are stored on the server and provided upon request from the user's terminal.

[0695] The user terminal retrieves prediction data, which is the result of analysis, from the server in real time. The retrieved data is visually displayed as graphs and charts using libraries such as matplotlib. This display allows the user to intuitively grasp future market price movements. If a large price movement is predicted based on the prediction data, an alarm message will be displayed on the screen, and notifications can also be made by sound or vibration. This allows the user to take immediate action to respond to sudden market fluctuations.

[0696] Furthermore, this system includes an automated trading function. Based on conditions set by the user in advance, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to trade without missing the optimal trading timing, aiming to maximize profits.

[0697] For example, data collection and analysis can be performed using the following prompt statements:

[0698] "Collect historical market data from market data provision services and use a generated AI model to predict future market price movements."

[0699] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[0700] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0701] Step 1:

[0702] The server collects historical market data from an external market data provider service. It retrieves data in JSON format using the requests library via an API (Application Programming Interface). The input is the URL of the API endpoint, and the output is market data in JSON format. In this step, the server performs the following specific actions:

[0703] Send a request to the API endpoint.

[0704] Market data is received as a response.

[0705] Save the received data in JSON format.

[0706] Step 2:

[0707] The server converts the acquired market data into a pandas dataframe and formats it. The input is market data in JSON format, and the output is a formatted dataframe. The specific data processing performed in this step is as follows:

[0708] Read JSON data and convert it to a pandas DataFrame.

[0709] Rename the columns in the dataframe as needed.

[0710] Format the time-series data to standardize the date and time format.

[0711] Step 3:

[0712] The server inputs the formatted data frame into a generating AI model to predict future market price movements. The input is the processed data frame, and the output is the predicted data. The data calculations performed in this step are as follows:

[0713] Extract features from a data frame.

[0714] The features are input into the generative AI model.

[0715] The generative AI model makes predictions and outputs them as predicted data.

[0716] Step 4:

[0717] The server holds the prediction data and provides it upon request from the user terminal. The input is the prediction data, and the output is the prediction data provided to the user terminal. In this step, the server performs the following actions:

[0718] Save the prediction data to the database.

[0719] It returns predictive data in response to requests from the user's terminal.

[0720] Step 5:

[0721] The user terminal retrieves predicted data, which is the analysis result, from the server and displays it visually. The input is predicted data from the server, and the output is information displayed visually in the form of graphs and charts. The specific actions performed in this step are as follows:

[0722] Send a request for prediction data to the server.

[0723] Analyze the prediction data received from the server.

[0724] Display the results as graphs or charts using the matplotlib library.

[0725] Step 6:

[0726] The user terminal issues an alert when a large price movement is predicted. The input is prediction data, and the output is an alert notification to the user. In this step, the user terminal performs the following specific actions:

[0727] Analyze the forecast data to see if significant price movements are predicted.

[0728] If a large price movement is predicted, an alert message will be displayed on the screen.

[0729] Notifications will be sent via voice or vibration as needed.

[0730] Step 7:

[0731] The user terminal executes automated trading based on user settings. Inputs include user settings and forecast data, while output is the actual execution of trades. The actions performed in this step are as follows:

[0732] Load user settings and check the trading conditions.

[0733] Analyze the prediction data and check if it meets the user-defined conditions.

[0734] If the conditions are met, the transaction will be executed automatically.

[0735] 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.

[0736] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, predicts future market price movements, displays them visually, and issues warnings as needed, further incorporating an emotion engine that recognizes user emotions. This system consists of a server, a user terminal, and an emotion engine.

[0737] Server-based processing

[0738] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, it uses the requests library to retrieve data. The retrieved data is converted into a pandas dataframe and formatted. This formatted data is input into a generative AI model, which analyzes the data and predicts future market price movements. The prediction results are stored on the server as prediction data.

[0739] Processing by the user terminal

[0740] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[0741] Emergency alert issued

[0742] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. The alert will not only be displayed as a warning message on the screen, but can also be notified via voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[0743] Automated trading function

[0744] This system also includes an automated trading function, which analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[0745] Introducing an emotional engine

[0746] A distinctive feature of this invention is the addition of an emotion engine. The emotion engine is an element for recognizing and analyzing the user's emotions and is built into the user terminal. The emotion engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc.

[0747] Processing by the emotion engine

[0748] The emotion engine embedded in the user's terminal analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging them to trade cautiously. It can also adjust investment strategies according to the user's emotional state. This allows users to make better investment decisions that take their own emotions into account.

[0749] Specific example

[0750] For example, suppose the server collects JSON data in the following format:

[0751] json

[0752] [

[0753] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0754] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[0755] ...

[0756] ]

[0757] The server analyzes this data and can obtain predictive data from the generative AI model, such as:

[0758] json

[0759] [

[0760] {"time": "2023-10-01 11:00", "price": 110},

[0761] {"time": "2023-10-01 12:00", "price": 115},

[0762] ...

[0763] ]

[0764] The user terminal retrieves this predictive data and displays it visually as follows.

[0765] -------------

[0766] | Future Price Movement |

[0767] Time: 11:00, Price: 110

[0768] | Time: 12:00, Price: 115 |

[0769] -------------

[0770] If a significant price movement is predicted, an alert will be issued and users will be notified.

[0771] Emergency Alert: Large price movement expected!

[0772] If the emotion engine detects user anxiety, it can display additional messages such as the following:

[0773] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[0774] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[0775] Thus, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and emotion engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[0776] The following describes the processing flow.

[0777] Step 1:

[0778] Data acquisition [server]

[0779] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[0780] Python

[0781] response = requests.get("http: / / api.marketdata.com")

[0782] data = response.json()

[0783] Step 2:

[0784] Data formatting [server]

[0785] The server converts the retrieved data into a pandas DataFrame. This DataFrame is then modified as needed, with column names and data types adjusted to make it suitable for analysis.

[0786] Python

[0787] data_df = pd.DataFrame(data)

[0788] Step 3:

[0789] Initialization of the generative AI model [server]

[0790] The server initializes the AI ​​model. This model analyzes historical market data to predict future price movements.

[0791] Python

[0792] model = PredictiveModel()

[0793] Step 4:

[0794] Data analysis [server]

[0795] The server inputs the formatted data into an AI model for analysis. This analysis predicts future market price movements, and the results are saved as predictive data.

[0796] Python

[0797] prediction = model.predict(data_df)

[0798] Step 5:

[0799] Obtaining predictive data [Device]

[0800] The device sends a request to the server to obtain prediction data, which is the result of the analysis. When the user starts up the device, it receives the latest prediction data from the server in real time.

[0801] Python

[0802] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[0803] Step 6:

[0804] Chart display [Terminal]

[0805] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[0806] Python

[0807] plt.figure(figsize=(10, 5))

[0808] plt.plot(prediction_data['time'], prediction_data['price'])

[0809] plt.title("Future Price Movement")

[0810] plt.xlabel("Time")

[0811] plt.ylabel("Price")

[0812] plt.show()

[0813] Step 7:

[0814] Detection of large price movements [Terminal]

[0815] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[0816] Python

[0817] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[0818] trigger_alert = True

[0819] else:

[0820] trigger_alert = False

[0821] Step 8:

[0822] Emergency alert issued [Terminal]

[0823] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[0824] Python

[0825] if trigger_alert:

[0826] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[0827] Step 9:

[0828] Confirmation of automated trading settings [User]

[0829] The system checks if the user has set up the automated trading function, and if the setting is enabled, it automatically executes trades when certain conditions are met.

[0830] Python

[0831] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[0832] error_trade()

[0833] Step 10:

[0834] Emotion engine initialization [Terminal]

[0835] The device initializes the emotion engine and prepares to analyze the user's emotional state in real time. The emotion engine utilizes data from the camera, microphone, keyboard input, and other sources.

[0836] Python

[0837] emotion_engine = EmotionEngine()

[0838] emotion_engine.initialize()

[0839] Step 11:

[0840] Emotion analysis [terminal]

[0841] The device uses an emotion engine to analyze the user's emotions from their facial expressions, voice tone, and input patterns. Based on the analysis results, it adjusts notifications and alerts.

[0842] Python

[0843] user_emotion = emotion_engine.analyze()

[0844] Step 12:

[0845] Emotion-based notification adjustments [device]

[0846] The system adjusts the intensity and content of notifications and alerts based on the user's emotional state. For example, if a user is feeling anxious, the system will provide more detailed information to increase their sense of security.

[0847] Python

[0848] if user_emotion == "anxious":

[0849] display_message("We noticed you seem anxious. Would you like more detailed analysis before making a decision?")

[0850] Step 13:

[0851] Adjusting investment strategies based on emotions [Terminal]

[0852] Based on the analysis results of the emotion engine, investment strategies based on predictive data will be adjusted. If the emotional state is not calm, countermeasures will be taken, such as recommending low-risk trades.

[0853] Python

[0854] if user_emotion != "calm":

[0855] adjust_investment_strategy("low-risk")

[0856] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, and the emotion engine analyzes the user's emotions, providing appropriate notifications and adjusting investment strategies. This enables the user to grasp market conditions in real time and make quick and appropriate investment decisions.

[0857] (Example 2)

[0858] 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".

[0859] Traditional market forecasting systems analyze past market data and make future predictions, but this alone is insufficient to accurately support changes in user sentiment and rapid responses to emergencies. Furthermore, warnings to users may be delayed when significant market fluctuations are predicted, and automated trading functions and real-time information updates may not function effectively.

[0860] 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.

[0861] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model and predicting future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for analyzing the user's emotions using an emotion analysis engine and adjusting notifications and actions based on the results. This enables market forecasting that takes into account the user's emotional state and prompt alert issuance, as well as the provision of real-time updated market information and the effective operation of automated trading functions.

[0862] "Historical market data" refers to past trading information and price trends in financial markets, including stock prices, exchange rates, and commodity prices over a specific period.

[0863] A "generative AI model" refers to a computational model that uses artificial intelligence technology to learn from data and predict future price movements and patterns.

[0864] "Future market price movements" refer to price fluctuations and trends in future financial markets predicted based on current data.

[0865] "Visual display methods" refer to ways of displaying predicted market data in an easy-to-understand format for users, such as using graphs, charts, and dashboards.

[0866] "Means of issuing warnings" refers to methods of notifying or alerting users when significant market fluctuations are anticipated, and includes voice notifications, pop-up messages, and vibrations.

[0867] An "emotion analysis engine" refers to technology for detecting and analyzing a user's emotional state, and this includes systems that recognize emotions using data from cameras, microphones, keyboard input, and other sources.

[0868] "Means of adjusting notifications and actions" refers to methods of adjusting the information displayed and the content of warnings issued based on the user's emotional state obtained by the emotion analysis engine.

[0869] "Methods for automated trading" refers to systems that automatically execute trades based on predicted market data and according to pre-set conditions.

[0870] "Real-time updates" refers to methods of continuously acquiring the latest market data and forecast results and keeping them immediately accessible to users.

[0871] A "user terminal" refers to a device used by a user to view or manipulate information, and this includes personal computers, smartphones, tablets, and other similar devices.

[0872] This invention is a system that collects market data, analyzes it using a generative AI model, predicts future market price movements, visually displays the results, and issues warnings as needed. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, more advanced investment support becomes possible. This system consists of a server, a user terminal, and an emotion analysis engine.

[0873] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The data is retrieved using the requests library, converted into a pandas DataFrame, and formatted. The formatted data is then input into a generating AI model for analysis and prediction of future market price movements. These prediction results are stored on the server and provided to the user's terminal.

[0874] The user terminal retrieves forecast data from the server and displays it visually as charts and graphs using libraries such as matplotlib. This allows users to intuitively grasp future market price movements. Furthermore, if a large price movement is predicted based on the forecast data, the user terminal will issue an alert. The alert can be notified not only as a warning message on the screen, but also by sound and vibration. This allows users to respond immediately to sudden market fluctuations.

[0875] Furthermore, this system includes an automated trading function, which automatically executes trades when specific triggers occur based on conditions pre-set by the user. This function allows users to trade at the optimal time and maximize their profits.

[0876] A distinctive feature of this invention is the incorporation of an emotion analysis engine. The emotion analysis engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc. The emotion analysis engine, which is embedded in the user terminal, analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging the user to proceed with the transaction cautiously.

[0877] As a specific example, the data collected by the server is in the following format:

[0878] [

[0879] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[0880] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[0881] ...

[0882] ]

[0883] The analyzed prediction data is expressed as follows:

[0884] [

[0885] {"time": "2023-10-01 11:00", "price": 110},

[0886] {"time": "2023-10-01 12:00", "price": 115},

[0887] ...

