system

Abstract

We provide the system. [Solution] A system that includes means for comparing multiple investment methods and proposing the optimal investment method to the user, means for AI-driven investment guidance based on the experience and intellect of legendary investors, and means for supporting the user's asset building.

Description

[Technical Field]

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

[0002] Patent Document 1 discloses a persona chatbot control method executed by at least one processor, the method comprising the steps of: receiving a user utterance; adding the user utterance to a prompt including an instruction associated with a description relating to a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance responding to the user utterance. [Prior Art Document] [Patent Document]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2022-180282 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] There are a wide variety of investment methods, and it is difficult for an individual investor to find an optimal investment method suited to themselves. [Means for Solving the Problem]

[0005] A system has been developed that includes means for comparing a plurality of investment methods and proposing an optimal investment method for a user, investment guidance means based on artificial intelligence built on the experience and intellect of legendary investors, and means for supporting the asset building of a user. This system enables individual investors to easily find the investment method optimal for themselves. [Brief Description of the Drawings]

[0006] [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 Embodiment 1 of Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2 of Embodiment 2. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2. [Figure 15] This is a sequence diagram showing the processing flow of the data processing system in Embodiment 3 of Example 3. [Figure 16] This is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3. [Figure 17] It is a sequence diagram showing the processing flow of the data processing system in Example 1 of Form Example 1 when an emotion engine is combined. [Figure 18] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] It is a sequence diagram showing the processing flow of the data processing system in Example 2 of Form Example 2 when an emotion engine is combined. [Figure 20] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] It is a sequence diagram showing the processing flow of the data processing system in Example 3 of Form Example 3 when an emotion engine is combined. [Figure 22] It is a sequence diagram showing the processing flow of the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. [Figure 23] It is a sequence diagram showing the processing flow of the data processing system in another embodiment.

Mode for Carrying Out the Invention

[0007] Hereinafter, an example of an embodiment of a system pertaining to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, terms used in the following description will be explained.

[0009] In the following embodiments, a marked processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of a plurality of arithmetic devices. Further, the processor may be one type of arithmetic device or a combination of a plurality of types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a marked RAM (Random Access Memory) is a memory for temporarily storing information, and is used as a work memory by the processor.

[0011] In the following embodiments, a marked storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a marked communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0013] 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."

[0014] [First Embodiment]

[0015] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0027] "Example of form 1"

[0028] One embodiment of the present invention is an investment guidance AI system. This system has means for comparing multiple investment methods and proposing the optimal investment method to the user. Specifically, it compares investment methods such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA, and proposes the optimal investment method based on information such as the user's investment objectives and risk tolerance.

[0029] "Example of form 2"

[0030] Furthermore, one embodiment of this invention is an AI-powered investment guidance system based on the experience and intellect of legendary investors. This AI uses algorithms based on the investors' experience and intellect to support the user's asset building. Specifically, the AI ​​analyzes the user's investment history and market trends and proposes the optimal investment strategy.

[0031] "Example of form 3"

[0032] Furthermore, one embodiment of the present invention involves means of supporting the user's asset building. Specifically, the AI ​​periodically analyzes the user's asset status and adjusts investment strategies or suggests new investment opportunities. For example, if the user's assets reach a certain target, the AI ​​notifies the user of this information and assists in setting new investment targets.

[0033] The following describes the processing flow for each example of the form.

[0034] "Example of form 1"

[0035] Step 1: The user enters information such as their investment objectives and risk tolerance into the system.

[0036] Step 2: The system compares multiple investment methods (such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA).

[0037] Step 3: The system proposes the optimal investment method based on the user's information.

[0038] "Example of form 2"

[0039] Step 1: The AI ​​uses algorithms based on the experience and intellect of legendary investors to analyze the user's investment history and market trends.

[0040] Step 2: The AI ​​proposes the optimal investment strategy based on the analysis results.

[0041] "Example of form 3"

[0042] Step 1: The AI ​​periodically analyzes the user's asset status.

[0043] Step 2: The AI ​​adjusts investment strategies and suggests new investment opportunities.

[0044] Step 3: When the AI ​​reaches a certain target for the user's assets, it notifies the user of this information and helps them set new investment goals.

[0045] (Example 1)

[0046] Next, we will describe Example 1 of Form 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."

[0047] In today's financial markets, users are required to make the optimal choices from a diverse range of financial products, which necessitates specialized knowledge and analysis. In particular, selecting the most suitable financial product based on a user's financial goals and risk tolerance is challenging, and there is a need for a system that can provide efficient and accurate recommendations.

[0048] 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.

[0049] In this invention, the server includes means for comparing multiple financial products and suggesting the most suitable financial product to the user, means for data analysis using historical market data and machine learning algorithms, and means for supporting the user's financial goals. This enables the user to efficiently select the most suitable financial product based on their own profile.

[0050] "Financial products" refer to products that are the subject of investment or asset management, and include individual defined contribution pension plans, small-amount investment tax exemption schemes, installment investment schemes, and junior investment schemes.

[0051] "User" refers to an individual or corporation that selects financial products and engages in investment or asset management.

[0052] "Means of proposing the optimal financial product" refers to the methods and processes for comparing multiple financial products based on the user's financial goals and risk tolerance, and selecting the most suitable product.

[0053] "Data analysis methods" refer to methods and processes for analyzing data using machine learning algorithms based on past market data and user input information, in order to provide users with useful information.

[0054] "Means to support financial goals" refers to methods and processes that provide the information and suggestions necessary to achieve the financial goals set by the user, and that support asset building.

[0055] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze user profiles and market data to propose the most suitable financial products.

[0056] As an embodiment for carrying out this invention, the investment guidance AI system is constructed as follows.

[0057] The server generates a program for an investment guidance AI system. This program is designed to suggest the most suitable financial products to the user. The server uses programming languages ​​such as Python and R to analyze historical market data and user input information. This allows for data analysis based on the user's risk tolerance and financial goals.

[0058] The server uses a generative AI model to create a user profile. This profile includes information such as the user's age, investment objectives, risk tolerance, and investment period. Based on this information, the server compares multiple financial products and selects the most suitable one.

[0059] The terminal provides an interface for users to access the system and enter necessary information. Users can enter prompt messages through the terminal, such as the following:

[0060] "I'm in my 40s and want to increase my assets while minimizing risk. Could you please tell me which investment method is best?"

[0061] "I want to save money for my child's college education. What investment method would be suitable?"

[0062] Upon receiving these prompts, the server suggests the most suitable financial products based on the user's profile. This suggestion is then communicated to the user via their terminal. This allows the user to efficiently make investments that align with their financial goals.

[0063] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0064] Step 1:

[0065] Users access the system through their terminals and enter information such as their investment objectives, age, risk tolerance, and investment period. This information is sent to the server and serves as the basis for creating the user's profile.

[0066] Step 2:

[0067] The server creates a profile based on the user information it receives. Using programming languages ​​such as Python or R, the server analyzes the input data and quantifies the user's risk tolerance and financial targets. This profile is then used for subsequent data analysis.

[0068] Step 3:

[0069] The server uses a generative AI model to analyze historical market data and user profiles. The server applies machine learning algorithms to perform data analysis to identify the most suitable financial products for the user. During this process, the risk and return of each financial product are evaluated.

[0070] Step 4:

[0071] Based on the analysis results, the server suggests the most suitable financial products to the user. These suggestions are then communicated to the user via their terminal. Specifically, if the user has a low risk tolerance, financial products that offer stable returns may be suggested.

[0072] Step 5:

[0073] Users review the suggested financial products on their devices and make investment decisions as needed. Based on these suggestions, users can make investment decisions that align with their financial goals.

[0074] (Application Example 1)

[0075] Next, we will describe Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server," and the smart device 14 will be referred to as a "terminal."

[0076] In today's investment environment, it is difficult for individual investors to select the optimal investment method that suits their investment objectives and risk tolerance. Furthermore, there is a lack of support for investors to effectively compare the diverse range of available investment options and make the best choices. Therefore, there is a need for a system that enables investors to build wealth efficiently and effectively.

[0077] 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.

[0078] In this invention, the server includes means for comparing multiple investment options and suggesting the optimal investment option to the user; means for analyzing past investment data and suggesting the optimal investment option based on the user's investment history and spending patterns; means for collecting the user's financial data and formatting and analyzing the data; means for using a machine learning model to predict the optimal investment option based on the user's risk tolerance and investment objectives; and means for providing a user interface that allows the user to compare and select investment plans. This makes it possible for the user to easily select the optimal investment option according to their own investment objectives and risk tolerance.

[0079] "Investment methods" is a general term for financial products and systems used to increase assets, and includes individual defined contribution pension plans and small-amount investment tax exemption schemes.

[0080] "User" refers to an individual or legal entity that uses the system to select and manage investments.

[0081] "Investment history" refers to a record of past investment activities, including information such as investment amount, investment destination, and investment period.

[0082] "Spending patterns" indicate the user's spending habits and show how much money they spend on what items.

[0083] "Financial data" refers to financial information such as a user's assets, liabilities, income, and expenses, and is the basic data necessary for investment decisions.

[0084] A "machine learning model" is a computational model that uses algorithms to learn patterns from data and perform predictions and classifications.

[0085] "Risk tolerance" is an indicator that shows the range of risk an investor can tolerate, and it represents an individual investor's attitude and ability to handle risk.

[0086] "Investment objectives" refer to the specific goals and intentions when making an investment, and include increasing assets, diversifying risk, and preparing for future funding needs.

[0087] A "user interface" refers to the screens and operating methods that allow users to interact with a system, and is a means of inputting information and displaying results.

[0088] To implement this invention, it is necessary to build a system in which a server plays a central role. The server will be programmed using Python, and the backend will be built using the Flask framework. Pandas and Scikit-learn will be used for data analysis. This will enable the server to collect users' financial data and to format and analyze the data.

[0089] Specifically, the server analyzes the user's investment history and spending patterns, and uses machine learning models to predict the optimal investment strategy based on the user's risk tolerance and investment objectives. This allows users to easily select the most suitable investment strategy according to their own investment objectives and risk tolerance.

[0090] The terminal provides a user interface, allowing users to compare and select investment plans. Users can receive information from the server via their smartphone or computer and make investment choices.

[0091] For example, if a user enters "I want to invest 50,000 yen per month," the server analyzes past spending data and assesses their risk tolerance. As a result, it can suggest that Tsumitate NISA (a type of tax-advantaged investment account) is the optimal option.

[0092] An example of a prompt to input into the generating AI model is: "The user's monthly investment limit is 50,000 yen, and their risk tolerance is moderate. Please suggest the optimal investment method."

[0093] In this way, by coordinating servers, terminals, and users, an efficient and effective investment support system can be realized.

[0094] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0095] Step 1:

[0096] The server receives input data from the user. This input data includes the user's available investment amount, risk tolerance, and investment objectives. Based on this data, the server understands the user's investment needs.

[0097] Step 2:

[0098] The server uses Pandas to retrieve users' past investment history and spending patterns from a database, then formats and analyzes the data. Input includes past transaction history and spending records, which are used to extract trends in the user's investment behavior. The output provides characteristics of the user's investment behavior.

[0099] Step 3:

[0100] The server uses Scikit-learn to run a machine learning model and predict the optimal investment strategy based on the user's risk tolerance and investment objectives. The input consists of formatted investment history data and the user's risk tolerance, which are used to calculate the optimal investment strategy. The output is a list of recommended investment strategies.

[0101] Step 4:

[0102] The server generates prompt messages using a generative AI model. The input includes the user's investment needs and predicted investment methods, and the server creates prompt messages based on this information. The output is a prompt message to be presented to the user.

[0103] Step 5:

[0104] The terminal displays prompt messages received from the server and recommended investment options to the user. The user can review the information presented through the terminal and make an investment choice.

[0105] Step 6:

[0106] The user selects an investment option presented through the terminal and executes the investment as needed. The input is recommended information from the server, which the user uses to make investment decisions. The output is the selected investment option.

[0107] In this way, servers, terminals, and users work together to achieve efficient and effective investment support.

[0108] (Example 2)

[0109] Next, we will describe Example 2 of Form Example 2. 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".

[0110] Conventional investment support systems have been unable to fully utilize users' investment history and market trends, making it difficult to propose optimal investment strategies. Furthermore, they have not been able to use algorithms that leverage the experience of legendary investors, thus failing to effectively support users' asset building.

[0111] 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.

[0112] In this invention, the server includes means for receiving investment history entered by the user, means for collecting market data, and means for analyzing the collected data and generating an optimal investment strategy. This makes it possible to propose an optimal investment strategy based on the user's investment history and market trends.

[0113] "A means of receiving user-entered investment history" refers to a function that allows users to input records of their past investment activities into the system and retrieve that information.

[0114] "Means for collecting market data" refers to a function that obtains information about financial markets from external information services and makes it available within the system.

[0115] "A means of analyzing collected data and generating the optimal investment strategy" refers to a function that analyzes the user's acquired investment history and market data to calculate and propose the most suitable investment method for the user.

[0116] "A method that uses algorithms based on the experience and knowledge of legendary investors" refers to a function that uses computational methods built on the past success stories and insights of prominent investors to formulate investment strategies.