[0888] ]

[0889] The following is an example of how a user terminal retrieves and visually displays this predictive data:

[0890] -------------

[0891] | Future Price Movement |

[0892] Time: 11:00, Price: 110

[0893] | Time: 12:00, Price: 115 |

[0894] -------------

[0895] The following warning will be displayed when a large price movement is expected:

[0896] Emergency Alert: Large price movement expected!

[0897] If the emotion analysis engine detects user anxiety, it will display a message like the following:

[0898] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[0899] Examples of prompt statements that can be used include the following:

[0900] "Provide a detailed prediction for the market prices based on the following past data: {past_data}. Consider factors such as {factors} and provide predictions for the next 24 hours."

[0901] As described above, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and sentiment analysis engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[0902] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0903] Step 1:

[0904] The server collects market data.

[0905] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The input is the API endpoint, and the output is the retrieved market data in JSON format. Specifically, the server uses the requests library to retrieve data from the API endpoint.

[0906] Step 2:

[0907] The server formats the data it has collected.

[0908] The acquired market data is converted into a pandas DataFrame and formatted. The input is the market data acquired in the previous step in JSON format, and the output is a formatted pandas DataFrame. Specifically, the server uses the pandas library to convert the JSON data into a DataFrame format.

[0909] Step 3:

[0910] The server analyzes the data and predicts future market price movements.

[0911] The system inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted pandas dataframe, and the output is data representing predicted market price movements. Specifically, the server uses a generative AI model in TensorFlow or PyTorch to perform data analysis and prediction.

[0912] Step 4:

[0913] The server stores the prediction data and provides it to the user's terminal.

[0914] The generated prediction data is stored on the server and provided as needed upon request from the user's terminal. The input is the prediction data, and the output is the stored data and the data provided to the user's terminal. Specifically, the server stores the data in the file system and provides the data to the user's terminal via an API.

[0915] Step 5:

[0916] The user's terminal acquires predictive data and displays it visually.

[0917] The user terminal sends a request to the server to retrieve prediction data. The retrieved data is then displayed in charts or graphs using visualization libraries such as matplotlib. The input is the prediction data retrieved from the server, and the output is the displayed chart or graph. Specifically, the user terminal sends an HTTP request, receives the data, and then generates the graph.

[0918] Step 6:

[0919] The user terminal will issue an alert if a large price movement is predicted.

[0920] The system analyzes forecast data and issues an alert if a large price movement is predicted. The input is forecast data, and the output is an alert message, voice notification, and vibration notification. Specifically, the user terminal calculates the maximum and minimum values ​​of the data, and displays and issues an alert if there is a large difference.

[0921] Step 7:

[0922] The user's terminal performs automated trading.

[0923] Buying and selling are performed automatically based on conditions set by the user. The inputs are the set conditions and predicted data, and the output is the result of the executed trades. Specifically, the user terminal checks the set values ​​and executes trades via the API if the conditions are met.

[0924] Step 8:

[0925] The emotion analysis engine analyzes the user's emotions and adjusts notifications and actions accordingly.

[0926] The system analyzes user emotions in real time using camera, microphone, and keyboard input, and adjusts notifications and alerts based on the results. The input is user emotion data, and the output is the adjusted notifications and actions. Specifically, the emotion analysis engine uses an emotion recognition algorithm to analyze the user's emotions and dynamically changes the system's response based on the results.

[0927] (Application Example 2)

[0928] 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."

[0929] There is a need to improve the accuracy of market price movement predictions and provide users with information to make more informed investment decisions. However, current systems have limitations in providing investment advice that takes emotions into account and in notifying users of sudden market changes in a timely manner. In particular, a lack of safe and efficient ways for users to obtain market information while in autonomous vehicles is a challenge.

[0930] 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.

[0931] In this invention, the server includes means for collecting historical data, means for analyzing historical data using a generative AI model to predict future price movements, and means for visually displaying the predicted future price movements. This enables means for issuing an alarm when a large price movement is predicted, and means for recognizing and analyzing user emotions to adjust notifications and alerts.

[0932] "Historical data" refers to various numerical data and information collected prior to the present. It is fundamental data for understanding market trends and predicting future developments.

[0933] A "generative AI model" refers to an artificial intelligence algorithm that learns patterns from large amounts of data to make new predictions and classifications. It is a machine learning model trained for a specific purpose.

[0934] "Future price movements" refers to predictions of fluctuations in the price or value of a market or a specific object at a future point in time.

[0935] "Visual display methods" refer to ways of making data and information visible in visual formats such as graphs and charts. These are display methods designed to make information easy for users to understand intuitively.

[0936] "Means of issuing warnings" refers to a system for notifying users of warnings when large price movements or anomalies are detected. These warnings are issued through methods such as voice, vibration, and screen displays.

[0937] "Means of recognizing and analyzing user emotions" refers to technologies that use devices such as cameras and microphones to detect emotions from a user's facial expressions and voice, and then analyze that information to understand the user's emotional state.

[0938] "Methods for automated trading" refer to systems that automatically execute buy and sell orders based on set conditions and predictive data. These functions aim to minimize user intervention and enable efficient trading.

[0939] "Real-time" means that data and information are processed and updated instantly. It refers to a state where the latest information is always provided without any time lag.

[0940] This invention relates to a system for predicting future market price movements in autonomous vehicles and providing investment support to users. This system consists of a server, a user terminal, and an emotion engine.

[0941] Server-based processing

[0942] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The retrieved data is converted into a pandas dataframe and formatted. The formatted data is input into a generative AI model, which performs data analysis and predicts future market price movements. The prediction results are stored on the server as prediction data.

[0943] Specifically, the server performs the following processes:

[0944] 1. Collect market data: Collect historical market data and convert it into a pandas dataframe.

[0945] 2. Data Analysis: The collected data is input into a generating AI model for analysis, and future market price movements are predicted.

[0946] 3. Saving prediction data: The analyzed prediction data is saved to the server.

[0947] Processing by the user terminal

[0948] The user terminal retrieves prediction data, which is the result of the analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs.

[0949] Specifically, the user terminal performs the following actions:

[0950] 1. Obtaining forecast data: Request and obtain the latest forecast data from the server.

[0951] 2. Visual display of data: The acquired data will be displayed to the user in the form of graphs and charts, allowing for intuitive understanding.

[0952] 3. Emotional Response: The emotion engine analyzes the user's emotions and, if they are feeling anxious, displays additional detailed information and advice.

[0953] Processing by the emotion engine

[0954] The emotion engine detects emotions from the user's facial expressions, voice tone, and input patterns through the camera, microphone, and keyboard input. If the user is feeling anxious, the system will provide more detailed information or display messages urging them to proceed cautiously. This allows users to make better investment decisions by taking their own emotions into consideration.

[0955] System Features

[0956] This system is particularly useful when users conduct investment activities within autonomous vehicles and offers the following advantages:

[0957] 1. Immediately notify users of sudden market fluctuations and prompt them to take action.

[0958] 2. Analyze the user's emotions and provide appropriate advice regarding anxiety and fear.

[0959] 3. Automated trading is executed based on predictive data to ensure optimal trading timing and avoid missing opportunities.

[0960] As a concrete example, imagine a scenario where, while traveling in an autonomous vehicle, a user can anticipate sudden market fluctuations based on predictive data and receive advice from an emotional engine to "avoid intuitive trading."

[0961] Examples of prompts to input into a generative AI model:

[0962] Based on historical market data, predict future market price movements. If the user expresses concerns, display additional support messages. Make predictions based on the following data and output the results in JSON format.

[0963] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0964] Step 1:

[0965] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The input is the API endpoint URL, and the output is the retrieved raw data.

[0966] Step 2:

[0967] The server retrieves data and converts it into a pandas DataFrame, then formats it. The input is raw data, and the output is a formatted pandas DataFrame. The data converted into a DataFrame is in a format suitable for analysis.

[0968] Step 3:

[0969] The server inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted data frame, and the output is predicted data. The generative AI model analyzes future market trends based on the input data.

[0970] Step 4:

[0971] The server stores the prediction data. The input is the prediction data from the generative AI model, and the output is the stored prediction data. The stored prediction data is later retrieved from the user's terminal.

[0972] Step 5:

[0973] The user terminal sends a request to the server and receives the latest forecast data in real time. The input is the request to the server, and the output is the forecast data. The user terminal receives this data and uses it in the next step.

[0974] Step 6:

[0975] The system visually displays the forecast data received by the user's terminal in a user-friendly format as graphs and charts. The input is forecast data, and the output is the visually displayed data. This allows users to intuitively grasp future market trends.

[0976] Step 7:

[0977] The emotion engine analyzes the user's emotions using input from the camera and microphone. The input is the user's facial expressions and voice data, and the output is the analyzed emotion data. The emotion engine detects whether the user is feeling anxious.

[0978] Step 8:

[0979] The user's device adjusts notifications and alerts based on the analysis results of the emotion engine. The input is emotion data, and the output is adjusted notifications and alerts. If the user is feeling anxious, more detailed information and advice will be displayed.

[0980] Step 9:

[0981] The user terminal automatically executes trades based on predicted future price movements. Inputs are predicted data and pre-set trading conditions, while output is the executed trades. This allows the user to make optimal trades in response to market trends.

[0982] Step 10:

[0983] The user terminal continuously updates market price movements in real time, periodically sending requests to the server to receive new forecast data. The input is a request to the server, and the output is the latest forecast data. This allows users to always make investment decisions based on the most up-to-date information.

[0984] 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.

[0985] 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.

[0986] 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.

[0987] [Third Embodiment]

[0988] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0989] 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.

[0990] 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).

[0991] 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.

[0992] 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.

[0993] 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).

[0994] 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.

[0995] 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.

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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".

[1000] This invention relates to a system that collects historical market data, analyzes it using a generated AI model, predicts future market price movements, displays them visually, and issues warnings as needed. This system consists of a server and user terminals.

[1001] Server-based processing

[1002] The server first collects historical market data from external market data providers. Generally, this data, including trading prices, volume, and time zones, is obtained via an API (Application Programming Interface). This data is provided in formats such as JSON and is often retrieved using the requests library.

[1003] Next, the server converts the acquired data into a pandas DataFrame and formats it. This formatted data is then input into a generative AI model to predict future price movements. The generative AI model uses advanced algorithms to predict future market trends by analyzing past patterns and trends. These prediction results are stored on the server as prediction data.

[1004] Processing by the user terminal

[1005] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is visually displayed in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[1006] Emergency alert issued

[1007] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. This alert will be displayed as a warning message on the screen, and notifications can also be made via sound and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[1008] Automated trading function

[1009] Furthermore, this system includes an automated trading function. Based on conditions pre-set by the user, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to make optimal trades without missing opportunities, maximizing their profits.

[1010] Specific example

[1011] For example, suppose the server collects JSON data in the following format:

[1012] json

[1013] [

[1014] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1015] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[1016] ...

[1017] ]

[1018] The server analyzes this data and can obtain predictive data from the generative AI model, such as:

[1019] json

[1020] [

[1021] {"time": "2023-10-01 11:00", "price": 110},

[1022] {"time": "2023-10-01 12:00", "price": 115},

[1023] ...

[1024] ]

[1025] The user terminal retrieves this predictive data and displays it visually as follows.

[1026] -------------

[1027] | Future Price Movement |

[1028] Time: 11:00, Price: 110

[1029] | Time: 12:00, Price: 115 |

[1030] -------------

[1031] If a significant price movement is predicted, an alert will be issued and users will be notified.

[1032] Emergency Alert: Large price movement expected!

[1033] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[1034] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[1035] The following describes the processing flow.

[1036] Step 1:

[1037] Data acquisition [server]

[1038] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[1039] Python

[1040] response = requests.get("http: / / api.marketdata.com")

[1041] data = response.json()

[1042] Step 2:

[1043] Data formatting [server]

[1044] The acquired data is converted into a pandas DataFrame and formatted. This DataFrame is then modified as needed, including changing column names and data types, to make it suitable for analysis.

[1045] Python

[1046] data_df = pd.DataFrame(data)

[1047] Step 3:

[1048] Initialization of the generative AI model [server]

[1049] The server initializes the AI ​​model. This model analyzes historical market data to predict future price movements.

[1050] Python

[1051] model = PredictiveModel()

[1052] Step 4:

[1053] Data analysis [server]

[1054] The server inputs the formatted data into a generating AI model for analysis. This analysis predicts future market price movements.

[1055] Python

[1056] prediction = model.predict(data_df)

[1057] Step 5:

[1058] Obtaining predictive data [Device]

[1059] The user's terminal sends a request to the server and retrieves the predicted data, which is the result of the analysis.

[1060] Python

[1061] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[1062] Step 6:

[1063] Chart display [Terminal]

[1064] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[1065] Python

[1066] plt.figure(figsize=(10, 5))

[1067] plt.plot(prediction_data['time'], prediction_data['price'])

[1068] plt.title("Future Price Movement")

[1069] plt.xlabel("Time")

[1070] plt.ylabel("Price")

[1071] plt.show()

[1072] Step 7:

[1073] Detection of large price movements [Terminal]

[1074] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[1075] Python

[1076] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[1077] trigger_alert = True

[1078] else:

[1079] trigger_alert = False

[1080] Step 8:

[1081] Emergency alert issued [Terminal]

[1082] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[1083] Python

[1084] if trigger_alert:

[1085] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[1086] Step 9:

[1087] Confirmation of automated trading settings [User]

[1088] The system checks if the user has enabled the automated trading function. If enabled, trades will be executed automatically when certain conditions are met.

[1089] Python

[1090] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[1091] error_trade()

[1092] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, issues an alert if a large price movement is predicted, and performs automated trading as needed. Through this series of processes, users can grasp market conditions in real time and make quick and appropriate investment decisions.

[1093] (Example 1)

[1094] 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."

[1095] Systems that collect historical market data and use it to predict future market price movements are required to respond immediately to constantly fluctuating market conditions. However, existing systems often lack efficient coordination in the entire process from data collection to analysis and prediction, which can lead to delays, particularly in real-time updates of predicted values ​​and the issuance of emergency alerts. Furthermore, automated trading functions based on user-defined conditions are often insufficient, resulting in missed opportunities and the inability to execute optimal trades.

[1096] 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.

[1097] In this invention, the server includes means for collecting historical market data from an external market data provision service, means for formatting the collected market data and converting it into a data frame, means for inputting the formatted data into a generating AI model to predict future market price movements, means for storing and maintaining the predicted data on the server, means for transmitting the predicted data to a user terminal, means for visually displaying the predicted future market price movements, and means for issuing an alarm when a large price movement is predicted. This enables efficient collection and analysis of historical market data, real-time updates of predictions for future market price movements, and immediate alarms to users in the event of large price movements. Furthermore, an automated trading function based on the predicted data enables the rapid execution of optimal trades according to conditions set by the user.

[1098] "Market data" refers to data that includes information related to trading, such as trading prices, trading volume, and time of day in the market.

[1099] A "data provision service" refers to an external information source that provides market data through APIs or similar means.

[1100] "API" refers to an application programming interface for communicating with external services and databases.

[1101] A "data frame" is a two-dimensional data structure consisting of rows and columns, and is used for organizing and analyzing data.

[1102] A "generative AI model" is a model that uses artificial intelligence algorithms to predict future market price movements.

[1103] "Predictive data" refers to data about future market price movements predicted by generative AI models.

[1104] A "user terminal" is a computing device used by a user that receives and displays information transmitted from a server.

[1105] "Visually displaying" refers to presenting information in an easy-to-understand format, such as graphs or charts.

[1106] An "alert" refers to a notification or warning intended to draw attention in an emergency.

[1107] "Automated trading" is a function in which a system automatically executes trades based on conditions set by the user.

[1108] "Real-time" refers to data processing and updates occurring almost instantly.

[1109] "Conditions" refer to specific criteria or triggers set by the user, and actions such as automated trading are executed based on these.

[1110] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, and predicts future market price movements. This system consists of a server and user terminals.

[1111] The server collects historical market data from external market data providers. Typically, this involves using an API (Application Programming Interface) to send HTTP requests and retrieve data. For example, the requests library can be used to retrieve data. Market data includes information such as trading price, trading volume, and time zone. This data is usually provided in JSON format.

[1112] The server converts the collected market data into a pandas DataFrame and formats it. This formatting involves data processing such as removing unnecessary columns and imputing missing values. The formatted data is then input into a generative AI model. This generative AI model is built using libraries such as TensorFlow or PyTorch, and has a sophisticated algorithm that predicts future price movements by learning patterns and trends from past market data.

[1113] Predictive data is stored on a server. This can be stored using a database or file system. This predictive data is properly managed so that it can be accessed later by user terminals.

[1114] The user terminal retrieves the latest forecast data from the server. When the user starts the terminal, it sends a request to the server and receives the forecast data in real time. The received forecast data is displayed visually in a user-friendly format. For example, charts and graphs can be created using the matplotlib library to allow users to intuitively understand future market price movements.

[1115] Furthermore, if significant price movements are predicted based on forecast data, the user's terminal will issue an emergency alert. This alert will not only be displayed as a warning message on the screen, but can also be notified by voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[1116] Furthermore, it also features an automated trading function that analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[1117] Specific example

[1118] For example, suppose a server collects the following market data:

[1119] json

[1120] [

[1121] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1122] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103}

[1123] ]

[1124] The server analyzes this data and obtains the following predictive data from the generative AI model:

[1125] json

[1126] [

[1127] {"time": "2023-10-01 11:00", "price": 110},

[1128] {"time": "2023-10-01 12:00", "price": 115}

[1129] ]

[1130] The user terminal retrieves this predictive data and displays it visually in the following format:

[1131] -------------

[1132] | Future Price Movement |

[1133] Time: 11:00, Price: 110

[1134] | Time: 12:00, Price: 115 |

[1135] -------------

[1136] If a significant price movement is detected by the prediction, the user terminal will issue an alert:

[1137] Emergency Alert: Large price movement expected!

[1138] If the conditions are met, automated trading will be executed:

[1139] Executing buy at price 110

[1140] Executing sell at price 115

[1141] Example of a prompt

[1142] Collect market data for this week and use a generative AI model to predict market price movements for next week. Display the prediction results on a chart and implement a feature to issue alerts if significant price movements are predicted. Also, include a system that performs automated trading based on user-defined conditions.

[1143] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[1144] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1145] Step 1: Collect market data

[1146] The server collects historical market data from external market data providers. It uses the API endpoint URL and authentication information as input. The output is in JSON format and includes information such as trading price, trading volume, and time zone. The server retrieves this data using HTTP requests, for example, by using the requests library to collect the data.

[1147] Step 2: Data Formatting and Processing

[1148] The server formats the collected market data and converts it into a pandas DataFrame. It uses JSON-formatted market data as input and outputs a formatted DataFrame. Specific operations include deleting unnecessary columns and imputing missing values. For example, it creates a DataFrame using the pandas library and performs the necessary formatting.

[1149] Step 3: Prediction using a generative AI model

[1150] The server inputs formatted data into a generating AI model to predict future market price movements. It uses a formatted dataframe as input and outputs predicted future price data. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to input historical data into the model and calculate predictions.

[1151] Step 4: Save prediction data

[1152] The server stores the prediction data obtained from the generated AI model. It uses predicted price data as input and stores the output in a database or file system on the server. Specifically, it might save the data to a JSON file, for example, to allow users to access it later.

[1153] Step 5: Obtaining Analysis Results

[1154] The user terminal retrieves the latest prediction data from the server. It uses the server's endpoint URL as input and receives the prediction data in JSON format as output. Specifically, it sends an HTTP request to retrieve data from the server.

[1155] Step 6: Visual representation of data

[1156] The user terminal visually displays the received forecast data. It uses the acquired forecast data as input and displays it as output in chart or graph format. Specifically, it uses the matplotlib library to draw graphs, intuitively showing the user future price movements.

[1157] Step 7: Confirm and issue emergency alerts

[1158] The user terminal issues an emergency alert when a large price movement is expected based on the forecast data. It uses forecast data obtained from the server as input and outputs a warning message and voice notification. Specifically, it compares the forecast value with a certain threshold, displays an alert if the threshold is exceeded, and notifies the user using voice and vibration functions.

[1159] Step 8: Setting up and running automated trading

[1160] The server executes automated trades based on user-defined conditions. It uses user-defined conditions and predicted data as input, and outputs appropriate trade actions. Specifically, it evaluates predicted values ​​based on user conditions, and if the conditions are met, it calls the trading API to execute the trade.

[1161] In this way, the server and user terminal cooperate at each step to collect, analyze, display, issue alerts for, and automate market data, becoming a powerful tool for investors to make appropriate and rapid investment decisions.

[1162] (Application Example 1)

[1163] 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."

[1164] Conventional market forecasting systems have low accuracy in predicting future market trends, making it difficult for users to make appropriate investment decisions based on them. Furthermore, they lack features such as alarm functions for large price movements and automated trading functions, often failing to function adequately in market environments where rapid response is required. The present invention aims to solve these problems and realize a system that provides more accurate and reliable market forecasting and responsive investment support.

[1165] 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.

[1166] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model to predict future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for executing automated trading based on user settings. As a result, users can grasp future market trends with high accuracy, respond immediately to large price movements, and trade at the optimal timing through automated trading.

[1167] "Historical market data" refers to information such as the trading price, trading volume, and time of day when actual transactions took place in the financial market in the past.

[1168] A "generative AI model" is a machine learning algorithm trained to identify patterns and trends from large amounts of data and predict future price movements.

[1169] "Future market price movements" refer to trends such as price fluctuations and trading volume fluctuations in future financial markets, as predicted using generative AI models.

[1170] "Visual display" means presenting predicted future market price movements in a format that users can intuitively understand, using display technologies such as graphs and charts.

[1171] "Issuing an alert" means using means such as voice, screen display, or vibration to warn the user when a significant fluctuation is predicted based on anticipated future market price movements.

[1172] "User settings" refer to the conditions and thresholds that users of the market application can individually set, and automated trading is executed based on these settings.

[1173] "Automated trading" refers to a function that automatically executes trades without manual intervention, based on predicted future market price movements and according to conditions pre-set by the user.

[1174] "Real-time updates" means that predicted future market price movements are instantly reflected in a short time whenever new data is acquired.

[1175] The system for implementing this invention consists of two main components: a server and a user terminal. The server collects historical market data from external market data provision services and analyzes it using a generative AI model. The user terminal receives predictive data provided by the server and displays it visually. It also issues an alert when a large price movement is predicted and executes automated trading based on user settings.

[1176] The server first collects market data via an API (Application Programming Interface) using the requests library. This data is provided in JSON format and converted to a DataFrame on the server side using the pandas library. After formatting into a DataFrame, it is input into a generative AI model to predict future market price movements. The generative AI model is trained using machine learning frameworks such as Keras and TensorFlow, and uses advanced algorithms to analyze past patterns and predict future market trends. These prediction results are stored on the server and provided upon request from the user's terminal.

[1177] The user terminal retrieves prediction data, which is the result of analysis, from the server in real time. The retrieved data is visually displayed as graphs and charts using libraries such as matplotlib. This display allows the user to intuitively grasp future market price movements. If a large price movement is predicted based on the prediction data, an alarm message will be displayed on the screen, and notifications can also be made by sound or vibration. This allows the user to take immediate action to respond to sudden market fluctuations.

[1178] Furthermore, this system includes an automated trading function. Based on conditions set by the user in advance, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to trade without missing the optimal trading timing, aiming to maximize profits.

[1179] For example, data collection and analysis can be performed using the following prompt statements:

[1180] "Collect historical market data from market data provision services and use a generated AI model to predict future market price movements."

[1181] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[1182] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1183] Step 1:

[1184] The server collects historical market data from an external market data provider service. It retrieves data in JSON format using the requests library via an API (Application Programming Interface). The input is the URL of the API endpoint, and the output is market data in JSON format. In this step, the server performs the following specific actions:

[1185] Send a request to the API endpoint.

[1186] Market data is received as a response.

[1187] Save the received data in JSON format.

[1188] Step 2:

[1189] The server converts the acquired market data into a pandas dataframe and formats it. The input is market data in JSON format, and the output is a formatted dataframe. The specific data processing performed in this step is as follows:

[1190] Read JSON data and convert it to a pandas DataFrame.

[1191] Rename the columns in the dataframe as needed.

[1192] Format the time-series data to standardize the date and time format.

[1193] Step 3:

[1194] The server inputs the formatted data frame into a generating AI model to predict future market price movements. The input is the processed data frame, and the output is the predicted data. The data calculations performed in this step are as follows:

[1195] Extract features from a data frame.

[1196] The features are input into the generative AI model.

[1197] The generative AI model makes predictions and outputs them as predicted data.

[1198] Step 4:

[1199] The server holds the prediction data and provides it upon request from the user terminal. The input is the prediction data, and the output is the prediction data provided to the user terminal. In this step, the server performs the following actions:

[1200] Save the prediction data to the database.