[0117] "Means of supporting users' asset building" refers to functions that provide advice and strategies for users to efficiently increase their assets and support their asset management.

[0118] To implement this invention, it is first necessary to generate a program on the server that receives investment history from users. This program has the function of receiving investment history entered by the user through a dedicated terminal or web application. Users can enter information such as past stock purchase and sale history and investment amount.

[0119] Next, the server collects market data. This data collection utilizes data from financial information services. Specifically, it obtains market data such as stock indices, exchange rates, and economic indicators from services like Yahoo Finance and Bloomberg.

[0120] The server uses machine learning libraries such as Python's Pandas library and Scikit-learn to analyze the user's investment history and market data. This makes it possible to identify past investment patterns and compare them with current market trends.

[0121] Based on the analysis results, the server uses a generative AI model to generate the optimal investment strategy. This generated strategy is designed to maximize returns while minimizing risk.

[0122] Finally, the server proposes the generated investment strategy to the user. The user can review the proposed strategy and make adjustments as needed.

[0123] As a concrete example, a user might enter a prompt message such as, "Based on my investment history over the past five years, please suggest a future investment strategy." Upon receiving this prompt, the server analyzes the user's investment history and market data, generates a specific investment strategy such as, "You should focus on technology stocks for the next six months," and proposes it to the user.

[0124] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0125] Step 1:

[0126] The user enters their investment history.

[0127] Users input their past investment history through a dedicated terminal or web application. This data includes stock purchase and sale history, investment amounts, and other information. This input data is sent to a server and stored in a database.

[0128] Step 2:

[0129] The server collects market data.

[0130] The server collects market data from financial information services. Specifically, it obtains data such as stock indices, exchange rates, and economic indicators via APIs. This data is updated in real time and stored in a database on the server.

[0131] Step 3:

[0132] The server analyzes the data.

[0133] The server uses the Python Pandas library to analyze the user's investment history and collected market data. The input data consists of the user's investment history and market data. Based on this data, the server identifies past investment patterns and compares them to current market trends. The analysis results are used in the next step.

[0134] Step 4:

[0135] The server generates the investment strategy.

[0136] The server uses a generative AI model to generate the optimal investment strategy based on the analysis results. The analysis results are used as input. The server calculates a strategy to maximize returns while minimizing risk and creates specific investment proposals.

[0137] Step 5:

[0138] The server proposes investment strategies to the user.

[0139] The server notifies the user of the generated investment strategy. The specific investment strategy is sent to the user's terminal as output. The user can review the proposed strategy and make adjustments as needed.

[0140] (Application Example 2)

[0141] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0142] In today's investment environment, it is difficult for individual investors to formulate optimal investment strategies based on vast amounts of information. Furthermore, there is a lack of means to receive real-time advice based on investors' experience and knowledge. Therefore, there is a need for support systems that enable investors to build wealth efficiently and effectively.

[0143] 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.

[0144] This invention includes a server that compares multiple investment methods and proposes the optimal investment method to the user, an artificial intelligence-based investment support method based on the experience and knowledge of legendary investors, and a method that analyzes the user's investment history and market trends and proposes the optimal investment strategy in real time. This enables the user to efficiently develop an investment strategy.

[0145] An "investment method" refers to the specific methods and strategies used to increase one's assets.

[0146] A "user" refers to an individual or legal entity that uses this system to conduct investment activities.

[0147] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and perform learning and reasoning.

[0148] "Investment support measures" refer to support functions provided to help users make optimal investment decisions.

[0149] "Investment history" refers to a record of the user's past investment activities.

[0150] "Market trends" refer to price fluctuations and trends in financial markets.

[0151] "Real-time" refers to information being processed instantly the moment it is generated.

[0152] An "investment strategy" is a set of action plans designed to achieve specific investment objectives.

[0153] A "smartphone" is a portable device that, in addition to the functions of a mobile phone, possesses multiple functions similar to those of a computer.

[0154] An "application" is a software program designed to provide a specific function or service.

[0155] The system for implementing this invention consists of a server and a user's terminal (smartphone). The server runs a generative AI model built using Python and calculates investment strategies using TENSORFLOW®. The server provides an API using Flask and accepts requests from the user's terminal. SQLite is used as the database to manage the user's investment history and market trend data.

[0156] The user's device communicates with a server via a dedicated application, allowing them to receive real-time investment advice. This application sends the user's investment history to the server and displays the investment strategies received from the server.

[0157] For example, if a user has previously invested heavily in technology-related assets, the server will analyze market trends in the technology sector and propose future investment strategies. Based on these suggestions, the user can then decide on their next investment actions.

[0158] An example of a prompt message is: "Based on the user's past investment history, please suggest the optimal investment strategy considering current market trends."

[0159] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0160] Step 1:

[0161] The user's device collects investment history data as input. This data includes past investment amounts, investment destinations, and investment periods. The collected data is sent to the server.

[0162] Step 2:

[0163] The server receives the investment history data as input and stores it in a database. Next, it preprocesses the data and converts it into a format suitable for the generative AI model. This preprocessing includes data normalization and imputation of missing values.

[0164] Step 3:

[0165] The server inputs pre-processed investment history data and market trend data into a generating AI model. The model analyzes the data using TensorFlow and outputs the optimal investment strategy. This analysis includes analysis of past market trends and risk assessment.

[0166] Step 4:

[0167] The server sends the investment strategy generated by the AI ​​model to the user's terminal. This investment strategy includes recommended investment targets, investment amounts, and risk assessments.

[0168] Step 5:

[0169] The user's device displays the investment strategy received from the server. Based on this information, the user can decide on their next investment action. Specifically, the application visually displays the investment strategy to make it easy for the user to understand.

[0170] (Example 3)

[0171] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0172] Conventional asset building support systems have struggled to effectively utilize users' financial information and propose optimal investment strategies tailored to their individual asset situations. Furthermore, they were unable to evaluate users' progress toward asset goals in real time and adjust investment strategies at appropriate times.

[0173] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0174] In this invention, the server includes means for collecting and storing the user's financial information in a database, means for preprocessing the collected financial information and converting it into an analyzable format, and means for analyzing the user's asset status using a generative AI model and predicting future asset trends. This makes it possible to propose an optimal investment strategy tailored to the user's individual asset situation.

[0175] "User" refers to an individual or legal entity that provides financial information and utilizes the asset building support system.

[0176] "Financial information" refers to data necessary to understand a user's asset status, such as their account balance, investment portfolio details, and transaction history.

[0177] A "database" refers to an information management system that stores collected financial information and makes it accessible as needed.

[0178] "Preprocessing" refers to processes such as data cleaning and normalization performed to convert collected financial information into an analyzable format.

[0179] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to analyze a user's asset situation and predict future asset trends.

[0180] "Asset status" refers to information that shows the current state and composition of a user's assets.

[0181] An "investment strategy" refers to specific investment policies and action plans proposed to optimize a user's asset building.

[0182] To implement this invention, a server must first collect the user's financial information and store it in a database. The server retrieves data such as account balances, investment portfolio details, and transaction history from financial institutions via an API. This data is stored in the database for later analysis.

[0183] Next, the server preprocesses the collected financial information. Specifically, it cleans and normalizes the data and imputes missing values. This process transforms the data into a format suitable for analysis by generative AI models. Data analysis libraries such as "Pandas" and "NumPy" are sometimes used for preprocessing.

[0184] Subsequently, the server analyzes the user's asset status using a generative AI model. This AI model is built using machine learning frameworks such as "TensorFlow" and "PyTorch," and predicts future asset trends based on the user's past data. The AI ​​model evaluates how well the user's assets are progressing towards their set goals and proposes the optimal investment strategy.

[0185] For example, if a user sets a goal of "doubling their assets within five years," the server will periodically collect asset data and analyze it using an AI model. The AI ​​model may suggest a shift to a lower-risk investment strategy once the user's assets reach 80% of their goal. This suggestion may include recommendations for specific investment targets and amounts.

[0186] An example of a prompt to be input to the generating AI model is, "Please suggest the next steps once the user's assets reach their target." This prompt prompts the AI ​​to generate specific advice to help the user set new investment goals. The specific processing flow in Example 3 is explained using Figure 15.

[0187] Step 1:

[0188] The server collects users' financial information. As input, it uses the user's authentication credentials to access financial institutions' APIs and retrieve data such as account balances, investment portfolio details, and transaction history. As output, it stores the retrieved data in a database. Specifically, the server periodically executes scheduled jobs to collect the latest financial information.

[0189] Step 2:

[0190] The server preprocesses the collected financial information. It uses raw data stored in a database as input. The output is data converted into an analyzable format. Specific data processing involves cleaning the data, imputing missing values, and normalizing the data as needed. This makes the data suitable for analysis by AI models.

[0191] Step 3:

[0192] The server analyzes the user's asset status using a generative AI model. Pre-processed data is supplied to the AI ​​model as input. The output is a prediction of the user's asset trends. Specifically, the AI ​​model uses machine learning algorithms to predict future asset trends based on past data. This prediction shows how well the user's assets are progressing towards their goals.

[0193] Step 4:

[0194] The server proposes the optimal investment strategy to the user based on the analysis results. It uses the prediction results of an AI model as input and generates specific investment strategy suggestions as output. Specifically, the server selects investment targets with reduced risk and presents investment opportunities in emerging markets, depending on the user's risk tolerance and investment goals.

[0195] Step 5:

[0196] The server notifies the user of the proposed investment strategy. It uses the generated investment strategy proposal as input and generates a notification message for the user as output. Specifically, the server communicates the details of the investment strategy to the user via email or in-app notifications. The user can then set new investment goals based on this information.

[0197] (Application Example 3)

[0198] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0199] In modern asset management, users need to adapt to diverse investment methods and market fluctuations, but there is a lack of support systems to efficiently handle these challenges. Furthermore, there is a need to monitor progress toward asset goals in real time and appropriately suggest new investment opportunities. Therefore, the challenge lies in providing a system that enables users to manage their assets optimally and effectively advance their wealth building.

[0200] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0201] In this invention, the server includes means for comparing multiple asset management methods and proposing the optimal asset management method to the user; means for providing asset management support using artificial intelligence based on past investment experience and knowledge; means for periodically analyzing the user's asset status and notifying the user of the progress toward achieving asset goals; and means for analyzing market trends and proposing new investment opportunities. This enables the user to manage their assets efficiently and effectively and advance their wealth accumulation.

[0202] "Asset management methods" refer to investment and savings methods used by individuals and corporations to increase their assets, and specifically include stocks, bonds, investment trusts, real estate, etc.

[0203] "User" refers to an individual or legal entity that uses this system for asset management.

[0204] "Artificial intelligence" is a technology in which computer systems imitate human intelligence to learn and reason, and in particular, in asset management, it is used to propose investment strategies and perform market analysis.

[0205] "Asset status" refers to information such as the type, quantity, and appraised value of assets held by the user, and serves as basic data for asset management.

[0206] "Asset targets" refer to the purpose of asset management and the amount of assets that users wish to achieve, and serve as guidelines for asset building.

[0207] "Market trends" refer to price fluctuations and trends in financial markets, changes in economic indicators, etc., and serve as a basis for making investment decisions.

[0208] An "investment opportunity" refers to a situation or condition under which one can make new investments to increase their assets, and represents an investment option that is advantageous to the user.

[0209] The system for implementing this invention consists of a network environment including a server and user terminals. The server executes programs developed using Python and consists of a backend using Flask and a frontend using React Native. TensorFlow is used for the artificial intelligence model.

[0210] The server retrieves data from users' bank and investment accounts via APIs. This data represents the user's asset status, and the server uses it to analyze asset management strategies. Specifically, an artificial intelligence model using TensorFlow evaluates the user's asset status and market trends, and proposes the optimal asset management method.

[0211] The user's device runs an application built with React Native and receives notifications from the server. When the user's asset goals are achieved, the server notifies the user via push notification. The server also analyzes market trends and suggests new investment opportunities to the user.

[0212] For example, if a user has set an asset goal of 1 million yen, the server will send a notification saying, "You are 50,000 yen away from your goal. Would you like to explore new investment opportunities?" when the user's assets reach 950,000 yen. An example of a prompt to input into the generating AI model would be, "Analyze the user's asset situation and suggest the optimal investment strategy. Current assets are 950,000 yen, and the goal is 1 million yen."

[0213] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0214] Step 1:

[0215] The server retrieves data from users' bank and investment accounts via an API. The input is the user's authentication information, and the output is data showing the user's asset status. This data includes the type and value of the user's assets. The server stores this data in a database.

[0216] Step 2:

[0217] The server executes a generative AI model using TensorFlow and analyzes the user's asset status data as input. The input is the asset status data obtained in step 1, and the output is a proposal for the optimal asset management method. The server generates the optimal investment strategy considering the user's asset goals and risk tolerance.

[0218] Step 3:

[0219] The server evaluates whether the user's assets are approaching their set target. The input is the user's current asset amount and the set asset target, and the output is the evaluation result of the target achievement status. The server calculates the remaining amount to reach the target and prepares to notify the user.