[1201] It returns predictive data in response to requests from the user's terminal.

[1202] Step 5:

[1203] The user terminal retrieves predicted data, which is the analysis result, from the server and displays it visually. The input is predicted data from the server, and the output is information displayed visually in the form of graphs and charts. The specific actions performed in this step are as follows:

[1204] Send a request for prediction data to the server.

[1205] Analyze the prediction data received from the server.

[1206] Display the results as graphs or charts using the matplotlib library.

[1207] Step 6:

[1208] The user terminal issues an alert when a large price movement is predicted. The input is prediction data, and the output is an alert notification to the user. In this step, the user terminal performs the following specific actions:

[1209] Analyze the forecast data to see if significant price movements are predicted.

[1210] If a large price movement is predicted, an alert message will be displayed on the screen.

[1211] Notifications will be sent via voice or vibration as needed.

[1212] Step 7:

[1213] The user terminal executes automated trading based on user settings. Inputs include user settings and forecast data, while output is the actual execution of trades. The actions performed in this step are as follows:

[1214] Load user settings and check the trading conditions.

[1215] Analyze the prediction data and check if it meets the user-defined conditions.

[1216] If the conditions are met, the transaction will be executed automatically.

[1217] 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.

[1218] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, predicts future market price movements, displays them visually, and issues warnings as needed, further incorporating an emotion engine that recognizes user emotions. This system consists of a server, a user terminal, and an emotion engine.

[1219] Server-based processing

[1220] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, it uses the requests library to retrieve data. The retrieved data is converted into a pandas dataframe and formatted. This formatted data is input into a generative AI model, which analyzes the data and predicts future market price movements. The prediction results are stored on the server as prediction data.

[1221] Processing by the user terminal

[1222] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[1223] Emergency alert issued

[1224] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. The alert will not only be displayed as a warning message on the screen, but can also be notified via voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[1225] Automated trading function

[1226] This system also includes an automated trading function, which analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[1227] Introducing an emotional engine

[1228] A distinctive feature of this invention is the addition of an emotion engine. The emotion engine is an element for recognizing and analyzing the user's emotions and is built into the user terminal. The emotion engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc.

[1229] Processing by the emotion engine

[1230] The emotion engine embedded in the user's terminal analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging them to trade cautiously. It can also adjust investment strategies according to the user's emotional state. This allows users to make better investment decisions that take their own emotions into account.

[1231] Specific example

[1232] For example, suppose the server collects JSON data in the following format:

[1233] json

[1234] [

[1235] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1236] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[1237] ...

[1238] ]

[1239] The server analyzes this data and can obtain predictive data from the generative AI model, such as:

[1240] json

[1241] [

[1242] {"time": "2023-10-01 11:00", "price": 110},

[1243] {"time": "2023-10-01 12:00", "price": 115},

[1244] ...

[1245] ]

[1246] The user terminal retrieves this predictive data and displays it visually as follows.

[1247] -------------

[1248] | Future Price Movement |

[1249] Time: 11:00, Price: 110

[1250] | Time: 12:00, Price: 115 |

[1251] -------------

[1252] If a significant price movement is predicted, an alert will be issued and users will be notified.

[1253] Emergency Alert: Large price movement expected!

[1254] If the emotion engine detects user anxiety, it can display additional messages such as the following:

[1255] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[1256] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[1257] Thus, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and emotion engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[1258] The following describes the processing flow.

[1259] Step 1:

[1260] Data acquisition [server]

[1261] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[1262] Python

[1263] response = requests.get("http: / / api.marketdata.com")

[1264] data = response.json()

[1265] Step 2:

[1266] Data formatting [server]

[1267] The server converts the retrieved data into a pandas DataFrame. This DataFrame is then modified as needed, with column names and data types adjusted to make it suitable for analysis.

[1268] Python

[1269] data_df = pd.DataFrame(data)

[1270] Step 3:

[1271] Initialization of the generative AI model [server]

[1272] The server initializes the AI ​​model. This model analyzes historical market data to predict future price movements.

[1273] Python

[1274] model = PredictiveModel()

[1275] Step 4:

[1276] Data analysis [server]

[1277] The server inputs the formatted data into an AI model for analysis. This analysis predicts future market price movements, and the results are saved as predictive data.

[1278] Python

[1279] prediction = model.predict(data_df)

[1280] Step 5:

[1281] Obtaining predictive data [Device]

[1282] The device sends a request to the server to obtain prediction data, which is the result of the analysis. When the user starts up the device, it receives the latest prediction data from the server in real time.

[1283] Python

[1284] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[1285] Step 6:

[1286] Chart display [Terminal]

[1287] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[1288] Python

[1289] plt.figure(figsize=(10, 5))

[1290] plt.plot(prediction_data['time'], prediction_data['price'])

[1291] plt.title("Future Price Movement")

[1292] plt.xlabel("Time")

[1293] plt.ylabel("Price")

[1294] plt.show()

[1295] Step 7:

[1296] Detection of large price movements [Terminal]

[1297] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[1298] Python

[1299] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[1300] trigger_alert = True

[1301] else:

[1302] trigger_alert = False

[1303] Step 8:

[1304] Emergency alert issued [Terminal]

[1305] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[1306] Python

[1307] if trigger_alert:

[1308] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[1309] Step 9:

[1310] Confirmation of automated trading settings [User]

[1311] The system checks if the user has set up the automated trading function, and if the setting is enabled, it automatically executes trades when certain conditions are met.

[1312] Python

[1313] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[1314] error_trade()

[1315] Step 10:

[1316] Emotion engine initialization [Terminal]

[1317] The device initializes the emotion engine and prepares to analyze the user's emotional state in real time. The emotion engine utilizes data from the camera, microphone, keyboard input, and other sources.

[1318] Python

[1319] emotion_engine = EmotionEngine()

[1320] emotion_engine.initialize()

[1321] Step 11:

[1322] Emotion analysis [terminal]

[1323] The device uses an emotion engine to analyze the user's emotions from their facial expressions, voice tone, and input patterns. Based on the analysis results, it adjusts notifications and alerts.

[1324] Python

[1325] user_emotion = emotion_engine.analyze()

[1326] Step 12:

[1327] Emotion-based notification adjustments [device]

[1328] The system adjusts the intensity and content of notifications and alerts based on the user's emotional state. For example, if a user is feeling anxious, the system will provide more detailed information to increase their sense of security.

[1329] Python

[1330] if user_emotion == "anxious":

[1331] display_message("We noticed you seem anxious. Would you like more detailed analysis before making a decision?")

[1332] Step 13:

[1333] Adjusting investment strategies based on emotions [Terminal]

[1334] Based on the analysis results of the emotion engine, investment strategies based on predictive data will be adjusted. If the emotional state is not calm, countermeasures will be taken, such as recommending low-risk trades.

[1335] Python

[1336] if user_emotion != "calm":

[1337] adjust_investment_strategy("low-risk")

[1338] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, and the emotion engine analyzes the user's emotions, providing appropriate notifications and adjusting investment strategies. This enables the user to grasp market conditions in real time and make quick and appropriate investment decisions.

[1339] (Example 2)

[1340] 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."

[1341] Traditional market forecasting systems analyze past market data and make future predictions, but this alone is insufficient to accurately support changes in user sentiment and rapid responses to emergencies. Furthermore, warnings to users may be delayed when significant market fluctuations are predicted, and automated trading functions and real-time information updates may not function effectively.

[1342] 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.

[1343] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model and predicting future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for analyzing the user's emotions using an emotion analysis engine and adjusting notifications and actions based on the results. This enables market forecasting that takes into account the user's emotional state and prompt alert issuance, as well as the provision of real-time updated market information and the effective operation of automated trading functions.

[1344] "Historical market data" refers to past trading information and price trends in financial markets, including stock prices, exchange rates, and commodity prices over a specific period.

[1345] A "generative AI model" refers to a computational model that uses artificial intelligence technology to learn from data and predict future price movements and patterns.

[1346] "Future market price movements" refer to price fluctuations and trends in future financial markets predicted based on current data.

[1347] "Visual display methods" refer to ways of displaying predicted market data in an easy-to-understand format for users, such as using graphs, charts, and dashboards.

[1348] "Means of issuing warnings" refers to methods of notifying or alerting users when significant market fluctuations are anticipated, and includes voice notifications, pop-up messages, and vibrations.

[1349] An "emotion analysis engine" refers to technology for detecting and analyzing a user's emotional state, and this includes systems that recognize emotions using data from cameras, microphones, keyboard input, and other sources.

[1350] "Means of adjusting notifications and actions" refers to methods of adjusting the information displayed and the content of warnings issued based on the user's emotional state obtained by the emotion analysis engine.

[1351] "Methods for automated trading" refers to systems that automatically execute trades based on predicted market data and according to pre-set conditions.

[1352] "Real-time updates" refers to methods of continuously acquiring the latest market data and forecast results and keeping them immediately accessible to users.

[1353] A "user terminal" refers to a device used by a user to view or manipulate information, and this includes personal computers, smartphones, tablets, and other similar devices.

[1354] This invention is a system that collects market data, analyzes it using a generative AI model, predicts future market price movements, visually displays the results, and issues warnings as needed. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, more advanced investment support becomes possible. This system consists of a server, a user terminal, and an emotion analysis engine.

[1355] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The data is retrieved using the requests library, converted into a pandas DataFrame, and formatted. The formatted data is then input into a generating AI model for analysis and prediction of future market price movements. These prediction results are stored on the server and provided to the user's terminal.

[1356] The user terminal retrieves forecast data from the server and displays it visually as charts and graphs using libraries such as matplotlib. This allows users to intuitively grasp future market price movements. Furthermore, if a large price movement is predicted based on the forecast data, the user terminal will issue an alert. The alert can be notified not only as a warning message on the screen, but also by sound and vibration. This allows users to respond immediately to sudden market fluctuations.

[1357] Furthermore, this system includes an automated trading function, which automatically executes trades when specific triggers occur based on conditions pre-set by the user. This function allows users to trade at the optimal time and maximize their profits.

[1358] A distinctive feature of this invention is the incorporation of an emotion analysis engine. The emotion analysis engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc. The emotion analysis engine, which is embedded in the user terminal, analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging the user to proceed with the transaction cautiously.

[1359] As a specific example, the data collected by the server is in the following format:

[1360] [

[1361] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1362] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[1363] ...

[1364] ]

[1365] The analyzed prediction data is expressed as follows:

[1366] [

[1367] {"time": "2023-10-01 11:00", "price": 110},

[1368] {"time": "2023-10-01 12:00", "price": 115},

[1369] ...

[1370] ]

[1371] The following is an example of how a user terminal retrieves and visually displays this predictive data:

[1372] -------------

[1373] | Future Price Movement |

[1374] Time: 11:00, Price: 110

[1375] | Time: 12:00, Price: 115 |

[1376] -------------

[1377] The following warning will be displayed when a large price movement is expected:

[1378] Emergency Alert: Large price movement expected!

[1379] If the emotion analysis engine detects user anxiety, it will display a message like the following:

[1380] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[1381] Examples of prompt statements that can be used include the following:

[1382] "Provide a detailed prediction for the market prices based on the following past data: {past_data}. Consider factors such as {factors} and provide predictions for the next 24 hours."

[1383] As described above, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and sentiment analysis engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[1384] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1385] Step 1:

[1386] The server collects market data.

[1387] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The input is the API endpoint, and the output is the retrieved market data in JSON format. Specifically, the server uses the requests library to retrieve data from the API endpoint.

[1388] Step 2:

[1389] The server formats the data it has collected.

[1390] The acquired market data is converted into a pandas DataFrame and formatted. The input is the market data acquired in the previous step in JSON format, and the output is a formatted pandas DataFrame. Specifically, the server uses the pandas library to convert the JSON data into a DataFrame format.

[1391] Step 3:

[1392] The server analyzes the data and predicts future market price movements.

[1393] The system inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted pandas dataframe, and the output is data representing predicted market price movements. Specifically, the server uses a generative AI model in TensorFlow or PyTorch to perform data analysis and prediction.

[1394] Step 4:

[1395] The server stores the prediction data and provides it to the user's terminal.

[1396] The generated prediction data is stored on the server and provided as needed upon request from the user's terminal. The input is the prediction data, and the output is the stored data and the data provided to the user's terminal. Specifically, the server stores the data in the file system and provides the data to the user's terminal via an API.

[1397] Step 5:

[1398] The user's terminal acquires predictive data and displays it visually.

[1399] The user terminal sends a request to the server to retrieve prediction data. The retrieved data is then displayed in charts or graphs using visualization libraries such as matplotlib. The input is the prediction data retrieved from the server, and the output is the displayed chart or graph. Specifically, the user terminal sends an HTTP request, receives the data, and then generates the graph.

[1400] Step 6:

[1401] The user terminal will issue an alert if a large price movement is predicted.

[1402] The system analyzes forecast data and issues an alert if a large price movement is predicted. The input is forecast data, and the output is an alert message, voice notification, and vibration notification. Specifically, the user terminal calculates the maximum and minimum values ​​of the data, and displays and issues an alert if there is a large difference.

[1403] Step 7:

[1404] The user's terminal performs automated trading.

[1405] Buying and selling are performed automatically based on conditions set by the user. The inputs are the set conditions and predicted data, and the output is the result of the executed trades. Specifically, the user terminal checks the set values ​​and executes trades via the API if the conditions are met.

[1406] Step 8:

[1407] The emotion analysis engine analyzes the user's emotions and adjusts notifications and actions accordingly.

[1408] The system analyzes user emotions in real time using camera, microphone, and keyboard input, and adjusts notifications and alerts based on the results. The input is user emotion data, and the output is the adjusted notifications and actions. Specifically, the emotion analysis engine uses an emotion recognition algorithm to analyze the user's emotions and dynamically changes the system's response based on the results.

[1409] (Application Example 2)

[1410] 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."

[1411] There is a need to improve the accuracy of market price movement predictions and provide users with information to make more informed investment decisions. However, current systems have limitations in providing investment advice that takes emotions into account and in notifying users of sudden market changes in a timely manner. In particular, a lack of safe and efficient ways for users to obtain market information while in autonomous vehicles is a challenge.

[1412] 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.

[1413] In this invention, the server includes means for collecting historical data, means for analyzing historical data using a generative AI model to predict future price movements, and means for visually displaying the predicted future price movements. This enables means for issuing an alarm when a large price movement is predicted, and means for recognizing and analyzing user emotions to adjust notifications and alerts.

[1414] "Historical data" refers to various numerical data and information collected prior to the present. It is fundamental data for understanding market trends and predicting future developments.

[1415] A "generative AI model" refers to an artificial intelligence algorithm that learns patterns from large amounts of data to make new predictions and classifications. It is a machine learning model trained for a specific purpose.

[1416] "Future price movements" refers to predictions of fluctuations in the price or value of a market or a specific object at a future point in time.

[1417] "Visual display methods" refer to ways of making data and information visible in visual formats such as graphs and charts. These are display methods designed to make information easy for users to understand intuitively.

[1418] "Means of issuing warnings" refers to a system for notifying users of warnings when large price movements or anomalies are detected. These warnings are issued through methods such as voice, vibration, and screen displays.

[1419] "Means of recognizing and analyzing user emotions" refers to technologies that use devices such as cameras and microphones to detect emotions from a user's facial expressions and voice, and then analyze that information to understand the user's emotional state.

[1420] "Methods for automated trading" refer to systems that automatically execute buy and sell orders based on set conditions and predictive data. These functions aim to minimize user intervention and enable efficient trading.

[1421] "Real-time" means that data and information are processed and updated instantly. It refers to a state where the latest information is always provided without any time lag.

[1422] This invention relates to a system for predicting future market price movements in autonomous vehicles and providing investment support to users. This system consists of a server, a user terminal, and an emotion engine.

[1423] Server-based processing

[1424] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The retrieved data is converted into a pandas dataframe and formatted. The formatted data is input into a generative AI model, which performs data analysis and predicts future market price movements. The prediction results are stored on the server as prediction data.

[1425] Specifically, the server performs the following processes:

[1426] 1. Collect market data: Collect historical market data and convert it into a pandas dataframe.

[1427] 2. Data Analysis: The collected data is input into a generating AI model for analysis, and future market price movements are predicted.

[1428] 3. Saving prediction data: The analyzed prediction data is saved to the server.

[1429] Processing by the user terminal

[1430] The user terminal retrieves prediction data, which is the result of the analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs.

[1431] Specifically, the user terminal performs the following actions:

[1432] 1. Obtaining forecast data: Request and obtain the latest forecast data from the server.

[1433] 2. Visual display of data: The acquired data will be displayed to the user in the form of graphs and charts, allowing for intuitive understanding.

[1434] 3. Emotional Response: The emotion engine analyzes the user's emotions and, if they are feeling anxious, displays additional detailed information and advice.

[1435] Processing by the emotion engine

[1436] The emotion engine detects emotions from the user's facial expressions, voice tone, and input patterns through the camera, microphone, and keyboard input. If the user is feeling anxious, the system will provide more detailed information or display messages urging them to proceed cautiously. This allows users to make better investment decisions by taking their own emotions into consideration.

[1437] System Features

[1438] This system is particularly useful when users conduct investment activities within autonomous vehicles and offers the following advantages:

[1439] 1. Immediately notify users of sudden market fluctuations and prompt them to take action.

[1440] 2. Analyze the user's emotions and provide appropriate advice regarding anxiety and fear.

[1441] 3. Automated trading is executed based on predictive data to ensure optimal trading timing and avoid missing opportunities.

[1442] As a concrete example, imagine a scenario where, while traveling in an autonomous vehicle, a user can anticipate sudden market fluctuations based on predictive data and receive advice from an emotional engine to "avoid intuitive trading."

[1443] Examples of prompts to input into a generative AI model:

[1444] Based on historical market data, predict future market price movements. If the user expresses concerns, display additional support messages. Make predictions based on the following data and output the results in JSON format.

[1445] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1446] Step 1:

[1447] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The input is the API endpoint URL, and the output is the retrieved raw data.

[1448] Step 2:

[1449] The server retrieves data and converts it into a pandas DataFrame, then formats it. The input is raw data, and the output is a formatted pandas DataFrame. The data converted into a DataFrame is in a format suitable for analysis.

[1450] Step 3:

[1451] The server inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted data frame, and the output is predicted data. The generative AI model analyzes future market trends based on the input data.

[1452] Step 4:

[1453] The server stores the prediction data. The input is the prediction data from the generative AI model, and the output is the stored prediction data. The stored prediction data is later retrieved from the user's terminal.

[1454] Step 5:

[1455] The user terminal sends a request to the server and receives the latest forecast data in real time. The input is the request to the server, and the output is the forecast data. The user terminal receives this data and uses it in the next step.

[1456] Step 6:

[1457] The system visually displays the forecast data received by the user's terminal in a user-friendly format as graphs and charts. The input is forecast data, and the output is the visually displayed data. This allows users to intuitively grasp future market trends.

[1458] Step 7:

[1459] The emotion engine analyzes the user's emotions using input from the camera and microphone. The input is the user's facial expressions and voice data, and the output is the analyzed emotion data. The emotion engine detects whether the user is feeling anxious.

[1460] Step 8:

[1461] The user's device adjusts notifications and alerts based on the analysis results of the emotion engine. The input is emotion data, and the output is adjusted notifications and alerts. If the user is feeling anxious, more detailed information and advice will be displayed.

[1462] Step 9:

[1463] The user terminal automatically executes trades based on predicted future price movements. Inputs are predicted data and pre-set trading conditions, while output is the executed trades. This allows the user to make optimal trades in response to market trends.

[1464] Step 10:

[1465] The user terminal continuously updates market price movements in real time, periodically sending requests to the server to receive new forecast data. The input is a request to the server, and the output is the latest forecast data. This allows users to always make investment decisions based on the most up-to-date information.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] [Fourth Embodiment]

[1470] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1471] 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.

[1472] 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).

[1473] 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.

[1474] 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.

[1475] 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).

[1476] 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.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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".

[1483] This invention relates to a system that collects historical market data, analyzes it using a generated AI model, predicts future market price movements, displays them visually, and issues warnings as needed. This system consists of a server and user terminals.

[1484] Server-based processing

[1485] The server first collects historical market data from external market data providers. Generally, this data, including trading prices, volume, and time zones, is obtained via an API (Application Programming Interface). This data is provided in formats such as JSON and is often retrieved using the requests library.

[1486] Next, the server converts the acquired data into a pandas DataFrame and formats it. This formatted data is then input into a generative AI model to predict future price movements. The generative AI model uses advanced algorithms to predict future market trends by analyzing past patterns and trends. These prediction results are stored on the server as prediction data.

[1487] Processing by the user terminal

[1488] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is visually displayed in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[1489] Emergency alert issued

[1490] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. This alert will be displayed as a warning message on the screen, and notifications can also be made via sound and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[1491] Automated trading function

[1492] Furthermore, this system includes an automated trading function. Based on conditions pre-set by the user, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to make optimal trades without missing opportunities, maximizing their profits.

[1493] Specific example

[1494] For example, suppose the server collects JSON data in the following format:

[1495] json

[1496] [

[1497] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1498] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[1499] ...

[1500] ]

[1501] The server analyzes this data and can obtain predictive data from the generative AI model, such as:

[1502] json

[1503] [

[1504] {"time": "2023-10-01 11:00", "price": 110},

[1505] {"time": "2023-10-01 12:00", "price": 115},

[1506] ...

[1507] ]

[1508] The user terminal retrieves this predictive data and displays it visually as follows.

[1509] -------------

[1510] | Future Price Movement |

[1511] Time: 11:00, Price: 110

[1512] | Time: 12:00, Price: 115 |

[1513] -------------

[1514] If a significant price movement is predicted, an alert will be issued and users will be notified.

[1515] Emergency Alert: Large price movement expected!

[1516] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[1517] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[1518] The following describes the processing flow.

[1519] Step 1:

[1520] Data acquisition [server]

[1521] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[1522] Python

[1523] response = requests.get("http: / / api.marketdata.com")

[1524] data = response.json()

[1525] Step 2:

[1526] Data formatting [server]

[1527] The acquired data is converted into a pandas DataFrame and formatted. This DataFrame is then modified as needed, including changing column names and data types, to make it suitable for analysis.

[1528] Python

[1529] data_df = pd.DataFrame(data)

[1530] Step 3:

[1531] Initialization of the generative AI model [server]

[1532] The server initializes the AI ​​model. This model analyzes historical market data to predict future price movements.

[1533] Python

[1534] model = PredictiveModel()

[1535] Step 4:

[1536] Data analysis [server]

[1537] The server inputs the formatted data into a generating AI model for analysis. This analysis predicts future market price movements.

[1538] Python

[1539] prediction = model.predict(data_df)

[1540] Step 5:

[1541] Obtaining predictive data [Device]

[1542] The user's terminal sends a request to the server and retrieves the predicted data, which is the result of the analysis.

[1543] Python

[1544] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[1545] Step 6:

[1546] Chart display [Terminal]

[1547] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[1548] Python

[1549] plt.figure(figsize=(10, 5))

[1550] plt.plot(prediction_data['time'], prediction_data['price'])

[1551] plt.title("Future Price Movement")

[1552] plt.xlabel("Time")

[1553] plt.ylabel("Price")

[1554] plt.show()

[1555] Step 7:

[1556] Detection of large price movements [Terminal]

[1557] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[1558] Python

[1559] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[1560] trigger_alert = True

[1561] else:

[1562] trigger_alert = False

[1563] Step 8:

[1564] Emergency alert issued [Terminal]

[1565] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[1566] Python

[1567] if trigger_alert:

[1568] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[1569] Step 9:

[1570] Confirmation of automated trading settings [User]

[1571] The system checks if the user has enabled the automated trading function. If enabled, trades will be executed automatically when certain conditions are met.

[1572] Python

[1573] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[1574] error_trade()

[1575] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, issues an alert if a large price movement is predicted, and performs automated trading as needed. Through this series of processes, users can grasp market conditions in real time and make quick and appropriate investment decisions.

[1576] (Example 1)

[1577] 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".

[1578] Systems that collect historical market data and use it to predict future market price movements are required to respond immediately to constantly fluctuating market conditions. However, existing systems often lack efficient coordination in the entire process from data collection to analysis and prediction, which can lead to delays, particularly in real-time updates of predicted values ​​and the issuance of emergency alerts. Furthermore, automated trading functions based on user-defined conditions are often insufficient, resulting in missed opportunities and the inability to execute optimal trades.

[1579] 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.

[1580] In this invention, the server includes means for collecting historical market data from an external market data provision service, means for formatting the collected market data and converting it into a data frame, means for inputting the formatted data into a generating AI model to predict future market price movements, means for storing and maintaining the predicted data on the server, means for transmitting the predicted data to a user terminal, means for visually displaying the predicted future market price movements, and means for issuing an alarm when a large price movement is predicted. This enables efficient collection and analysis of historical market data, real-time updates of predictions for future market price movements, and immediate alarms to users in the event of large price movements. Furthermore, an automated trading function based on the predicted data enables the rapid execution of optimal trades according to conditions set by the user.