[0220] Step 4:

[0221] The server analyzes market trends and proposes new investment opportunities. The input is real-time market data, and the output is a list of investment opportunities favorable to the user. The server uses a generative AI model to analyze market data and identify investment opportunities.

[0222] Step 5:

[0223] The device receives notifications from the server and displays them to the user. The input is notification data sent from the server, and the output is a push notification to the user. The device displays the user's progress toward their asset goals and new investment opportunities, prompting the user to take the next action.

[0224] 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.

[0225] "Example of form 1"

[0226] One embodiment of the present invention is a system incorporating an emotion engine. This system recognizes the user's emotions and adjusts the investment strategy based on that emotional state. Specifically, when the user is feeling stressed, it avoids high-risk investments and recommends stable investments. Conversely, when the user is relaxed, it determines that they are willing to take risks and proposes high-return investments.

[0227] "Example of form 2"

[0228] Furthermore, the emotion engine makes investment suggestions that take the user's emotional state into account. For example, when a user is feeling happy, it suggests investments that will amplify that happiness. Conversely, when a user is feeling sad, it suggests investments that will alleviate that sadness.

[0229] "Example of form 3"

[0230] Furthermore, the emotion engine captures changes in the user's emotions in real time and instantly adjusts the investment strategy accordingly. For example, if a user suddenly experiences a situation that causes significant stress, the emotion engine immediately detects this change and switches the investment strategy to a more safety-oriented approach.

[0231] The following describes the processing flow for each example of the form.

[0232] "Example of form 1"

[0233] Step 1: The emotion engine recognizes the user's emotions in real time.

[0234] Step 2: Adjust investment strategies based on the emotional state recognized by the emotion engine. Specifically, when the user is feeling stressed, avoid high-risk investments and recommend stable investments.

[0235] Step 3: When the user is relaxed, we assume they are willing to take risks and propose high-return investments.

[0236] "Example of form 2"

[0237] Step 1: The emotion engine recognizes the user's emotions in real time.

[0238] Step 2: The emotion engine makes investment suggestions based on the emotional state it recognizes. For example, when a user is feeling happy, it suggests investments that will amplify that happiness.

[0239] Step 3: When a user is feeling sad, suggest an investment that will alleviate that sadness.

[0240] "Example of form 3"

[0241] Step 1: The emotion engine captures changes in the user's emotions in real time.

[0242] Step 2: Instantly adjust your investment strategy in response to the emotional changes detected by the emotional engine.

[0243] Step 3: For example, if a user suddenly experiences a situation that causes them significant stress, the emotion engine will immediately detect this change and switch to a safer investment strategy.

[0244] (Example 1)

[0245] Next, we will describe Example 1 of Form 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."

[0246] Conventional financial product selection systems did not take into account the emotional state of users, making it difficult to propose the most suitable financial products based on their psychological condition. Furthermore, there was a lack of effective means to collect and analyze user information, making it impossible to provide personalized recommendations to individual users.

[0247] 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.

[0248] In this invention, the server includes means for comparing multiple financial products and suggesting the most suitable financial product to the user, means for recognizing the user's emotional state and adjusting the financial strategy based on that state, and means for collecting user information and storing it in a database. This makes it possible to suggest the most suitable financial product according to the user's psychological state and to adjust the strategy to suit each individual user.

[0249] "Financial products" refer to products that are the subject of investment or asset management, and include individual defined contribution pension plans, tax-exempt schemes, savings plans, and junior plans.

[0250] "User" refers to an individual or legal entity that intends to use this system to select financial products.

[0251] "Emotional state" refers to the user's psychological state and includes emotions such as stress and relaxation.

[0252] A "financial strategy" refers to an asset management policy formulated based on the user's investment objectives and risk tolerance.

[0253] A "database" refers to an information management system that systematically stores user information and allows for searching and analysis as needed.

[0254] A "machine learning algorithm" refers to a computational method that performs predictions and classifications by analyzing data and learning patterns.

[0255] "Proposal" refers to the act of showing users the most suitable financial products or strategies based on the analysis results.

[0256] As an embodiment for carrying out this invention, the investment guidance AI system is configured as follows.

[0257] First, the user enters information about their investment objectives and risk tolerance through a web browser. This clarifies the user's investment needs and risk profile. The terminal then sends the entered information to the server.

[0258] The server stores the received user information in a database. A data management system such as MySQL® is used for the database. The stored information is organized using the Python Pandas library.

[0259] Next, the server uses machine learning algorithms such as Scikit-learn to predict the optimal financial product based on the user's profile. This prediction includes analysis that takes historical data and market trends into account.

[0260] Furthermore, the device uses its camera and microphone to collect information about the user's emotional state. The server then uses TensorFlow to run an emotion recognition model to determine whether the user is stressed or relaxed.

[0261] The server comprehensively analyzes this information and proposes the most suitable financial product to the user. The proposal is customized according to the user's emotional state and risk tolerance.

[0262] For example, if a user provides information indicating they "want to minimize risk" and the system determines they are "feeling stressed," the server will suggest stable financial products.

[0263] Examples of prompts include, "Please suggest the best financial product for a user with a low risk tolerance," and "Please tell me the recommended financial strategy for a user who is experiencing stress."

[0264] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0265] Step 1:

[0266] Users enter information about their investment objectives and risk tolerance through a web browser. This information includes age, investment period, and risk tolerance (low, medium, high). This information serves as foundational data to clarify the user's investment needs.

[0267] Step 2:

[0268] The terminal sends the information entered by the user to the server. The server stores the received information in a MySQL database. The information stored in the database is used for subsequent analysis.

[0269] Step 3:

[0270] The server organizes the stored user information using the Python Pandas library. The organized data is then ready for analysis by machine learning algorithms.

[0271] Step 4:

[0272] The server uses Scikit-learn to predict the optimal financial product based on the user's profile. The input is organized user information, and the output is a list of financial products suitable for the user.

[0273] Step 5:

[0274] The terminal collects the user's emotional state using a camera and a microphone. The collected data includes the user's facial expressions and voice tones. These data are used to determine the user's psychological state.

[0275] Step 6:

[0276] The server executes an emotion recognition model using TensorFlow to analyze the user's emotional state. Emotion data transmitted from the terminal is used as input, and a determination result of whether the user feels stressed or relaxed is obtained as output.

[0277] Step 7:

[0278] The server comprehensively analyzes the user's investment information and emotional state, and proposes optimal financial products. The proposal is customized according to the user's risk tolerance and emotional state. The output includes the optimal financial product for the user and the reason therefor.

[0279] Step 8:

[0280] The terminal displays the proposal result received from the server to the user. Specifically, the recommended financial product and the reason therefor are displayed on a web page. The user can make an investment decision based on this information.

[0281] (Application Example 1)

[0282] Next, Application Example 1 of Embodiment 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0283] In modern asset management, investors need to choose the optimal investment method from a variety of options, but fully understanding the characteristics and risks of each method is difficult. Furthermore, investors' emotional states can influence their investment decisions, creating a need for emotionally-based investment strategy recommendations. Moreover, a system is needed that can propose the most suitable investment method to investors through real-time sentiment analysis.

[0284] 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.

[0285] In this invention, the server includes means for comparing multiple asset management methods and proposing the optimal asset management method to the user, means for providing asset management support using artificial intelligence based on the knowledge and experience of prominent investors, and means for analyzing the user's emotional state and adjusting the asset management strategy based on that state. This makes it possible to propose the optimal asset management method that takes the user's emotional state into consideration.

[0286] "Asset management methods" is a general term for the financial products and investment methods that individuals and corporations choose to increase their assets.

[0287] "User" refers to an individual or legal entity that uses an asset management system to build wealth.

[0288] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[0289] "Emotional state" refers to the psychological and emotional state of the user and is a factor that influences investment decision-making.

[0290] "Data collection means" refers to a device or method for acquiring information necessary to analyze a user's emotional state in real time.

[0291] "Asset management support tools" refer to a part of a system that provides information and analysis to help users select the optimal asset management method.

[0292] The system for implementing this invention operates in a network environment including a server and terminals. The server runs a program that compares multiple asset management methods and proposes the optimal asset management method to the user. Specifically, the server uses artificial intelligence based on the knowledge and experience of prominent investors to propose the optimal asset management method that takes into account the user's asset management objectives and risk tolerance.

[0293] The device is equipped with data collection capabilities for real-time analysis of the user's emotional state. Specifically, it uses the device's camera and microphone to capture the user's facial expressions and voice tone, and uses an emotion recognition AI model (e.g., Microsoft® Azure® Emotion API) to determine the emotional state. This information is sent to a server and used to adjust asset management strategies.

[0294] For example, while a user is using their smartphone, the device's camera captures the user's facial expressions and the microphone analyzes their voice tone. If the emotion recognition AI model detects "stress," the server notifies the device with a message saying, "Based on your current emotional state, we recommend a stable investment strategy."

[0295] An example of a prompt for the generating AI model is, "If the user's emotional state is stress, please suggest a stable investment strategy." Based on this prompt, the server generates an appropriate investment strategy and proposes it to the user.

[0296] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0297] Step 1:

[0298] The terminal collects data using a camera and a microphone to analyze the user's emotional state in real time. The inputs are the user's facial expression image and audio data. These pieces of data are sent to an emotion recognition AI model.

[0299] Step 2:

[0300] The terminal uses an emotion recognition AI model to determine the user's emotional state from the collected facial expression image and audio data. The input is the data collected in step 1, and the output is the user's emotional state (e.g., stress, relaxed). In this process, the Emotion API of Microsoft Azure is used to analyze emotions.

[0301] Step 3:

[0302] The terminal transmits the determined emotional state to the server. The input is the emotional state obtained in step 2, and the output is data transmission to the server.

[0303] Step 4:

[0304] Based on the received emotional state, the server uses a generative AI model to propose an optimal asset management method in consideration of the user's asset management objectives and risk tolerance. The inputs are the emotional state and the user's asset management information, and the output is a proposal for the optimal asset management method.

[0305] Step 5:

[0306] The server transmits the generated proposal for the asset management method to the terminal. The input is the proposal generated in step 4, and the output is data transmission to the terminal.

[0307] Step 6:

[0308] The terminal notifies the user of the asset management suggestions received from the server. The input is the suggestions received in step 5, and the output is the notification to the user. Specifically, the terminal screen displays the message, "Based on your current emotional state, we recommend a stable asset management method."

[0309] (Example 2)

[0310] Next, we will describe Example 2 of Form Example 2. 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".

[0311] Conventional investment support systems have the drawback of not considering the emotional state of the user when making investment suggestions, making it difficult to increase user psychological satisfaction. Furthermore, they lack the ability to propose sophisticated investment strategies that utilize the experience of past investors, and therefore could not effectively support users' asset building.

[0312] 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.

[0313] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user, means for investment support using artificial intelligence based on the experience and knowledge of past investors, and means for analyzing the user's emotional state and making investment suggestions that correspond to those emotions. This makes it possible to make investment suggestions that take the user's emotional state into consideration, thereby increasing psychological satisfaction and supporting effective asset building.

[0314] "Investment methods" is a general term for specific methods and strategies used to increase assets.

[0315] "User" refers to an individual or legal entity that uses the system to conduct investment activities.

[0316] "Artificial intelligence" is a technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0317] "Investment support measures" refer to functions that provide advice and suggestions to help users manage their assets effectively.

[0318] "Emotional state" refers to the psychological state and mood of the user and is a factor that influences investment decisions.

[0319] "Investment proposal" refers to recommendations or advice on specific investment actions given to users.

[0320] An "investment strategy" refers to a set of investment actions or policies planned to achieve a specific objective.

[0321] The following system is constructed as an embodiment of this invention.

[0322] The server first collects the user's investment history and market trend data. Specifically, it retrieves the user's past transaction data from the database and obtains the latest market data using external financial information services. This allows the server to understand the user's investment patterns and market trends.

[0323] Next, the server organizes the data using the Python Pandas library and extracts data features using Scikit-learn. This prepares the foundational data for investment strategies. Furthermore, the server uses a machine learning model built with TensorFlow to predict investment strategies suitable for the user. This model implements an algorithm based on the experience and knowledge of past investors.

[0324] The device analyzes the user's emotional state in real time. Specifically, it captures the user's facial expressions with its camera and analyzes the user's emotions using OpenCV and an emotion analysis library. This allows the device to determine the user's current emotional state.

[0325] The server customizes the generated investment strategy according to the user's emotional state. For example, if the user is happy, it suggests aggressive investments that involve taking risks, while if they are sad, it suggests investments that prioritize safety.

[0326] Users can receive investment suggestions from AI through their devices. Specifically, users can review the suggested investment strategies on their device screens and, if necessary, input prompts into the AI ​​model to request further suggestions. For example, by inputting a prompt such as "Tell me more about a low-risk investment strategy," the AI ​​will present a detailed strategy.

[0327] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0328] Step 1:

[0329] The server collects users' investment history and market trend data. It uses past transaction data from the database and market data from external financial information services as input. Based on this data, the server prepares foundational data to understand users' investment patterns and market trends. The output consists of organized investment history data and market trend data.