[1581] "Market data" refers to data that includes information related to trading, such as trading prices, trading volume, and time of day in the market.

[1582] A "data provision service" refers to an external information source that provides market data through APIs or similar means.

[1583] "API" refers to an application programming interface for communicating with external services and databases.

[1584] A "data frame" is a two-dimensional data structure consisting of rows and columns, and is used for organizing and analyzing data.

[1585] A "generative AI model" is a model that uses artificial intelligence algorithms to predict future market price movements.

[1586] "Predictive data" refers to data about future market price movements predicted by generative AI models.

[1587] A "user terminal" is a computing device used by a user that receives and displays information transmitted from a server.

[1588] "Visually displaying" refers to presenting information in an easy-to-understand format, such as graphs or charts.

[1589] An "alert" refers to a notification or warning intended to draw attention in an emergency.

[1590] "Automated trading" is a function in which a system automatically executes trades based on conditions set by the user.

[1591] "Real-time" refers to data processing and updates occurring almost instantly.

[1592] "Conditions" refer to specific criteria or triggers set by the user, and actions such as automated trading are executed based on these.

[1593] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, and predicts future market price movements. This system consists of a server and user terminals.

[1594] The server collects historical market data from external market data providers. Typically, this involves using an API (Application Programming Interface) to send HTTP requests and retrieve data. For example, the requests library can be used to retrieve data. Market data includes information such as trading price, trading volume, and time zone. This data is usually provided in JSON format.

[1595] The server converts the collected market data into a pandas DataFrame and formats it. This formatting involves data processing such as removing unnecessary columns and imputing missing values. The formatted data is then input into a generative AI model. This generative AI model is built using libraries such as TensorFlow or PyTorch, and has a sophisticated algorithm that predicts future price movements by learning patterns and trends from past market data.

[1596] Predictive data is stored on a server. This can be stored using a database or file system. This predictive data is properly managed so that it can be accessed later by user terminals.

[1597] The user terminal retrieves the latest forecast data from the server. When the user starts the terminal, it sends a request to the server and receives the forecast data in real time. The received forecast data is displayed visually in a user-friendly format. For example, charts and graphs can be created using the matplotlib library to allow users to intuitively understand future market price movements.

[1598] Furthermore, if significant price movements are predicted based on forecast data, the user's terminal will issue an emergency alert. This alert will not only be displayed as a warning message on the screen, but can also be notified by voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[1599] Furthermore, it also features an automated trading function that analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[1600] Specific example

[1601] For example, suppose a server collects the following market data:

[1602] json

[1603] [

[1604] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1605] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103}

[1606] ]

[1607] The server analyzes this data and obtains the following predictive data from the generative AI model:

[1608] json

[1609] [

[1610] {"time": "2023-10-01 11:00", "price": 110},

[1611] {"time": "2023-10-01 12:00", "price": 115}

[1612] ]

[1613] The user terminal retrieves this predictive data and displays it visually in the following format:

[1614] -------------

[1615] | Future Price Movement |

[1616] Time: 11:00, Price: 110

[1617] | Time: 12:00, Price: 115 |

[1618] -------------

[1619] If a significant price movement is detected by the prediction, the user terminal will issue an alert:

[1620] Emergency Alert: Large price movement expected!

[1621] If the conditions are met, automated trading will be executed:

[1622] Executing buy at price 110

[1623] Executing sell at price 115

[1624] Example of a prompt

[1625] Collect market data for this week and use a generative AI model to predict market price movements for next week. Display the prediction results on a chart and implement a feature to issue alerts if significant price movements are predicted. Also, include a system that performs automated trading based on user-defined conditions.

[1626] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[1627] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1628] Step 1: Collect market data

[1629] The server collects historical market data from external market data providers. It uses the API endpoint URL and authentication information as input. The output is in JSON format and includes information such as trading price, trading volume, and time zone. The server retrieves this data using HTTP requests, for example, by using the requests library to collect the data.

[1630] Step 2: Data Formatting and Processing

[1631] The server formats the collected market data and converts it into a pandas DataFrame. It uses JSON-formatted market data as input and outputs a formatted DataFrame. Specific operations include deleting unnecessary columns and imputing missing values. For example, it creates a DataFrame using the pandas library and performs the necessary formatting.

[1632] Step 3: Prediction using a generative AI model

[1633] The server inputs formatted data into a generating AI model to predict future market price movements. It uses a formatted dataframe as input and outputs predicted future price data. Specifically, it uses machine learning libraries such as TensorFlow and PyTorch to input historical data into the model and calculate predictions.

[1634] Step 4: Save prediction data

[1635] The server stores the prediction data obtained from the generated AI model. It uses predicted price data as input and stores the output in a database or file system on the server. Specifically, it might save the data to a JSON file, for example, to allow users to access it later.

[1636] Step 5: Obtaining Analysis Results

[1637] The user terminal retrieves the latest prediction data from the server. It uses the server's endpoint URL as input and receives the prediction data in JSON format as output. Specifically, it sends an HTTP request to retrieve data from the server.

[1638] Step 6: Visual representation of data

[1639] The user terminal visually displays the received forecast data. It uses the acquired forecast data as input and displays it as output in chart or graph format. Specifically, it uses the matplotlib library to draw graphs, intuitively showing the user future price movements.

[1640] Step 7: Confirm and issue emergency alerts

[1641] The user terminal issues an emergency alert when a large price movement is expected based on the forecast data. It uses forecast data obtained from the server as input and outputs a warning message and voice notification. Specifically, it compares the forecast value with a certain threshold, displays an alert if the threshold is exceeded, and notifies the user using voice and vibration functions.

[1642] Step 8: Setting up and running automated trading

[1643] The server executes automated trades based on user-defined conditions. It uses user-defined conditions and predicted data as input, and outputs appropriate trade actions. Specifically, it evaluates predicted values ​​based on user conditions, and if the conditions are met, it calls the trading API to execute the trade.

[1644] In this way, the server and user terminal cooperate at each step to collect, analyze, display, issue alerts for, and automate market data, becoming a powerful tool for investors to make appropriate and rapid investment decisions.

[1645] (Application Example 1)

[1646] 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".

[1647] Conventional market forecasting systems have low accuracy in predicting future market trends, making it difficult for users to make appropriate investment decisions based on them. Furthermore, they lack features such as alarm functions for large price movements and automated trading functions, often failing to function adequately in market environments where rapid response is required. The present invention aims to solve these problems and realize a system that provides more accurate and reliable market forecasting and responsive investment support.

[1648] 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.

[1649] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model to predict future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for executing automated trading based on user settings. As a result, users can grasp future market trends with high accuracy, respond immediately to large price movements, and trade at the optimal timing through automated trading.

[1650] "Historical market data" refers to information such as the trading price, trading volume, and time of day when actual transactions took place in the financial market in the past.

[1651] A "generative AI model" is a machine learning algorithm trained to identify patterns and trends from large amounts of data and predict future price movements.

[1652] "Future market price movements" refer to trends such as price fluctuations and trading volume fluctuations in future financial markets, as predicted using generative AI models.

[1653] "Visual display" means presenting predicted future market price movements in a format that users can intuitively understand, using display technologies such as graphs and charts.

[1654] "Issuing an alert" means using means such as voice, screen display, or vibration to warn the user when a significant fluctuation is predicted based on anticipated future market price movements.

[1655] "User settings" refer to the conditions and thresholds that users of the market application can individually set, and automated trading is executed based on these settings.

[1656] "Automated trading" refers to a function that automatically executes trades without manual intervention, based on predicted future market price movements and according to conditions pre-set by the user.

[1657] "Real-time updates" means that predicted future market price movements are instantly reflected in a short time whenever new data is acquired.

[1658] The system for implementing this invention consists of two main components: a server and a user terminal. The server collects historical market data from external market data provision services and analyzes it using a generative AI model. The user terminal receives predictive data provided by the server and displays it visually. It also issues an alert when a large price movement is predicted and executes automated trading based on user settings.

[1659] The server first collects market data via an API (Application Programming Interface) using the requests library. This data is provided in JSON format and converted to a DataFrame on the server side using the pandas library. After formatting into a DataFrame, it is input into a generative AI model to predict future market price movements. The generative AI model is trained using machine learning frameworks such as Keras and TensorFlow, and uses advanced algorithms to analyze past patterns and predict future market trends. These prediction results are stored on the server and provided upon request from the user's terminal.

[1660] The user terminal retrieves prediction data, which is the result of analysis, from the server in real time. The retrieved data is visually displayed as graphs and charts using libraries such as matplotlib. This display allows the user to intuitively grasp future market price movements. If a large price movement is predicted based on the prediction data, an alarm message will be displayed on the screen, and notifications can also be made by sound or vibration. This allows the user to take immediate action to respond to sudden market fluctuations.

[1661] Furthermore, this system includes an automated trading function. Based on conditions set by the user in advance, it analyzes predictive data and automatically executes trades when a specific trigger occurs. This function allows users to trade without missing the optimal trading timing, aiming to maximize profits.

[1662] For example, data collection and analysis can be performed using the following prompt statements:

[1663] "Collect historical market data from market data provision services and use a generated AI model to predict future market price movements."

[1664] Thus, the present invention provides a powerful tool for investors to make appropriate and rapid investment decisions by enabling a server and user terminal to cooperate in collecting, analyzing, displaying, issuing alarms, and automating trading based on market data.

[1665] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1666] Step 1:

[1667] The server collects historical market data from an external market data provider service. It retrieves data in JSON format using the requests library via an API (Application Programming Interface). The input is the URL of the API endpoint, and the output is market data in JSON format. In this step, the server performs the following specific actions:

[1668] Send a request to the API endpoint.

[1669] Market data is received as a response.

[1670] Save the received data in JSON format.

[1671] Step 2:

[1672] The server converts the acquired market data into a pandas dataframe and formats it. The input is market data in JSON format, and the output is a formatted dataframe. The specific data processing performed in this step is as follows:

[1673] Read JSON data and convert it to a pandas DataFrame.

[1674] Rename the columns in the dataframe as needed.

[1675] Format the time-series data to standardize the date and time format.

[1676] Step 3:

[1677] The server inputs the formatted data frame into a generating AI model to predict future market price movements. The input is the processed data frame, and the output is the predicted data. The data calculations performed in this step are as follows:

[1678] Extract features from a data frame.

[1679] The features are input into the generative AI model.

[1680] The generative AI model makes predictions and outputs them as predicted data.

[1681] Step 4:

[1682] The server holds the prediction data and provides it upon request from the user terminal. The input is the prediction data, and the output is the prediction data provided to the user terminal. In this step, the server performs the following actions:

[1683] Save the prediction data to the database.

[1684] It returns predictive data in response to requests from the user's terminal.

[1685] Step 5:

[1686] The user terminal retrieves predicted data, which is the analysis result, from the server and displays it visually. The input is predicted data from the server, and the output is information displayed visually in the form of graphs and charts. The specific actions performed in this step are as follows:

[1687] Send a request for prediction data to the server.

[1688] Analyze the prediction data received from the server.

[1689] Display the results as graphs or charts using the matplotlib library.

[1690] Step 6:

[1691] The user terminal issues an alert when a large price movement is predicted. The input is prediction data, and the output is an alert notification to the user. In this step, the user terminal performs the following specific actions:

[1692] Analyze the forecast data to see if significant price movements are predicted.

[1693] If a large price movement is predicted, an alert message will be displayed on the screen.

[1694] Notifications will be sent via voice or vibration as needed.

[1695] Step 7:

[1696] The user terminal executes automated trading based on user settings. Inputs include user settings and forecast data, while output is the actual execution of trades. The actions performed in this step are as follows:

[1697] Load user settings and check the trading conditions.

[1698] Analyze the prediction data and check if it meets the user-defined conditions.

[1699] If the conditions are met, the transaction will be executed automatically.

[1700] 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.

[1701] This invention relates to a system that collects historical market data, analyzes it using a generative AI model, predicts future market price movements, displays them visually, and issues warnings as needed, further incorporating an emotion engine that recognizes user emotions. This system consists of a server, a user terminal, and an emotion engine.

[1702] Server-based processing

[1703] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, it uses the requests library to retrieve data. The retrieved data is converted into a pandas dataframe and formatted. This formatted data is input into a generative AI model, which analyzes the data and predicts future market price movements. The prediction results are stored on the server as prediction data.

[1704] Processing by the user terminal

[1705] The user terminal retrieves prediction data, which is the result of analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs. This allows the user to intuitively grasp future market price movements.

[1706] Emergency alert issued

[1707] Based on the analysis of forecast data, if a significant price movement is predicted, the user terminal will issue an emergency alert. The alert will not only be displayed as a warning message on the screen, but can also be notified via voice and vibration. This allows users to respond immediately to sudden market fluctuations and minimize risk.

[1708] Automated trading function

[1709] This system also includes an automated trading function, which analyzes predictive data based on conditions set by the user and automatically executes trades when specific triggers occur. This function allows users to make optimal trades without missing opportunities and maximize profits.

[1710] Introducing an emotional engine

[1711] A distinctive feature of this invention is the addition of an emotion engine. The emotion engine is an element for recognizing and analyzing the user's emotions and is built into the user terminal. The emotion engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc.

[1712] Processing by the emotion engine

[1713] The emotion engine embedded in the user's terminal analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging them to trade cautiously. It can also adjust investment strategies according to the user's emotional state. This allows users to make better investment decisions that take their own emotions into account.

[1714] Specific example

[1715] For example, suppose the server collects JSON data in the following format:

[1716] json

[1717] [

[1718] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1719] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[1720] ...

[1721] ]

[1722] The server analyzes this data and can obtain predictive data from the generative AI model, such as:

[1723] json

[1724] [

[1725] {"time": "2023-10-01 11:00", "price": 110},

[1726] {"time": "2023-10-01 12:00", "price": 115},

[1727] ...

[1728] ]

[1729] The user terminal retrieves this predictive data and displays it visually as follows.

[1730] -------------

[1731] | Future Price Movement |

[1732] Time: 11:00, Price: 110

[1733] | Time: 12:00, Price: 115 |

[1734] -------------

[1735] If a significant price movement is predicted, an alert will be issued and users will be notified.

[1736] Emergency Alert: Large price movement expected!

[1737] If the emotion engine detects user anxiety, it can display additional messages such as the following:

[1738] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[1739] If the automated trading function is enabled, trades will be executed automatically based on predictive data.

[1740] Thus, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and emotion engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[1741] The following describes the processing flow.

[1742] Step 1:

[1743] Data acquisition [server]

[1744] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. For example, the requests library can be used to retrieve data as follows:

[1745] Python

[1746] response = requests.get("http: / / api.marketdata.com")

[1747] data = response.json()

[1748] Step 2:

[1749] Data formatting [server]

[1750] The server converts the retrieved data into a pandas DataFrame. This DataFrame is then modified as needed, with column names and data types adjusted to make it suitable for analysis.

[1751] Python

[1752] data_df = pd.DataFrame(data)

[1753] Step 3:

[1754] Initialization of the generative AI model [server]

[1755] The server initializes the AI ​​model. This model analyzes historical market data to predict future price movements.

[1756] Python

[1757] model = PredictiveModel()

[1758] Step 4:

[1759] Data analysis [server]

[1760] The server inputs the formatted data into an AI model for analysis. This analysis predicts future market price movements, and the results are saved as predictive data.

[1761] Python

[1762] prediction = model.predict(data_df)

[1763] Step 5:

[1764] Obtaining predictive data [Device]

[1765] The device sends a request to the server to obtain prediction data, which is the result of the analysis. When the user starts up the device, it receives the latest prediction data from the server in real time.

[1766] Python

[1767] prediction_data = server.analyze_data(server.collect_data("http: / / api.marketdata.com"))

[1768] Step 6:

[1769] Chart display [Terminal]

[1770] The device draws charts based on the acquired forecast data and displays them visually to the user. This allows the user to intuitively grasp future market price movements.

[1771] Python

[1772] plt.figure(figsize=(10, 5))

[1773] plt.plot(prediction_data['time'], prediction_data['price'])

[1774] plt.title("Future Price Movement")

[1775] plt.xlabel("Time")

[1776] plt.ylabel("Price")

[1777] plt.show()

[1778] Step 7:

[1779] Detection of large price movements [Terminal]

[1780] The device checks if the prediction data contains significant price movements. For example, it detects when the difference between the highest and lowest values ​​exceeds a certain threshold.

[1781] Python

[1782] if max(prediction_data['price']) - min(prediction_data['price']) > 50:

[1783] trigger_alert = True

[1784] else:

[1785] trigger_alert = False

[1786] Step 8:

[1787] Emergency alert issued [Terminal]

[1788] If a significant price movement is predicted, the device will issue an emergency alert to the user. A warning message will be displayed on the screen, and in some cases, notifications will also be made via sound or vibration.

[1789] Python

[1790] if trigger_alert:

[1791] print("\033[91m" + "Emergency Alert: Large price movement expected!" + "\033[0m")

[1792] Step 9:

[1793] Confirmation of automated trading settings [User]

[1794] The system checks if the user has set up the automated trading function, and if the setting is enabled, it automatically executes trades when certain conditions are met.

[1795] Python

[1796] if user_auto_trade_enabled and check_trade_conditions(prediction_data):

[1797] error_trade()

[1798] Step 10:

[1799] Emotion engine initialization [Terminal]

[1800] The device initializes the emotion engine and prepares to analyze the user's emotional state in real time. The emotion engine utilizes data from the camera, microphone, keyboard input, and other sources.

[1801] Python

[1802] emotion_engine = EmotionEngine()

[1803] emotion_engine.initialize()

[1804] Step 11:

[1805] Emotion analysis [terminal]

[1806] The device uses an emotion engine to analyze the user's emotions from their facial expressions, voice tone, and input patterns. Based on the analysis results, it adjusts notifications and alerts.

[1807] Python

[1808] user_emotion = emotion_engine.analyze()

[1809] Step 12:

[1810] Emotion-based notification adjustments [device]

[1811] The system adjusts the intensity and content of notifications and alerts based on the user's emotional state. For example, if a user is feeling anxious, the system will provide more detailed information to increase their sense of security.

[1812] Python

[1813] if user_emotion == "anxious":

[1814] display_message("We noticed you seem anxious. Would you like more detailed analysis before making a decision?")

[1815] Step 13:

[1816] Adjusting investment strategies based on emotions [Terminal]

[1817] Based on the analysis results of the emotion engine, investment strategies based on predictive data will be adjusted. If the emotional state is not calm, countermeasures will be taken, such as recommending low-risk trades.

[1818] Python

[1819] if user_emotion != "calm":

[1820] adjust_investment_strategy("low-risk")

[1821] In this way, the system's server collects and analyzes market data and provides predictive data to the user's terminal. The terminal also displays the data visually, and the emotion engine analyzes the user's emotions, providing appropriate notifications and adjusting investment strategies. This enables the user to grasp market conditions in real time and make quick and appropriate investment decisions.

[1822] (Example 2)

[1823] 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".

[1824] Traditional market forecasting systems analyze past market data and make future predictions, but this alone is insufficient to accurately support changes in user sentiment and rapid responses to emergencies. Furthermore, warnings to users may be delayed when significant market fluctuations are predicted, and automated trading functions and real-time information updates may not function effectively.

[1825] 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.

[1826] In this invention, the server includes means for collecting historical market data, means for analyzing historical market data using a generative AI model and predicting future market price movements, means for visually displaying the predicted future market price movements, means for issuing an alert when a large price movement is predicted, and means for analyzing the user's emotions using an emotion analysis engine and adjusting notifications and actions based on the results. This enables market forecasting that takes into account the user's emotional state and prompt alert issuance, as well as the provision of real-time updated market information and the effective operation of automated trading functions.

[1827] "Historical market data" refers to past trading information and price trends in financial markets, including stock prices, exchange rates, and commodity prices over a specific period.

[1828] A "generative AI model" refers to a computational model that uses artificial intelligence technology to learn from data and predict future price movements and patterns.

[1829] "Future market price movements" refer to price fluctuations and trends in future financial markets predicted based on current data.

[1830] "Visual display methods" refer to ways of displaying predicted market data in an easy-to-understand format for users, such as using graphs, charts, and dashboards.

[1831] "Means of issuing warnings" refers to methods of notifying or alerting users when significant market fluctuations are anticipated, and includes voice notifications, pop-up messages, and vibrations.

[1832] An "emotion analysis engine" refers to technology for detecting and analyzing a user's emotional state, and this includes systems that recognize emotions using data from cameras, microphones, keyboard input, and other sources.

[1833] "Means of adjusting notifications and actions" refers to methods of adjusting the information displayed and the content of warnings issued based on the user's emotional state obtained by the emotion analysis engine.

[1834] "Methods for automated trading" refers to systems that automatically execute trades based on predicted market data and according to pre-set conditions.

[1835] "Real-time updates" refers to methods of continuously acquiring the latest market data and forecast results and keeping them immediately accessible to users.

[1836] A "user terminal" refers to a device used by a user to view or manipulate information, and this includes personal computers, smartphones, tablets, and other similar devices.

[1837] This invention is a system that collects market data, analyzes it using a generative AI model, predicts future market price movements, visually displays the results, and issues warnings as needed. Furthermore, by combining it with an emotion analysis engine that recognizes user emotions, more advanced investment support becomes possible. This system consists of a server, a user terminal, and an emotion analysis engine.

[1838] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The data is retrieved using the requests library, converted into a pandas DataFrame, and formatted. The formatted data is then input into a generating AI model for analysis and prediction of future market price movements. These prediction results are stored on the server and provided to the user's terminal.

[1839] The user terminal retrieves forecast data from the server and displays it visually as charts and graphs using libraries such as matplotlib. This allows users to intuitively grasp future market price movements. Furthermore, if a large price movement is predicted based on the forecast data, the user terminal will issue an alert. The alert can be notified not only as a warning message on the screen, but also by sound and vibration. This allows users to respond immediately to sudden market fluctuations.

[1840] Furthermore, this system includes an automated trading function, which automatically executes trades when specific triggers occur based on conditions pre-set by the user. This function allows users to trade at the optimal time and maximize their profits.

[1841] A distinctive feature of this invention is the incorporation of an emotion analysis engine. The emotion analysis engine detects emotions from the user's facial expressions, voice tone, input patterns, etc., through the camera, microphone, keyboard input, etc. The emotion analysis engine, which is embedded in the user terminal, analyzes the user's emotions in real time and adjusts notifications and alerts based on the analysis results. For example, if the user is feeling anxious, the system can provide more detailed information or display a message urging the user to proceed with the transaction cautiously.

[1842] As a specific example, the data collected by the server is in the following format:

[1843] [

[1844] {"time": "2023-10-01 09:00", "open": 100, "close": 105, "high": 110, "low": 95},

[1845] {"time": "2023-10-01 10:00", "open": 105, "close": 108, "high": 112, "low": 103},

[1846] ...

[1847] ]

[1848] The analyzed prediction data is expressed as follows:

[1849] [

[1850] {"time": "2023-10-01 11:00", "price": 110},

[1851] {"time": "2023-10-01 12:00", "price": 115},

[1852] ...

[1853] ]

[1854] The following is an example of how a user terminal retrieves and visually displays this predictive data:

[1855] -------------

[1856] | Future Price Movement |

[1857] Time: 11:00, Price: 110

[1858] | Time: 12:00, Price: 115 |

[1859] -------------

[1860] The following warning will be displayed when a large price movement is expected:

[1861] Emergency Alert: Large price movement expected!

[1862] If the emotion analysis engine detects user anxiety, it will display a message like the following:

[1863] We noticed you seem anxious. Would you like more detailed analysis before making a decision?

[1864] Examples of prompt statements that can be used include the following:

[1865] "Provide a detailed prediction for the market prices based on the following past data: {past_data}. Consider factors such as {factors} and provide predictions for the next 24 hours."

[1866] As described above, the present invention provides a powerful tool for users to grasp market conditions in real time and make quick and appropriate investment decisions by having a server, user terminal, and sentiment analysis engine cooperate to collect, analyze, display market data, issue alarms, perform automated trading, and respond to emotions.

[1867] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1868] Step 1:

[1869] The server collects market data.

[1870] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The input is the API endpoint, and the output is the retrieved market data in JSON format. Specifically, the server uses the requests library to retrieve data from the API endpoint.

[1871] Step 2:

[1872] The server formats the data it has collected.

[1873] The acquired market data is converted into a pandas DataFrame and formatted. The input is the market data acquired in the previous step in JSON format, and the output is a formatted pandas DataFrame. Specifically, the server uses the pandas library to convert the JSON data into a DataFrame format.

[1874] Step 3:

[1875] The server analyzes the data and predicts future market price movements.

[1876] The system inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted pandas dataframe, and the output is data representing predicted market price movements. Specifically, the server uses a generative AI model in TensorFlow or PyTorch to perform data analysis and prediction.