[0330] Step 2:

[0331] The server uses the Python Pandas library to organize the collected data and Scikit-learn to extract data features. The input consists of investment history data and market trend data obtained in step 1. Data organization and feature extraction generate foundational data for investment strategies. The output is a dataset with extracted features.

[0332] Step 3:

[0333] The server uses a machine learning model built with TensorFlow to predict an investment strategy suitable for the user. The input is a dataset from which features obtained in step 2 have been extracted. The machine learning model implements an algorithm based on the past experience and knowledge of investors, thereby generating the optimal investment strategy. The output is the investment strategy proposed to the user.

[0334] Step 4:

[0335] The device analyzes the user's emotional state in real time. It uses facial expression data captured by the device's camera as input. Using OpenCV and an emotion analysis library, it analyzes the user's emotions and determines their current emotional state. The output provides information about the user's emotional state.

[0336] Step 5:

[0337] The server customizes the generated investment strategy according to the user's emotional state. The inputs used are the investment strategy obtained in step 3 and the emotional state information obtained in step 4. If the user is happy, it suggests a risky, aggressive investment; if they are sad, it suggests a safety-oriented investment. The output is an investment strategy adjusted according to the user's emotions.

[0338] Step 6:

[0339] The user receives investment proposals from the AI ​​via their device. The adjusted investment strategy obtained in step 5 is used as input. The user can review the proposed investment strategy on the device screen and, if necessary, input prompt sentences into the AI ​​model to request further suggestions. The output is the investment strategy presented to the user, along with additional suggestions based on the prompt sentences entered by the user.

[0340] (Application Example 2)

[0341] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0342] In today's investment environment, it is difficult for individual investors to select the optimal investment strategy. Furthermore, an investor's emotional state can influence investment decisions, posing a risk to wealth creation. Moreover, there is a demand for swift and efficient methods in executing investments. To address these challenges, a sophisticated investment support system that takes into account investors' experience and emotions is necessary.

[0343] 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.

[0344] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user; means for investment support using artificial intelligence based on the experience and knowledge of legendary investors; means including an emotion engine that estimates the user's emotional state and makes investment suggestions based on those emotions; and means for coordinating with an electronic payment service to immediately execute the proposed investment. As a result, the user can receive optimal investment suggestions tailored to their emotions and execute investments quickly.

[0345] An "investment method" refers to the specific investment methods and strategies used to increase one's assets.

[0346] "Users" refers to individual investors or customers who use this system.

[0347] "Artificial intelligence" is a technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0348] "Investment support measures" refer to functions and technologies that support users in making optimal investments.

[0349] The "emotional engine" is part of a system that analyzes the emotional state of users and makes investment recommendations based on the results.

[0350] An "electronic payment service" is an online payment system that allows for the sending and receiving of funds via the internet.

[0351] "Suggested investments" refer to specific investment options or strategies that the system recommends to the user.

[0352] The system for carrying out this invention includes a server, a user terminal, and an electronic payment service. The server runs a program to compare multiple investment methods and propose the optimal investment method to the user. The server analyzes the user's investment history and market trends using artificial intelligence based on the experience and knowledge of legendary investors. Furthermore, the server uses an emotion engine to estimate the user's emotional state obtained from the user terminal and makes investment suggestions based on that emotion.

[0353] The user terminal is a device such as a smartphone or tablet that receives investment proposals from the server and notifies the user. The user terminal uses cameras and sensors to capture the user's facial expressions and voice, and sends data to the server to estimate their emotional state.

[0354] Electronic payment services work in conjunction with servers to provide online payment functionality for immediately executing proposed investments. This allows users to invest quickly and efficiently.

[0355] As a concrete example, the server analyzes the user's investment history and current market trends and generates a prompt message saying, "We have analyzed your investment history and current market trends. Now is a good time to invest. Do you want to proceed with the investment?" This prompt message is sent to the user's terminal, and if the user selects "Yes," the investment is executed through the electronic payment service.

[0356] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0357] Step 1:

[0358] The server collects user investment history data and market trend data. It receives the user's past investment history and current market data as input, and feeds this data into a generating AI model. Data processing involves pattern analysis of investment history and extraction of market trends to generate foundational data for proposing optimal investment strategies. The analysis results are obtained as output.

[0359] Step 2:

[0360] The server receives emotion data from the user terminal. It receives facial expression data and voice data transmitted from the user terminal as input and feeds them into the emotion engine. As data processing, it estimates the user's emotional state using an emotion recognition algorithm. The output is data indicating the user's emotional state.

[0361] Step 3:

[0362] The server integrates analysis results and emotional state data to generate optimal investment recommendations for the user. It receives the analysis results from Step 1 and the emotional state data from Step 2 as input, and uses a generative AI model to generate prompt messages. Specifically, it creates a prompt message such as, "We have analyzed your investment history and current market trends. Now is a good time to invest. Do you wish to proceed?" The output is the generated prompt message.

[0363] Step 4:

[0364] The server sends the generated prompt message to the user terminal. It receives the prompt message generated in step 3 as input and sends it to the user terminal. The output is the prompt message displayed on the user terminal.

[0365] Step 5:

[0366] The user reviews the prompt displayed on the terminal and selects whether to proceed with the investment. The user selects "Yes" or "No" in response to the prompt as input. The output is response data based on the user's selection.

[0367] Step 6:

[0368] The server executes the investment through an electronic payment service based on the user's selection. It receives user selection data as input and calls the electronic payment service's API. As data calculations, it calculates the investment amount and processes the payment. As output, it sends a confirmation message to the user's terminal.

[0369] (Example 3)

[0370] Next, we will describe Embodiment 3 of Embodiment Example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0371] Conventional asset building support systems have faced challenges in flexibly adjusting investment strategies in response to changes in users' financial situation and emotions, and therefore failing to propose optimal investment methods. In particular, the lack of adjustments to investment strategies that take into account changes in users' emotions resulted in insufficient risk management.

[0372] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0373] In this invention, the server includes means for comparing multiple investment options and proposing the most suitable investment option to the user; means for providing investment guidance using artificial intelligence based on past investment experience and knowledge; means for supporting the user's asset building; means for periodically analyzing the user's asset information and adjusting the investment strategy; and means for detecting changes in the user's emotions in real time and adjusting the investment strategy. This makes it possible to propose flexible and optimal investment strategies that respond to the user's asset situation and emotional changes.

[0374] "Investment methods" is a general term for financial products and investment methods that users can choose to increase their assets.

[0375] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[0376] "Investment guidance tools" refer to systems and processes designed to propose optimal investment methods to users and support their asset building.

[0377] "Asset building" is the process by which users increase their assets over the long term and achieve their financial goals.

[0378] "Asset information" refers to data about a user's financial assets, including balances, investment amounts, and asset types.

[0379] An "investment strategy" is a plan or policy for efficiently managing assets and optimizing risk and return.

[0380] "Emotional change" refers to a change in the user's psychological state, including emotional shifts such as stress and feelings of relief.

[0381] A description of embodiments for carrying out this invention will be given.

[0382] The server runs a program that compares multiple investment options and proposes the optimal investment method to support users in building their assets. This program uses artificial intelligence to provide investment guidance based on past investment experience and knowledge. Specifically, the server periodically collects users' asset information and inputs it into an AI model for analysis. This AI model considers the user's investment objectives and risk tolerance to generate the optimal investment strategy.

[0383] The device uses sensors from a smartwatch or smartphone to detect changes in the user's emotions in real time. This collects data such as heart rate and voice tone, which is then input into the emotion engine. The emotion engine analyzes this data and adjusts the investment strategy according to the user's emotional changes.

[0384] For example, if a user sets a savings goal of 1 million yen, the server uses AI to detect when the user's assets reach 1 million yen and notifies the user. Furthermore, it can suggest a next savings goal of 2 million yen.

[0385] Examples of prompts for the generating AI model include "Generate a notification message when the user's assets reach their target amount" and "Suggest adjustments to the investment strategy based on the user's emotional changes."

[0386] In this way, the system can provide a flexible and optimal investment strategy that responds to the user's asset situation and emotional changes. The flow of the specific processing in Example 3 will be explained using Figure 21.

[0387] Step 1:

[0388] The server collects user asset information. Specifically, it retrieves data from bank accounts and investment accounts via APIs. This data includes balances, investment amounts, and asset types. Input is data from the user's financial institutions, and output is asset information stored on the server.

[0389] Step 2:

[0390] The server inputs the collected asset information into an AI model to analyze the asset status. The AI ​​model evaluates asset increases and decreases by comparing them with past data and determines whether the goals have been achieved. The input is the asset information obtained in step 1, and the output is the result of the asset status analysis.

[0391] Step 3:

[0392] The server adjusts investment strategies based on the analysis results and proposes new investment opportunities. Specifically, the AI ​​predicts market trends and selects investment targets considering risk and return. The input is the analysis results from step 2, and the output is investment proposals for the user.

[0393] Step 4:

[0394] The device collects the user's emotional data in real time. Using sensors in smartwatches and smartphones, it detects changes in emotion from data such as heart rate and voice tone. The input is data from sensors, and the output is emotional data.

[0395] Step 5:

[0396] The terminal uses an emotion engine to analyze the user's emotional changes and adjust the investment strategy as needed. For example, if the user is feeling stressed, the emotion engine instructs the server to switch to a lower-risk investment strategy. The input is the emotional data from step 4, and the output is the adjusted investment strategy.

[0397] Step 6:

[0398] The server integrates the analysis results of emotional and asset data and provides feedback to the user. Specifically, it generates and sends a report to the user explaining the achievement status of asset goals and the reasons for strategic changes based on emotions. The input is the output of steps 3 and 5, and the output is the feedback report to the user.

[0399] (Application Example 3)

[0400] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0401] In modern wealth building, users need to adapt to diverse investment methods and market fluctuations, but individual emotional changes also influence investment decisions. However, conventional systems do not adjust investment strategies to take user emotions into account, making it difficult to optimize wealth building.

[0402] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0403] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user; means for providing investment guidance using artificial intelligence based on the investor's experience and knowledge; means for recognizing the user's emotions in real time and adjusting the investment strategy according to changes in those emotions; and means for periodically analyzing the user's asset status and notifying the user of the progress toward achieving investment goals. This makes it possible to provide flexible investment strategies that take into account changes in the user's emotions.

[0404] An "investment method" refers to the specific financial products or strategies chosen to increase one's assets.

[0405] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[0406] "Investment guidance methods" refer to methods for proposing optimal investment strategies to users and supporting their asset building.

[0407] "Emotion recognition means" refers to technology that detects a user's emotional state in real time and adjusts the system's operation based on that information.

[0408] "Asset analysis methods" refer to methods for periodically evaluating a user's asset situation and determining whether their investment goals are being achieved.

[0409] An "investment strategy" is a plan or set of guidelines established to effectively manage assets.

[0410] "Asset building" is the process by which individuals and organizations increase their assets and achieve financial stability.

[0411] The system for carrying out this invention includes a server, a user terminal, and an emotion recognition device. The server is equipped with artificial intelligence to periodically analyze the user's asset status and suggest the optimal investment method. The user terminal is a device such as a smartphone or computer, which receives notifications from the server and provides information to the user. The emotion recognition device detects the user's emotions in real time and transmits that data to the server.

[0412] The server analyzes the user's asset status based on information obtained from a financial database. Based on the analysis results, the server notifies the user of their progress toward investment goals and proposes new investment strategies. An emotion recognition device detects the user's emotional state and sends this information to the server, which is used to adjust the investment strategy.

[0413] As a concrete example, if a user is experiencing stress, the emotion recognition device sends this information to a server. The server considers the user's emotional state and proposes a safety-oriented investment strategy. Using a generative AI model, it generates the optimal strategy based on the prompt, "What investment strategy should be proposed if the user is experiencing stress?"

[0414] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0415] Step 1:

[0416] The server retrieves user asset information from a financial database. It uses the user's account information as input. The output is user asset status data. Based on this data, the server prepares to analyze the user's asset status.

[0417] Step 2:

[0418] The server analyzes the acquired asset status data and evaluates the user's progress toward achieving their investment goals. Asset status data is used as input. An evaluation result showing the progress toward investment goals is obtained as output. Based on this evaluation result, the server determines what to notify the user about.

[0419] Step 3:

[0420] Emotion recognition devices detect a user's emotional state in real time. They use the user's biometric information and behavioral data as input. The output is the user's emotional state data. This data is sent to a server to help adjust investment strategies based on emotions.

[0421] Step 4:

[0422] The server receives emotional state data and generates an investment strategy tailored to the user's emotions. It uses emotional state data and asset status evaluation results as input. The output is an adjusted investment strategy. Using a generative AI model, it generates the optimal strategy based on the prompt, "What investment strategy should be proposed if the user is experiencing stress?"

[0423] Step 5:

[0424] The server notifies the user terminal of the adjusted investment strategy. It uses the adjusted investment strategy as input and generates a notification message for the user as output. The user receives this notification and can consider changing their investment strategy.

[0425] (Other examples)

[0426] Next, other embodiments 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".

[0427] In today's investment environment, it is difficult for individual investors to select the optimal investment method that suits their investment objectives and risk tolerance. Furthermore, investors' emotional states often influence investment decisions, and there is a need for investment strategies that take this into account. Moreover, effectively utilizing vast amounts of market data and the experience of past investors is also a challenging task.