[1877] Step 4:

[1878] The server stores the prediction data and provides it to the user's terminal.

[1879] The generated prediction data is stored on the server and provided as needed upon request from the user's terminal. The input is the prediction data, and the output is the stored data and the data provided to the user's terminal. Specifically, the server stores the data in the file system and provides the data to the user's terminal via an API.

[1880] Step 5:

[1881] The user's terminal acquires predictive data and displays it visually.

[1882] The user terminal sends a request to the server to retrieve prediction data. The retrieved data is then displayed in charts or graphs using visualization libraries such as matplotlib. The input is the prediction data retrieved from the server, and the output is the displayed chart or graph. Specifically, the user terminal sends an HTTP request, receives the data, and then generates the graph.

[1883] Step 6:

[1884] The user terminal will issue an alert if a large price movement is predicted.

[1885] The system analyzes forecast data and issues an alert if a large price movement is predicted. The input is forecast data, and the output is an alert message, voice notification, and vibration notification. Specifically, the user terminal calculates the maximum and minimum values ​​of the data, and displays and issues an alert if there is a large difference.

[1886] Step 7:

[1887] The user's terminal performs automated trading.

[1888] Buying and selling are performed automatically based on conditions set by the user. The inputs are the set conditions and predicted data, and the output is the result of the executed trades. Specifically, the user terminal checks the set values ​​and executes trades via the API if the conditions are met.

[1889] Step 8:

[1890] The emotion analysis engine analyzes the user's emotions and adjusts notifications and actions accordingly.

[1891] The system analyzes user emotions in real time using camera, microphone, and keyboard input, and adjusts notifications and alerts based on the results. The input is user emotion data, and the output is the adjusted notifications and actions. Specifically, the emotion analysis engine uses an emotion recognition algorithm to analyze the user's emotions and dynamically changes the system's response based on the results.

[1892] (Application Example 2)

[1893] 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".

[1894] There is a need to improve the accuracy of market price movement predictions and provide users with information to make more informed investment decisions. However, current systems have limitations in providing investment advice that takes emotions into account and in notifying users of sudden market changes in a timely manner. In particular, a lack of safe and efficient ways for users to obtain market information while in autonomous vehicles is a challenge.

[1895] 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.

[1896] In this invention, the server includes means for collecting historical data, means for analyzing historical data using a generative AI model to predict future price movements, and means for visually displaying the predicted future price movements. This enables means for issuing an alarm when a large price movement is predicted, and means for recognizing and analyzing user emotions to adjust notifications and alerts.

[1897] "Historical data" refers to various numerical data and information collected prior to the present. It is fundamental data for understanding market trends and predicting future developments.

[1898] A "generative AI model" refers to an artificial intelligence algorithm that learns patterns from large amounts of data to make new predictions and classifications. It is a machine learning model trained for a specific purpose.

[1899] "Future price movements" refers to predictions of fluctuations in the price or value of a market or a specific object at a future point in time.

[1900] "Visual display methods" refer to ways of making data and information visible in visual formats such as graphs and charts. These are display methods designed to make information easy for users to understand intuitively.

[1901] "Means of issuing warnings" refers to a system for notifying users of warnings when large price movements or anomalies are detected. These warnings are issued through methods such as voice, vibration, and screen displays.

[1902] "Means of recognizing and analyzing user emotions" refers to technologies that use devices such as cameras and microphones to detect emotions from a user's facial expressions and voice, and then analyze that information to understand the user's emotional state.

[1903] "Methods for automated trading" refer to systems that automatically execute buy and sell orders based on set conditions and predictive data. These functions aim to minimize user intervention and enable efficient trading.

[1904] "Real-time" means that data and information are processed and updated instantly. It refers to a state where the latest information is always provided without any time lag.

[1905] This invention relates to a system for predicting future market price movements in autonomous vehicles and providing investment support to users. This system consists of a server, a user terminal, and an emotion engine.

[1906] Server-based processing

[1907] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The retrieved data is converted into a pandas dataframe and formatted. The formatted data is input into a generative AI model, which performs data analysis and predicts future market price movements. The prediction results are stored on the server as prediction data.

[1908] Specifically, the server performs the following processes:

[1909] 1. Collect market data: Collect historical market data and convert it into a pandas dataframe.

[1910] 2. Data Analysis: The collected data is input into a generating AI model for analysis, and future market price movements are predicted.

[1911] 3. Saving prediction data: The analyzed prediction data is saved to the server.

[1912] Processing by the user terminal

[1913] The user terminal retrieves prediction data, which is the result of the analysis, from the server. When the user starts up the terminal, it sends a request to the server and receives the latest prediction data in real time. This prediction data is displayed visually in a user-friendly format as charts and graphs.

[1914] Specifically, the user terminal performs the following actions:

[1915] 1. Obtaining forecast data: Request and obtain the latest forecast data from the server.

[1916] 2. Visual display of data: The acquired data will be displayed to the user in the form of graphs and charts, allowing for intuitive understanding.

[1917] 3. Emotional Response: The emotion engine analyzes the user's emotions and, if they are feeling anxious, displays additional detailed information and advice.

[1918] Processing by the emotion engine

[1919] The emotion engine detects emotions from the user's facial expressions, voice tone, and input patterns through the camera, microphone, and keyboard input. If the user is feeling anxious, the system will provide more detailed information or display messages urging them to proceed cautiously. This allows users to make better investment decisions by taking their own emotions into consideration.

[1920] System Features

[1921] This system is particularly useful when users conduct investment activities within autonomous vehicles and offers the following advantages:

[1922] 1. Immediately notify users of sudden market fluctuations and prompt them to take action.

[1923] 2. Analyze the user's emotions and provide appropriate advice regarding anxiety and fear.

[1924] 3. Automated trading is executed based on predictive data to ensure optimal trading timing and avoid missing opportunities.

[1925] As a concrete example, imagine a scenario where, while traveling in an autonomous vehicle, a user can anticipate sudden market fluctuations based on predictive data and receive advice from an emotional engine to "avoid intuitive trading."

[1926] Examples of prompts to input into a generative AI model:

[1927] Based on historical market data, predict future market price movements. If the user expresses concerns, display additional support messages. Make predictions based on the following data and output the results in JSON format.

[1928] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1929] Step 1:

[1930] The server sends a request to the API endpoint of the market data provision service to retrieve historical market data. The requests library is used for this data retrieval. The input is the API endpoint URL, and the output is the retrieved raw data.

[1931] Step 2:

[1932] The server retrieves data and converts it into a pandas DataFrame, then formats it. The input is raw data, and the output is a formatted pandas DataFrame. The data converted into a DataFrame is in a format suitable for analysis.

[1933] Step 3:

[1934] The server inputs formatted data into a generative AI model to predict future market price movements. The input is a formatted data frame, and the output is predicted data. The generative AI model analyzes future market trends based on the input data.

[1935] Step 4:

[1936] The server stores the prediction data. The input is the prediction data from the generative AI model, and the output is the stored prediction data. The stored prediction data is later retrieved from the user's terminal.

[1937] Step 5:

[1938] The user terminal sends a request to the server and receives the latest forecast data in real time. The input is the request to the server, and the output is the forecast data. The user terminal receives this data and uses it in the next step.

[1939] Step 6:

[1940] The system visually displays the forecast data received by the user's terminal in a user-friendly format as graphs and charts. The input is forecast data, and the output is the visually displayed data. This allows users to intuitively grasp future market trends.

[1941] Step 7:

[1942] The emotion engine analyzes the user's emotions using input from the camera and microphone. The input is the user's facial expressions and voice data, and the output is the analyzed emotion data. The emotion engine detects whether the user is feeling anxious.

[1943] Step 8:

[1944] The user's device adjusts notifications and alerts based on the analysis results of the emotion engine. The input is emotion data, and the output is adjusted notifications and alerts. If the user is feeling anxious, more detailed information and advice will be displayed.

[1945] Step 9:

[1946] The user terminal automatically executes trades based on predicted future price movements. Inputs are predicted data and pre-set trading conditions, while output is the executed trades. This allows the user to make optimal trades in response to market trends.

[1947] Step 10:

[1948] The user terminal continuously updates market price movements in real time, periodically sending requests to the server to receive new forecast data. The input is a request to the server, and the output is the latest forecast data. This allows users to always make investment decisions based on the most up-to-date information.

[1949] 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.

[1950] 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.

[1951] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1952] 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.

[1953] 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.

[1954] 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.

[1955] 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.

[1956] 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.

[1957] 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."

[1958] 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.

[1959] 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.

[1960] 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.

[1961] 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.

[1962] 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.

[1963] 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.

[1964] 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.

[1965] 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.

[1966] 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.

[1967] 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.

[1968] 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.

[1969] 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 as being incorporated by reference.

[1970] The following is further disclosed regarding the embodiments described above.

[1971] (Claim 1)

[1972] Means of collecting historical market data,

[1973] A method for analyzing past market data using a generative AI model to predict future market price movements,

[1974] A means of visually displaying predicted future market price movements,

[1975] A means of issuing a warning when a large price movement is predicted,

[1976] A system that includes this.

[1977] (Claim 2)

[1978] The system according to claim 1, further comprising means for performing automated trading based on predicted future market price movements.

[1979] (Claim 3)

[1980] The system according to claim 1, further comprising means for updating predicted future market price movements in real time.

[1981] "Example 1"

[1982] (Claim 1)

[1983] Methods for collecting historical market data from external market data provision services,

[1984] A means of formatting the collected market data and converting it into a data frame,

[1985] A method for inputting formatted data into a generating AI model to predict future market price movements,

[1986] A means of storing and keeping predictive data on a server,

[1987] A means of sending predictive data to the user terminal,

[1988] A means of visually displaying predicted future market price movements,

[1989] A means of issuing a warning when a large price movement is predicted,

[1990] A system that includes this.

[1991] (Claim 2)

[1992] The system according to claim 1, further comprising means for performing automated trading based on predicted future market price movements.

[1993] (Claim 3)

[1994] The system according to claim 1, further comprising means for updating predicted future market price movements in real time.

[1995] "Application Example 1"

[1996] (Claim 1)

[1997] Means of collecting historical market data,

[1998] A method for analyzing past market data using a generative AI model to predict future market price movements,

[1999] A means of visually displaying predicted future market price movements,

[2000] A means of issuing a warning when a large price movement is predicted,

[2001] A means of executing automated trading based on user settings,

[2002] A system that includes this.

[2003] (Claim 2)

[2004] The system according to claim 1, further comprising means for updating predicted future market price movements in real time.

[2005] (Claim 3)

[2006] The system according to claim 1, further comprising means for performing automated trading when certain conditions are met, based on predicted future market price movements.

[2007] "Example 2 of combining an emotion engine"

[2008] (Claim 1)

[2009] Means of collecting historical market data,

[2010] A method for analyzing past market data using a generative AI model to predict future market price movements,

[2011] A means of visually displaying predicted future market price movements,

[2012] A means of issuing a warning when a large price movement is predicted,

[2013] A means of analyzing a user's emotions using an emotion analysis engine and adjusting notifications and actions based on the results,

[2014] A system that includes this.

[2015] (Claim 2)

[2016] The system according to claim 1, further comprising means for performing automated trading based on predicted future market price movements.

[2017] (Claim 3)

[2018] The system according to claim 1, further comprising means for updating predicted future market price movements in real time.

[2019] (Claim 4)

[2020] The system according to claim 1, further comprising means for storing data collected using a user terminal as predictive data on a server and providing the predictive data to the user terminal.

[2021] "Application example 2 when combining with an emotional engine"

[2022] (Claim 1)

[2023] Means of collecting past data,

[2024] A method for analyzing past data using a generative AI model to predict future price movements,

[2025] A means of visually displaying predicted future price movements,

[2026] A means of issuing a warning when a large price movement is predicted,

[2027] A means of recognizing and analyzing user emotions and adjusting notifications and alerts accordingly,

[2028] A system that includes this.

[2029] (Claim 2)

[2030] The system according to claim 1, further comprising means for performing automated trading based on predicted future price movements.

[2031] (Claim 3)

[2032] The system according to claim 1, further comprising means for updating predicted future price movements in real time. [Explanation of Symbols]

[2033] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting historical market data, A method for analyzing past market data using a generative AI model to predict future market price movements, A means of visually displaying predicted future market price movements, A means of issuing a warning when a large price movement is predicted, A system that includes this.

2. The system according to claim 1, further comprising means for performing automated trading based on predicted future market price movements.

3. The system according to claim 1, further comprising means for updating predicted future market price movements in real time.

Images