[0428] The identification process performed by the identification processing unit 290 of the data processing device 12 in other embodiments is realized by the following means.

[0429] This invention includes a server that generates prompts to instruct the evaluation of investment instruments using a generative AI model; a database of past investor experiences and knowledge, and a means for artificial intelligence to generate investment strategies by referring to this database; and a means including an emotion engine that recognizes the user's emotional state in real time and adjusts the investment strategy based on that emotion. This makes it possible to suggest the optimal investment instrument according to the user's investment objectives and risk tolerance.

[0430] A "generative AI model" is an artificial intelligence model that performs natural language processing based on user input and proposes the optimal investment strategy.

[0431] A "prompt message" is an instruction given to a generating AI model to perform a specific task, and it includes content that reflects the user's investment objectives and risk tolerance.

[0432] "Investment methods" is a general term for financial products and investment methods that users choose to increase their assets, and includes individual defined contribution pension plans and small-amount investment tax exemption schemes.

[0433] An "emotion engine" is a software component that recognizes a user's emotional state in real time and adjusts investment strategies based on that information.

[0434] A "database" is a collection of information that systematically stores past investor experiences and market data, making it accessible as needed.

[0435] This invention is a system that proposes the optimal investment method according to the user's investment objectives and risk tolerance. The system consists of three main components: a server, a terminal, and the user.

[0436] The server first collects past investor success stories and market analysis reports from publicly available databases and financial information services on the internet. This data is scraped using a Python script and stored in a MySQL database. The database contains information such as the investor's name, investment method, success rate, and relevant market conditions.

[0437] Next, the server generates prompt messages for input into the AI ​​model based on the investment objectives and risk tolerance entered by the user through the terminal. Specifically, it uses the natural language processing library NLTK to create a prompt message such as, "The user wants to invest in a medium-risk investment and wants to double their assets within 5 years."

[0438] The generative AI model used is OpenAI's GPT-4®. The server inputs prompt statements into this generative AI model, which then proposes the optimal investment strategy. The generative AI model analyzes the prompt statements and evaluates relevant investment strategies from a historical database. The evaluation results are adjusted based on the user's risk tolerance and market trends.

[0439] The device provides an interface through a React-based web application where users can input their investment objectives and risk tolerance. Users set specific goals using sliders and text boxes. The device also uses its built-in camera and microphone to collect the user's facial expressions and voice tone in real time. This data is analyzed using emotion recognition software (e.g., Affectiva) to identify the user's emotional state.

[0440] The server adjusts the generated investment strategy based on emotional data obtained from emotion recognition software. For example, if the user is feeling anxious, it prioritizes suggesting investment options with reduced risk. The adjusted investment strategy is notified to the user's device, and the user can then execute investments based on the suggestions.

[0441] Example prompt: The user is looking for a medium-risk investment and wants to double their assets within 5 years.

[0442] The flow of specific processing in other embodiments will be explained using Figure 23.

[0443] Step 1:

[0444] The server collects past investor success stories and market analysis reports from publicly available databases and financial information services on the internet. Input includes raw data obtained through APIs and web scraping. This data is processed using Python scripts and organized into information such as investor names, investment methods, success rates, and relevant market conditions. The output is stored in a MySQL database.

[0445] Step 2:

[0446] The terminal provides an interface through a React-based web application that allows users to input their investment objectives and risk tolerance. Inputs include investment goals and risk tolerance set by the user using sliders and text boxes. This input data is sent to the server in JSON format. Output is the user's input information stored on the server.

[0447] Step 3:

[0448] The server generates prompt text for input to the generative AI model based on the information entered by the user. This input includes data about the user's investment objectives and risk tolerance. Using the natural language processing library NLTK, the server analyzes this data and creates a prompt text such as, "The user desires a medium-risk investment and wants to double their assets within five years." The generated prompt text is then sent to the generative AI model as output.

[0449] Step 4:

[0450] The server inputs prompt statements into a generative AI model such as OpenAI's GPT-4, which then proposes the optimal investment strategy. The input consists of prompt statements. The generative AI model analyzes the prompt statements and evaluates relevant investment strategies from a historical database. The output is a list of the evaluated investment strategies.

[0451] Step 5:

[0452] The device uses its built-in camera and microphone to collect the user's facial expressions and voice tone in real time. Input includes the user's facial expression data and voice data. This data is analyzed using emotion recognition software (e.g., Affectiva) to identify the user's emotional state. The user's emotional state is then sent to a server as output.

[0453] Step 6:

[0454] The server adjusts the generated investment strategy based on emotional data obtained from emotion recognition software. The input includes the user's emotional state and a list of evaluated investment options. For example, if the user is feeling anxious, the list is adjusted to prioritize suggesting investment options with lower risk. The output is the adjusted investment strategy.

[0455] Step 7:

[0456] The server notifies the user's device of the adjusted investment strategy. The input is the adjusted investment strategy. The output is the notification sent to the user via email or in-app notification. The user can then execute the investment based on the proposal.

[0457] 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.

[0458] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> 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.

[0459] Other examples of generative AI include Gemini® (registered trademark) (Internet search). <url: https: gemini.google.com ?hl="ja">) are some examples.

[0460] 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.

[0461] [Second Embodiment]

[0462] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0463] 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.

[0464] The data processing device 12 includes 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.

[0465] Computer 22 includes a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. A database 24 and a 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).

[0466] 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.

[0467] 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.

[0468] 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).

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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.

[0474] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0475] "Example of form 1"

[0476] One embodiment of the present invention is an investment guidance AI system. This system has means for comparing multiple investment methods and proposing the optimal investment method to the user. Specifically, it compares investment methods such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA, and proposes the optimal investment method based on information such as the user's investment objectives and risk tolerance.

[0477] "Example of form 2"

[0478] Furthermore, one embodiment of this invention is an AI-powered investment guidance system based on the experience and intellect of legendary investors. This AI uses algorithms based on the investors' experience and intellect to support the user's asset building. Specifically, the AI ​​analyzes the user's investment history and market trends and proposes the optimal investment strategy.

[0479] "Example of form 3"

[0480] Furthermore, one embodiment of the present invention involves means of supporting the user's asset building. Specifically, the AI ​​periodically analyzes the user's asset status and adjusts investment strategies or suggests new investment opportunities. For example, if the user's assets reach a certain target, the AI ​​notifies the user of this information and assists in setting new investment targets.

[0481] The following describes the processing flow for each example of the form.

[0482] "Example of form 1"

[0483] Step 1: The user enters information such as their investment objectives and risk tolerance into the system.

[0484] Step 2: The system compares multiple investment methods (such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA).

[0485] Step 3: The system proposes the optimal investment method based on the user's information.

[0486] "Example of form 2"

[0487] Step 1: The AI ​​uses algorithms based on the experience and intellect of legendary investors to analyze the user's investment history and market trends.

[0488] Step 2: The AI ​​proposes the optimal investment strategy based on the analysis results.

[0489] "Example of form 3"

[0490] Step 1: The AI ​​periodically analyzes the user's asset status.

[0491] Step 2: The AI ​​adjusts investment strategies and suggests new investment opportunities.

[0492] Step 3: When the AI ​​reaches a certain target for the user's assets, it notifies the user of this information and helps them set new investment goals.

[0493] (Example 1)

[0494] Next, we will describe Example 1 of Form 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".

[0495] In today's financial markets, users are required to make the optimal choices from a diverse range of financial products, which necessitates specialized knowledge and analysis. In particular, selecting the most suitable financial product based on a user's financial goals and risk tolerance is challenging, and there is a need for a system that can provide efficient and accurate recommendations.

[0496] 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.

[0497] In this invention, the server includes means for comparing multiple financial products and suggesting the most suitable financial product to the user, means for data analysis using historical market data and machine learning algorithms, and means for supporting the user's financial goals. This enables the user to efficiently select the most suitable financial product based on their own profile.

[0498] "Financial products" refer to products that are the subject of investment or asset management, and include individual defined contribution pension plans, small-amount investment tax exemption schemes, installment investment schemes, and junior investment schemes.

[0499] "User" refers to an individual or corporation that selects financial products and engages in investment or asset management.

[0500] "Means of proposing the optimal financial product" refers to the methods and processes for comparing multiple financial products based on the user's financial goals and risk tolerance, and selecting the most suitable product.

[0501] "Data analysis methods" refer to methods and processes for analyzing data using machine learning algorithms based on past market data and user input information, in order to provide users with useful information.

[0502] "Means to support financial goals" refers to methods and processes that provide the information and suggestions necessary to achieve the financial goals set by the user, and that support asset building.

[0503] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze user profiles and market data to propose the most suitable financial products.

[0504] As an embodiment for carrying out this invention, the investment guidance AI system is constructed as follows.

[0505] The server generates a program for an investment guidance AI system. This program is designed to suggest the most suitable financial products to the user. The server uses programming languages ​​such as Python and R to analyze historical market data and user input information. This allows for data analysis based on the user's risk tolerance and financial goals.

[0506] The server uses a generative AI model to create a user profile. This profile includes information such as the user's age, investment objectives, risk tolerance, and investment period. Based on this information, the server compares multiple financial products and selects the most suitable one.

[0507] The terminal provides an interface for users to access the system and enter necessary information. Users can enter prompt messages through the terminal, such as the following:

[0508] "I'm in my 40s and want to increase my assets while minimizing risk. Could you please tell me which investment method is best?"

[0509] "I want to save money for my child's college education. What investment method would be suitable?"

[0510] Upon receiving these prompts, the server suggests the most suitable financial products based on the user's profile. This suggestion is then communicated to the user via their terminal. This allows the user to efficiently make investments that align with their financial goals.

[0511] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0512] Step 1:

[0513] Users access the system through their terminals and enter information such as their investment objectives, age, risk tolerance, and investment period. This information is sent to the server and serves as the basis for creating the user's profile.

[0514] Step 2:

[0515] The server creates a profile based on the user information it receives. Using programming languages ​​such as Python or R, the server analyzes the input data and quantifies the user's risk tolerance and financial targets. This profile is then used for subsequent data analysis.

[0516] Step 3:

[0517] The server uses a generative AI model to analyze historical market data and user profiles. The server applies machine learning algorithms to perform data analysis to identify the most suitable financial products for the user. During this process, the risk and return of each financial product are evaluated.

[0518] Step 4:

[0519] Based on the analysis results, the server suggests the most suitable financial products to the user. These suggestions are then communicated to the user via their terminal. Specifically, if the user has a low risk tolerance, financial products that offer stable returns may be suggested.

[0520] Step 5:

[0521] Users review the suggested financial products on their devices and make investment decisions as needed. Based on these suggestions, users can make investment decisions that align with their financial goals.

[0522] (Application Example 1)

[0523] Next, we will describe Application Example 1 of Form 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."

[0524] In today's investment environment, it is difficult for individual investors to select the optimal investment method that suits their investment objectives and risk tolerance. Furthermore, there is a lack of support for investors to effectively compare the diverse range of available investment options and make the best choices. Therefore, there is a need for a system that enables investors to build wealth efficiently and effectively.

[0525] 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.

[0526] In this invention, the server includes means for comparing multiple investment options and suggesting the optimal investment option to the user; means for analyzing past investment data and suggesting the optimal investment option based on the user's investment history and spending patterns; means for collecting the user's financial data and formatting and analyzing the data; means for using a machine learning model to predict the optimal investment option based on the user's risk tolerance and investment objectives; and means for providing a user interface that allows the user to compare and select investment plans. This makes it possible for the user to easily select the optimal investment option according to their own investment objectives and risk tolerance.

[0527] "Investment methods" is a general term for financial products and systems used to increase assets, and includes individual defined contribution pension plans and small-amount investment tax exemption schemes.

[0528] "User" refers to an individual or legal entity that uses the system to select and manage investments.

[0529] "Investment history" refers to a record of past investment activities, including information such as investment amount, investment destination, and investment period.

[0530] "Spending patterns" indicate the user's spending habits and show how much money they spend on what items.

[0531] "Financial data" refers to financial information such as a user's assets, liabilities, income, and expenses, and is the basic data necessary for investment decisions.

[0532] A "machine learning model" is a computational model that uses algorithms to learn patterns from data and perform predictions and classifications.

[0533] "Risk tolerance" is an indicator that shows the range of risk an investor can tolerate, and it represents an individual investor's attitude and ability to handle risk.

[0534] "Investment objectives" refer to the specific goals and intentions when making an investment, and include increasing assets, diversifying risk, and preparing for future funding needs.

[0535] A "user interface" refers to the screens and operating methods that allow users to interact with a system, and is a means of inputting information and displaying results.

[0536] To implement this invention, it is necessary to build a system in which a server plays a central role. The server will be programmed using Python, and the backend will be built using the Flask framework. Pandas and Scikit-learn will be used for data analysis. This will enable the server to collect users' financial data and to format and analyze the data.

[0537] Specifically, the server analyzes the user's investment history and spending patterns, and uses machine learning models to predict the optimal investment strategy based on the user's risk tolerance and investment objectives. This allows users to easily select the most suitable investment strategy according to their own investment objectives and risk tolerance.

[0538] The terminal provides a user interface, allowing users to compare and select investment plans. Users can receive information from the server via their smartphone or computer and make investment choices.

[0539] For example, if a user enters "I want to invest 50,000 yen per month," the server analyzes past spending data and assesses their risk tolerance. As a result, it can suggest that Tsumitate NISA (a type of tax-advantaged investment account) is the optimal option.

[0540] An example of a prompt to input into the generating AI model is: "The user's monthly investment limit is 50,000 yen, and their risk tolerance is moderate. Please suggest the optimal investment method."

[0541] In this way, by coordinating servers, terminals, and users, an efficient and effective investment support system can be realized.

[0542] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0543] Step 1:

[0544] The server receives input data from the user. This input data includes the user's available investment amount, risk tolerance, and investment objectives. Based on this data, the server understands the user's investment needs.

[0545] Step 2:

[0546] The server uses Pandas to retrieve users' past investment history and spending patterns from a database, then formats and analyzes the data. Input includes past transaction history and spending records, which are used to extract trends in the user's investment behavior. The output provides characteristics of the user's investment behavior.

[0547] Step 3:

[0548] The server uses Scikit-learn to run a machine learning model and predict the optimal investment strategy based on the user's risk tolerance and investment objectives. The input consists of formatted investment history data and the user's risk tolerance, which are used to calculate the optimal investment strategy. The output is a list of recommended investment strategies.

[0549] Step 4:

[0550] The server generates prompt messages using a generative AI model. The input includes the user's investment needs and predicted investment methods, and the server creates prompt messages based on this information. The output is a prompt message to be presented to the user.

[0551] Step 5:

[0552] The terminal displays prompt messages received from the server and recommended investment options to the user. The user can review the information presented through the terminal and make an investment choice.

[0553] Step 6:

[0554] The user selects an investment option presented through the terminal and executes the investment as needed. The input is recommended information from the server, which the user uses to make investment decisions. The output is the selected investment option.

[0555] In this way, servers, terminals, and users work together to achieve efficient and effective investment support.

[0556] (Example 2)

[0557] Next, we will describe Example 2 of Form 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".

[0558] Conventional investment support systems have been unable to fully utilize users' investment history and market trends, making it difficult to propose optimal investment strategies. Furthermore, they have not been able to use algorithms that leverage the experience of legendary investors, thus failing to effectively support users' asset building.

[0559] 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.

[0560] In this invention, the server includes means for receiving investment history entered by the user, means for collecting market data, and means for analyzing the collected data and generating an optimal investment strategy. This makes it possible to propose an optimal investment strategy based on the user's investment history and market trends.

[0561] "A means of receiving user-entered investment history" refers to a function that allows users to input records of their past investment activities into the system and retrieve that information.

[0562] "Means for collecting market data" refers to a function that obtains information about financial markets from external information services and makes it available within the system.

[0563] "A means of analyzing collected data and generating the optimal investment strategy" refers to a function that analyzes the user's acquired investment history and market data to calculate and propose the most suitable investment method for the user.

[0564] "A method that uses algorithms based on the experience and knowledge of legendary investors" refers to a function that uses computational methods built on the past success stories and insights of prominent investors to formulate investment strategies.

[0565] "Means of supporting users' asset building" refers to functions that provide advice and strategies for users to efficiently increase their assets and support their asset management.

[0566] To implement this invention, it is first necessary to generate a program on the server that receives investment history from users. This program has the function of receiving investment history entered by the user through a dedicated terminal or web application. Users can enter information such as past stock purchase and sale history and investment amount.

[0567] Next, the server collects market data. This data collection utilizes data from financial information services. Specifically, it obtains market data such as stock indices, exchange rates, and economic indicators from services like Yahoo Finance and Bloomberg.

[0568] The server uses machine learning libraries such as Python's Pandas library and Scikit-learn to analyze the user's investment history and market data. This makes it possible to identify past investment patterns and compare them with current market trends.

[0569] Based on the analysis results, the server uses a generative AI model to generate the optimal investment strategy. This generated strategy is designed to maximize returns while minimizing risk.

[0570] Finally, the server proposes the generated investment strategy to the user. The user can review the proposed strategy and make adjustments as needed.

[0571] As a concrete example, a user might enter a prompt message such as, "Based on my investment history over the past five years, please suggest a future investment strategy." Upon receiving this prompt, the server analyzes the user's investment history and market data, generates a specific investment strategy such as, "You should focus on technology stocks for the next six months," and proposes it to the user.

[0572] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0573] Step 1:

[0574] The user enters their investment history.

[0575] Users input their past investment history through a dedicated terminal or web application. This data includes stock purchase and sale history, investment amounts, and other information. This input data is sent to a server and stored in a database.

[0576] Step 2:

[0577] The server collects market data.

[0578] The server collects market data from financial information services. Specifically, it obtains data such as stock indices, exchange rates, and economic indicators via APIs. This data is updated in real time and stored in a database on the server.

[0579] Step 3:

[0580] The server analyzes the data.

[0581] The server uses the Python Pandas library to analyze the user's investment history and collected market data. The input data consists of the user's investment history and market data. Based on this data, the server identifies past investment patterns and compares them to current market trends. The analysis results are used in the next step.

[0582] Step 4:

[0583] The server generates the investment strategy.

[0584] The server uses a generative AI model to generate the optimal investment strategy based on the analysis results. The analysis results are used as input. The server calculates a strategy to maximize returns while minimizing risk and creates specific investment proposals.

[0585] Step 5:

[0586] The server proposes investment strategies to the user.

[0587] The server notifies the user of the generated investment strategy. The specific investment strategy is sent to the user's terminal as output. The user can review the proposed strategy and make adjustments as needed.

[0588] (Application Example 2)

[0589] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0590] In today's investment environment, it is difficult for individual investors to formulate optimal investment strategies based on vast amounts of information. Furthermore, there is a lack of means to receive real-time advice based on investors' experience and knowledge. Therefore, there is a need for support systems that enable investors to build wealth efficiently and effectively.

[0591] 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.

[0592] This invention includes a server that compares multiple investment methods and proposes the optimal investment method to the user, an artificial intelligence-based investment support method based on the experience and knowledge of legendary investors, and a method that analyzes the user's investment history and market trends and proposes the optimal investment strategy in real time. This enables the user to efficiently develop an investment strategy.

[0593] An "investment method" refers to the specific methods and strategies used to increase one's assets.

[0594] A "user" refers to an individual or legal entity that uses this system to conduct investment activities.

[0595] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and perform learning and reasoning.

[0596] "Investment support measures" refer to support functions provided to help users make optimal investment decisions.

[0597] "Investment history" refers to a record of the user's past investment activities.

[0598] "Market trends" refer to price fluctuations and trends in financial markets.

[0599] "Real-time" refers to information being processed instantly the moment it is generated.

[0600] An "investment strategy" is a set of action plans designed to achieve specific investment objectives.

[0601] A "smartphone" is a portable device that, in addition to the functions of a mobile phone, possesses multiple functions similar to those of a computer.

[0602] An "application" is a software program designed to provide a specific function or service.

[0603] The system for implementing this invention consists of a server and a user's terminal (smartphone). The server runs a generative AI model built using Python and calculates investment strategies using TensorFlow. The server provides an API using Flask and accepts requests from the user's terminal. SQLite is used as the database to manage the user's investment history and market trend data.

[0604] The user's device communicates with a server via a dedicated application, allowing them to receive real-time investment advice. This application sends the user's investment history to the server and displays the investment strategies received from the server.

[0605] For example, if a user has previously invested heavily in technology-related assets, the server will analyze market trends in the technology sector and propose future investment strategies. Based on these suggestions, the user can then decide on their next investment actions.

[0606] An example of a prompt message is: "Based on the user's past investment history, please suggest the optimal investment strategy considering current market trends."

[0607] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0608] Step 1:

[0609] The user's device collects investment history data as input. This data includes past investment amounts, investment destinations, and investment periods. The collected data is sent to the server.

[0610] Step 2:

[0611] The server receives the investment history data as input and stores it in a database. Next, it preprocesses the data and converts it into a format suitable for the generative AI model. This preprocessing includes data normalization and imputation of missing values.

[0612] Step 3:

[0613] The server inputs pre-processed investment history data and market trend data into a generating AI model. The model analyzes the data using TensorFlow and outputs the optimal investment strategy. This analysis includes analysis of past market trends and risk assessment.

[0614] Step 4:

[0615] The server sends the investment strategy generated by the AI ​​model to the user's terminal. This investment strategy includes recommended investment targets, investment amounts, and risk assessments.

[0616] Step 5:

[0617] The user's device displays the investment strategy received from the server. Based on this information, the user can decide on their next investment action. Specifically, the application visually displays the investment strategy to make it easy for the user to understand.

[0618] (Example 3)

[0619] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[0620] Conventional asset building support systems have struggled to effectively utilize users' financial information and propose optimal investment strategies tailored to their individual asset situations. Furthermore, they were unable to evaluate users' progress toward asset goals in real time and adjust investment strategies at appropriate times.

[0621] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0622] In this invention, the server includes means for collecting and storing the user's financial information in a database, means for preprocessing the collected financial information and converting it into an analyzable format, and means for analyzing the user's asset status using a generative AI model and predicting future asset trends. This makes it possible to propose an optimal investment strategy tailored to the user's individual asset situation.

[0623] "User" refers to an individual or legal entity that provides financial information and utilizes the asset building support system.

[0624] "Financial information" refers to data necessary to understand a user's asset status, such as their account balance, investment portfolio details, and transaction history.

[0625] A "database" refers to an information management system that stores collected financial information and makes it accessible as needed.

[0626] "Preprocessing" refers to processes such as data cleaning and normalization performed to convert collected financial information into an analyzable format.

[0627] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to analyze a user's asset situation and predict future asset trends.

[0628] "Asset status" refers to information that shows the current state and composition of a user's assets.

[0629] An "investment strategy" refers to specific investment policies and action plans proposed to optimize a user's asset building.

[0630] To implement this invention, a server must first collect the user's financial information and store it in a database. The server retrieves data such as account balances, investment portfolio details, and transaction history from financial institutions via an API. This data is stored in the database for later analysis.

[0631] Next, the server preprocesses the collected financial information. Specifically, it cleans and normalizes the data and imputes missing values. This process transforms the data into a format suitable for analysis by generative AI models. Data analysis libraries such as "Pandas" and "NumPy" are sometimes used for preprocessing.

[0632] Subsequently, the server analyzes the user's asset status using a generative AI model. This AI model is built using machine learning frameworks such as "TensorFlow" and "PyTorch," and predicts future asset trends based on the user's past data. The AI ​​model evaluates how well the user's assets are progressing towards their set goals and proposes the optimal investment strategy.

[0633] For example, if a user sets a goal of "doubling their assets within five years," the server will periodically collect asset data and analyze it using an AI model. The AI ​​model may suggest a shift to a lower-risk investment strategy once the user's assets reach 80% of their goal. This suggestion may include recommendations for specific investment targets and amounts.

[0634] An example of a prompt to be input to the generating AI model is, "Please suggest the next steps once the user's assets reach their target." This prompt prompts the AI ​​to generate specific advice to help the user set new investment goals. The specific processing flow in Example 3 is explained using Figure 15.

[0635] Step 1:

[0636] The server collects users' financial information. As input, it uses the user's authentication credentials to access financial institutions' APIs and retrieve data such as account balances, investment portfolio details, and transaction history. As output, it stores the retrieved data in a database. Specifically, the server periodically executes scheduled jobs to collect the latest financial information.

[0637] Step 2:

[0638] The server preprocesses the collected financial information. It uses raw data stored in a database as input. The output is data converted into an analyzable format. Specific data processing involves cleaning the data, imputing missing values, and normalizing the data as needed. This makes the data suitable for analysis by AI models.

[0639] Step 3:

[0640] The server analyzes the user's asset status using a generative AI model. Pre-processed data is supplied to the AI ​​model as input. The output is a prediction of the user's asset trends. Specifically, the AI ​​model uses machine learning algorithms to predict future asset trends based on past data. This prediction shows how well the user's assets are progressing towards their goals.

[0641] Step 4:

[0642] The server proposes the optimal investment strategy to the user based on the analysis results. It uses the prediction results of an AI model as input and generates specific investment strategy suggestions as output. Specifically, the server selects investment targets with reduced risk and presents investment opportunities in emerging markets, depending on the user's risk tolerance and investment goals.

[0643] Step 5:

[0644] The server notifies the user of the proposed investment strategy. It uses the generated investment strategy proposal as input and generates a notification message for the user as output. Specifically, the server communicates the details of the investment strategy to the user via email or in-app notifications. The user can then set new investment goals based on this information.

[0645] (Application Example 3)

[0646] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0647] In modern asset management, users need to adapt to diverse investment methods and market fluctuations, but there is a lack of support systems to efficiently handle these challenges. Furthermore, there is a need to monitor progress toward asset goals in real time and appropriately suggest new investment opportunities. Therefore, the challenge lies in providing a system that enables users to manage their assets optimally and effectively advance their wealth building.

[0648] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0649] In this invention, the server includes means for comparing multiple asset management methods and proposing the optimal asset management method to the user; means for providing asset management support using artificial intelligence based on past investment experience and knowledge; means for periodically analyzing the user's asset status and notifying the user of the progress toward achieving asset goals; and means for analyzing market trends and proposing new investment opportunities. This enables the user to manage their assets efficiently and effectively and advance their wealth accumulation.

[0650] "Asset management methods" refer to investment and savings methods used by individuals and corporations to increase their assets, and specifically include stocks, bonds, investment trusts, real estate, etc.

[0651] "User" refers to an individual or legal entity that uses this system for asset management.

[0652] "Artificial intelligence" is a technology in which computer systems imitate human intelligence to learn and reason, and in particular, in asset management, it is used to propose investment strategies and perform market analysis.

[0653] "Asset status" refers to information such as the type, quantity, and appraised value of assets held by the user, and serves as basic data for asset management.

[0654] "Asset targets" refer to the purpose of asset management and the amount of assets that users wish to achieve, and serve as guidelines for asset building.

[0655] "Market trends" refer to price fluctuations and trends in financial markets, changes in economic indicators, etc., and serve as a basis for making investment decisions.

[0656] An "investment opportunity" refers to a situation or condition under which one can make new investments to increase their assets, and represents an investment option that is advantageous to the user.

[0657] The system for implementing this invention consists of a network environment including a server and user terminals. The server executes programs developed using Python and consists of a backend using Flask and a frontend using React Native. TensorFlow is used for the artificial intelligence model.

[0658] The server retrieves data from users' bank and investment accounts via APIs. This data represents the user's asset status, and the server uses it to analyze asset management strategies. Specifically, an artificial intelligence model using TensorFlow evaluates the user's asset status and market trends, and proposes the optimal asset management method.

[0659] The user's device runs an application built with React Native and receives notifications from the server. When the user's asset goals are achieved, the server notifies the user via push notification. The server also analyzes market trends and suggests new investment opportunities to the user.

[0660] For example, if a user has set an asset goal of 1 million yen, the server will send a notification saying, "You are 50,000 yen away from your goal. Would you like to explore new investment opportunities?" when the user's assets reach 950,000 yen. An example of a prompt to input into the generating AI model would be, "Analyze the user's asset situation and suggest the optimal investment strategy. Current assets are 950,000 yen, and the goal is 1 million yen."

[0661] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[0662] Step 1:

[0663] The server retrieves data from users' bank and investment accounts via an API. The input is the user's authentication information, and the output is data showing the user's asset status. This data includes the type and value of the user's assets. The server stores this data in a database.

[0664] Step 2:

[0665] The server executes a generative AI model using TensorFlow and analyzes the user's asset status data as input. The input is the asset status data obtained in step 1, and the output is a proposal for the optimal asset management method. The server generates the optimal investment strategy considering the user's asset goals and risk tolerance.

[0666] Step 3:

[0667] The server evaluates whether the user's assets are approaching their set target. The input is the user's current asset amount and the set asset target, and the output is the evaluation result of the target achievement status. The server calculates the remaining amount to reach the target and prepares to notify the user.

[0668] Step 4:

[0669] The server analyzes market trends and proposes new investment opportunities. The input is real-time market data, and the output is a list of investment opportunities favorable to the user. The server uses a generative AI model to analyze market data and identify investment opportunities.

[0670] Step 5:

[0671] The device receives notifications from the server and displays them to the user. The input is notification data sent from the server, and the output is a push notification to the user. The device displays the user's progress toward their asset goals and new investment opportunities, prompting the user to take the next action.

[0672] 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.

[0673] "Example of form 1"

[0674] One embodiment of the present invention is a system incorporating an emotion engine. This system recognizes the user's emotions and adjusts the investment strategy based on that emotional state. Specifically, when the user is feeling stressed, it avoids high-risk investments and recommends stable investments. Conversely, when the user is relaxed, it determines that they are willing to take risks and proposes high-return investments.

[0675] "Example of form 2"

[0676] Furthermore, the emotion engine makes investment suggestions that take the user's emotional state into account. For example, when a user is feeling happy, it suggests investments that will amplify that happiness. Conversely, when a user is feeling sad, it suggests investments that will alleviate that sadness.

[0677] "Example of form 3"

[0678] Furthermore, the emotion engine captures changes in the user's emotions in real time and instantly adjusts the investment strategy accordingly. For example, if a user suddenly experiences a situation that causes significant stress, the emotion engine immediately detects this change and switches the investment strategy to a more safety-oriented approach.

[0679] The following describes the processing flow for each example of the form.

[0680] "Example of form 1"

[0681] Step 1: The emotion engine recognizes the user's emotions in real time.

[0682] Step 2: Adjust investment strategies based on the emotional state recognized by the emotion engine. Specifically, when the user is feeling stressed, avoid high-risk investments and recommend stable investments.

[0683] Step 3: When the user is relaxed, we assume they are willing to take risks and propose high-return investments.

[0684] "Example of form 2"

[0685] Step 1: The emotion engine recognizes the user's emotions in real time.

[0686] Step 2: The emotion engine makes investment suggestions based on the emotional state it recognizes. For example, when a user is feeling happy, it suggests investments that will amplify that happiness.

[0687] Step 3: When a user is feeling sad, suggest an investment that will alleviate that sadness.

[0688] "Example of form 3"

[0689] Step 1: The emotion engine captures changes in the user's emotions in real time.

[0690] Step 2: Instantly adjust your investment strategy in response to the emotional changes detected by the emotional engine.

[0691] Step 3: For example, if a user suddenly experiences a situation that causes them significant stress, the emotion engine will immediately detect this change and switch to a safer investment strategy.

[0692] (Example 1)

[0693] Next, we will describe Example 1 of Form 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".

[0694] Conventional financial product selection systems did not take into account the emotional state of users, making it difficult to propose the most suitable financial products based on their psychological condition. Furthermore, there was a lack of effective means to collect and analyze user information, making it impossible to provide personalized recommendations to individual users.

[0695] 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.

[0696] In this invention, the server includes means for comparing multiple financial products and suggesting the most suitable financial product to the user, means for recognizing the user's emotional state and adjusting the financial strategy based on that state, and means for collecting user information and storing it in a database. This makes it possible to suggest the most suitable financial product according to the user's psychological state and to adjust the strategy to suit each individual user.

[0697] "Financial products" refer to products that are the subject of investment or asset management, and include individual defined contribution pension plans, tax-exempt schemes, savings plans, and junior plans.

[0698] "User" refers to an individual or legal entity that intends to use this system to select financial products.

[0699] "Emotional state" refers to the user's psychological state and includes emotions such as stress and relaxation.

[0700] A "financial strategy" refers to an asset management policy formulated based on the user's investment objectives and risk tolerance.

[0701] A "database" refers to an information management system that systematically stores user information and allows for searching and analysis as needed.

[0702] A "machine learning algorithm" refers to a computational method that performs predictions and classifications by analyzing data and learning patterns.

[0703] "Proposal" refers to the act of showing users the most suitable financial products or strategies based on the analysis results.

[0704] As an embodiment for carrying out this invention, the investment guidance AI system is configured as follows.

[0705] First, the user enters information about their investment objectives and risk tolerance through a web browser. This clarifies the user's investment needs and risk profile. The terminal then sends the entered information to the server.

[0706] The server stores the received user information in a database. A data management system such as MySQL is used for the database. The stored information is organized using the Python Pandas library.

[0707] Next, the server uses machine learning algorithms such as Scikit-learn to predict the optimal financial product based on the user's profile. This prediction includes analysis that takes historical data and market trends into account.

[0708] Furthermore, the device uses its camera and microphone to collect information about the user's emotional state. The server then uses TensorFlow to run an emotion recognition model to determine whether the user is stressed or relaxed.

[0709] The server comprehensively analyzes this information and proposes the most suitable financial product to the user. The proposal is customized according to the user's emotional state and risk tolerance.

[0710] For example, if a user provides information indicating they "want to minimize risk" and the system determines they are "feeling stressed," the server will suggest stable financial products.

[0711] Examples of prompts include, "Please suggest the best financial product for a user with a low risk tolerance," and "Please tell me the recommended financial strategy for a user who is experiencing stress."

[0712] The flow of the specific processing in Example 1 will be explained using Figure 17.

[0713] Step 1:

[0714] Users enter information about their investment objectives and risk tolerance through a web browser. This information includes age, investment period, and risk tolerance (low, medium, high). This information serves as foundational data to clarify the user's investment needs.

[0715] Step 2:

[0716] The terminal sends the information entered by the user to the server. The server stores the received information in a MySQL database. The information stored in the database is used for subsequent analysis.

[0717] Step 3:

[0718] The server organizes the stored user information using the Python Pandas library. The organized data is then ready for analysis by machine learning algorithms.

[0719] Step 4:

[0720] The server uses Scikit-learn to predict the optimal financial product based on the user's profile. The input is organized user information, and the output is a list of financial products suitable for the user.

[0721] Step 5:

[0722] The device uses its camera and microphone to collect information about the user's emotional state. This collected data includes the user's facial expressions and tone of voice. This data is used to assess the user's psychological state.

[0723] Step 6:

[0724] The server uses TensorFlow to run an emotion recognition model and analyze the user's emotional state. The input is emotion data sent from the device, and the output is a judgment on whether the user is stressed or relaxed.

[0725] Step 7:

[0726] The server comprehensively analyzes the user's investment information and emotional state to suggest the most suitable financial products. These suggestions are customized according to the user's risk tolerance and emotional state. The output includes the most suitable financial products for the user and the reasons for their selection.

[0727] Step 8:

[0728] The terminal displays the suggested results received from the server to the user. Specifically, the recommended financial products and the reasons for their recommendation are displayed on the web page. The user can then make investment decisions based on this information.

[0729] (Application Example 1)

[0730] Next, we will describe Application Example 1 of Form 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."

[0731] In modern asset management, investors need to choose the optimal investment method from a variety of options, but fully understanding the characteristics and risks of each method is difficult. Furthermore, investors' emotional states can influence their investment decisions, creating a need for emotionally-based investment strategy recommendations. Moreover, a system is needed that can propose the most suitable investment method to investors through real-time sentiment analysis.

[0732] 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.

[0733] In this invention, the server includes means for comparing multiple asset management methods and proposing the optimal asset management method to the user, means for providing asset management support using artificial intelligence based on the knowledge and experience of prominent investors, and means for analyzing the user's emotional state and adjusting the asset management strategy based on that state. This makes it possible to propose the optimal asset management method that takes the user's emotional state into consideration.

[0734] "Asset management methods" is a general term for the financial products and investment methods that individuals and corporations choose to increase their assets.

[0735] "User" refers to an individual or legal entity that uses an asset management system to build wealth.

[0736] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[0737] "Emotional state" refers to the psychological and emotional state of the user and is a factor that influences investment decision-making.

[0738] "Data collection means" refers to a device or method for acquiring information necessary to analyze a user's emotional state in real time.

[0739] "Asset management support tools" refer to a part of a system that provides information and analysis to help users select the optimal asset management method.

[0740] The system for implementing this invention operates in a network environment including a server and terminals. The server runs a program that compares multiple asset management methods and proposes the optimal asset management method to the user. Specifically, the server uses artificial intelligence based on the knowledge and experience of prominent investors to propose the optimal asset management method that takes into account the user's asset management objectives and risk tolerance.

[0741] The device is equipped with data collection capabilities for real-time analysis of the user's emotional state. Specifically, it uses the device's camera and microphone to capture the user's facial expressions and voice tone, and uses an emotion recognition AI model (e.g., Microsoft Azure's Emotion API) to determine their emotional state. This information is sent to a server and used to adjust asset management strategies.

[0742] For example, while a user is using their smartphone, the device's camera captures the user's facial expressions and the microphone analyzes their voice tone. If the emotion recognition AI model detects "stress," the server notifies the device with a message saying, "Based on your current emotional state, we recommend a stable investment strategy."

[0743] An example of a prompt for the generating AI model is, "If the user's emotional state is stress, please suggest a stable investment strategy." Based on this prompt, the server generates an appropriate investment strategy and proposes it to the user.

[0744] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[0745] Step 1:

[0746] The device uses a camera and microphone to collect data in order to analyze the user's emotional state in real time. The input consists of images of the user's facial expressions and audio data. This data is sent to an emotion recognition AI model.

[0747] Step 2:

[0748] The device uses an emotion recognition AI model to determine the user's emotional state from collected facial images and audio data. The input is the data collected in step 1, and the output is the user's emotional state (e.g., stressed, relaxed). This process uses the Microsoft Azure Emotion API to analyze emotions.

[0749] Step 3:

[0750] The terminal sends the determined emotional state to the server. The input is the emotional state obtained in step 2, and the output is the transmission of data to the server.

[0751] Step 4:

[0752] The server uses an AI model to generate optimal investment strategies, taking into account the user's investment goals and risk tolerance, based on the received emotional state. The input is the emotional state and the user's investment information, and the output is a proposal for the optimal investment strategy.

[0753] Step 5:

[0754] The server sends the generated asset management proposal to the terminal. The input is the proposal generated in step 4, and the output is the data transmission to the terminal.

[0755] Step 6:

[0756] The terminal notifies the user of the asset management suggestions received from the server. The input is the suggestions received in step 5, and the output is the notification to the user. Specifically, the terminal screen displays the message, "Based on your current emotional state, we recommend a stable asset management method."

[0757] (Example 2)

[0758] Next, we will describe Example 2 of Form 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".

[0759] Conventional investment support systems have the drawback of not considering the emotional state of the user when making investment suggestions, making it difficult to increase user psychological satisfaction. Furthermore, they lack the ability to propose sophisticated investment strategies that utilize the experience of past investors, and therefore could not effectively support users' asset building.

[0760] 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.

[0761] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user, means for investment support using artificial intelligence based on the experience and knowledge of past investors, and means for analyzing the user's emotional state and making investment suggestions that correspond to those emotions. This makes it possible to make investment suggestions that take the user's emotional state into consideration, thereby increasing psychological satisfaction and supporting effective asset building.

[0762] "Investment methods" is a general term for specific methods and strategies used to increase assets.

[0763] "User" refers to an individual or legal entity that uses the system to conduct investment activities.

[0764] "Artificial intelligence" is a technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0765] "Investment support measures" refer to functions that provide advice and suggestions to help users manage their assets effectively.

[0766] "Emotional state" refers to the psychological state and mood of the user and is a factor that influences investment decisions.

[0767] "Investment proposal" refers to recommendations or advice on specific investment actions given to users.

[0768] An "investment strategy" refers to a set of investment actions or policies planned to achieve a specific objective.

[0769] The following system is constructed as an embodiment of this invention.

[0770] The server first collects the user's investment history and market trend data. Specifically, it retrieves the user's past transaction data from the database and obtains the latest market data using external financial information services. This allows the server to understand the user's investment patterns and market trends.

[0771] Next, the server organizes the data using the Python Pandas library and extracts data features using Scikit-learn. This prepares the foundational data for investment strategies. Furthermore, the server uses a machine learning model built with TensorFlow to predict investment strategies suitable for the user. This model implements an algorithm based on the experience and knowledge of past investors.

[0772] The device analyzes the user's emotional state in real time. Specifically, it captures the user's facial expressions with its camera and analyzes the user's emotions using OpenCV and an emotion analysis library. This allows the device to determine the user's current emotional state.

[0773] The server customizes the generated investment strategy according to the user's emotional state. For example, if the user is happy, it suggests aggressive investments that involve taking risks, while if they are sad, it suggests investments that prioritize safety.

[0774] Users can receive investment suggestions from AI through their devices. Specifically, users can review the suggested investment strategies on their device screens and, if necessary, input prompts into the AI ​​model to request further suggestions. For example, by inputting a prompt such as "Tell me more about a low-risk investment strategy," the AI ​​will present a detailed strategy.

[0775] The flow of the specific processing in Example 2 will be explained using Figure 19.

[0776] Step 1:

[0777] The server collects users' investment history and market trend data. It uses past transaction data from the database and market data from external financial information services as input. Based on this data, the server prepares foundational data to understand users' investment patterns and market trends. The output consists of organized investment history data and market trend data.

[0778] Step 2:

[0779] The server uses the Python Pandas library to organize the collected data and Scikit-learn to extract data features. The input consists of investment history data and market trend data obtained in step 1. Data organization and feature extraction generate foundational data for investment strategies. The output is a dataset with extracted features.

[0780] Step 3:

[0781] The server uses a machine learning model built with TensorFlow to predict an investment strategy suitable for the user. The input is a dataset from which features obtained in step 2 have been extracted. The machine learning model implements an algorithm based on the past experience and knowledge of investors, thereby generating the optimal investment strategy. The output is the investment strategy proposed to the user.

[0782] Step 4:

[0783] The device analyzes the user's emotional state in real time. It uses facial expression data captured by the device's camera as input. Using OpenCV and an emotion analysis library, it analyzes the user's emotions and determines their current emotional state. The output provides information about the user's emotional state.

[0784] Step 5:

[0785] The server customizes the generated investment strategy according to the user's emotional state. The inputs used are the investment strategy obtained in step 3 and the emotional state information obtained in step 4. If the user is happy, it suggests a risky, aggressive investment; if they are sad, it suggests a safety-oriented investment. The output is an investment strategy adjusted according to the user's emotions.

[0786] Step 6:

[0787] The user receives investment proposals from the AI ​​via their device. The adjusted investment strategy obtained in step 5 is used as input. The user can review the proposed investment strategy on the device screen and, if necessary, input prompt sentences into the AI ​​model to request further suggestions. The output is the investment strategy presented to the user, along with additional suggestions based on the prompt sentences entered by the user.

[0788] (Application Example 2)

[0789] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0790] In today's investment environment, it is difficult for individual investors to select the optimal investment strategy. Furthermore, an investor's emotional state can influence investment decisions, posing a risk to wealth creation. Moreover, there is a demand for swift and efficient methods in executing investments. To address these challenges, a sophisticated investment support system that takes into account investors' experience and emotions is necessary.

[0791] 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.

[0792] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user; means for investment support using artificial intelligence based on the experience and knowledge of legendary investors; means including an emotion engine that estimates the user's emotional state and makes investment suggestions based on those emotions; and means for coordinating with an electronic payment service to immediately execute the proposed investment. As a result, the user can receive optimal investment suggestions tailored to their emotions and execute investments quickly.

[0793] An "investment method" refers to the specific investment methods and strategies used to increase one's assets.

[0794] "Users" refers to individual investors or customers who use this system.

[0795] "Artificial intelligence" is a technology that allows computers to mimic human intelligence and perform learning and reasoning.

[0796] "Investment support measures" refer to functions and technologies that support users in making optimal investments.

[0797] The "emotional engine" is part of a system that analyzes the emotional state of users and makes investment recommendations based on the results.

[0798] An "electronic payment service" is an online payment system that allows for the sending and receiving of funds via the internet.

[0799] "Suggested investments" refer to specific investment options or strategies that the system recommends to the user.

[0800] The system for carrying out this invention includes a server, a user terminal, and an electronic payment service. The server runs a program to compare multiple investment methods and propose the optimal investment method to the user. The server analyzes the user's investment history and market trends using artificial intelligence based on the experience and knowledge of legendary investors. Furthermore, the server uses an emotion engine to estimate the user's emotional state obtained from the user terminal and makes investment suggestions based on that emotion.

[0801] The user terminal is a device such as a smartphone or tablet that receives investment proposals from the server and notifies the user. The user terminal uses cameras and sensors to capture the user's facial expressions and voice, and sends data to the server to estimate their emotional state.

[0802] Electronic payment services work in conjunction with servers to provide online payment functionality for immediately executing proposed investments. This allows users to invest quickly and efficiently.

[0803] As a concrete example, the server analyzes the user's investment history and current market trends and generates a prompt message saying, "We have analyzed your investment history and current market trends. Now is a good time to invest. Do you want to proceed with the investment?" This prompt message is sent to the user's terminal, and if the user selects "Yes," the investment is executed through the electronic payment service.

[0804] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[0805] Step 1:

[0806] The server collects user investment history data and market trend data. It receives the user's past investment history and current market data as input, and feeds this data into a generating AI model. Data processing involves pattern analysis of investment history and extraction of market trends to generate foundational data for proposing optimal investment strategies. The analysis results are obtained as output.

[0807] Step 2:

[0808] The server receives emotion data from the user terminal. It receives facial expression data and voice data transmitted from the user terminal as input and feeds them into the emotion engine. As data processing, it estimates the user's emotional state using an emotion recognition algorithm. The output is data indicating the user's emotional state.

[0809] Step 3:

[0810] The server integrates analysis results and emotional state data to generate optimal investment recommendations for the user. It receives the analysis results from Step 1 and the emotional state data from Step 2 as input, and uses a generative AI model to generate prompt messages. Specifically, it creates a prompt message such as, "We have analyzed your investment history and current market trends. Now is a good time to invest. Do you wish to proceed?" The output is the generated prompt message.

[0811] Step 4:

[0812] The server sends the generated prompt message to the user terminal. It receives the prompt message generated in step 3 as input and sends it to the user terminal. The output is the prompt message displayed on the user terminal.

[0813] Step 5:

[0814] The user reviews the prompt displayed on the terminal and selects whether to proceed with the investment. The user selects "Yes" or "No" in response to the prompt as input. The output is response data based on the user's selection.

[0815] Step 6:

[0816] The server executes the investment through an electronic payment service based on the user's selection. It receives user selection data as input and calls the electronic payment service's API. As data calculations, it calculates the investment amount and processes the payment. As output, it sends a confirmation message to the user's terminal.

[0817] (Example 3)

[0818] Next, we will describe Embodiment 3 of Embodiment Example 3. 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".

[0819] Conventional asset building support systems have faced challenges in flexibly adjusting investment strategies in response to changes in users' financial situation and emotions, and therefore failing to propose optimal investment methods. In particular, the lack of adjustments to investment strategies that take into account changes in users' emotions resulted in insufficient risk management.

[0820] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[0821] In this invention, the server includes means for comparing multiple investment options and proposing the most suitable investment option to the user; means for providing investment guidance using artificial intelligence based on past investment experience and knowledge; means for supporting the user's asset building; means for periodically analyzing the user's asset information and adjusting the investment strategy; and means for detecting changes in the user's emotions in real time and adjusting the investment strategy. This makes it possible to propose flexible and optimal investment strategies that respond to the user's asset situation and emotional changes.

[0822] "Investment methods" is a general term for financial products and investment methods that users can choose to increase their assets.

[0823] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[0824] "Investment guidance tools" refer to systems and processes designed to propose optimal investment methods to users and support their asset building.

[0825] "Asset building" is the process by which users increase their assets over the long term and achieve their financial goals.

[0826] "Asset information" refers to data about a user's financial assets, including balances, investment amounts, and asset types.

[0827] An "investment strategy" is a plan or policy for efficiently managing assets and optimizing risk and return.

[0828] "Emotional change" refers to a change in the user's psychological state, including emotional shifts such as stress and feelings of relief.

[0829] A description of embodiments for carrying out this invention will be given.

[0830] The server runs a program that compares multiple investment options and proposes the optimal investment method to support users in building their assets. This program uses artificial intelligence to provide investment guidance based on past investment experience and knowledge. Specifically, the server periodically collects users' asset information and inputs it into an AI model for analysis. This AI model considers the user's investment objectives and risk tolerance to generate the optimal investment strategy.

[0831] The device uses sensors from a smartwatch or smartphone to detect changes in the user's emotions in real time. This collects data such as heart rate and voice tone, which is then input into the emotion engine. The emotion engine analyzes this data and adjusts the investment strategy according to the user's emotional changes.

[0832] For example, if a user sets a savings goal of 1 million yen, the server uses AI to detect when the user's assets reach 1 million yen and notifies the user. Furthermore, it can suggest a next savings goal of 2 million yen.

[0833] Examples of prompts for the generating AI model include "Generate a notification message when the user's assets reach their target amount" and "Suggest adjustments to the investment strategy based on the user's emotional changes."

[0834] In this way, the system can provide a flexible and optimal investment strategy that responds to the user's asset situation and emotional changes. The flow of the specific processing in Example 3 will be explained using Figure 21.

[0835] Step 1:

[0836] The server collects user asset information. Specifically, it retrieves data from bank accounts and investment accounts via APIs. This data includes balances, investment amounts, and asset types. Input is data from the user's financial institutions, and output is asset information stored on the server.

[0837] Step 2:

[0838] The server inputs the collected asset information into an AI model to analyze the asset status. The AI ​​model evaluates asset increases and decreases by comparing them with past data and determines whether the goals have been achieved. The input is the asset information obtained in step 1, and the output is the result of the asset status analysis.

[0839] Step 3:

[0840] The server adjusts investment strategies based on the analysis results and proposes new investment opportunities. Specifically, the AI ​​predicts market trends and selects investment targets considering risk and return. The input is the analysis results from step 2, and the output is investment proposals for the user.

[0841] Step 4:

[0842] The device collects the user's emotional data in real time. Using sensors in smartwatches and smartphones, it detects changes in emotion from data such as heart rate and voice tone. The input is data from sensors, and the output is emotional data.

[0843] Step 5:

[0844] The terminal uses an emotion engine to analyze the user's emotional changes and adjust the investment strategy as needed. For example, if the user is feeling stressed, the emotion engine instructs the server to switch to a lower-risk investment strategy. The input is the emotional data from step 4, and the output is the adjusted investment strategy.

[0845] Step 6:

[0846] The server integrates the analysis results of emotional and asset data and provides feedback to the user. Specifically, it generates and sends a report to the user explaining the achievement status of asset goals and the reasons for strategic changes based on emotions. The input is the output of steps 3 and 5, and the output is the feedback report to the user.

[0847] (Application Example 3)

[0848] Next, we will describe application example 3 of form example 3. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 as the "terminal".

[0849] In modern wealth building, users need to adapt to diverse investment methods and market fluctuations, but individual emotional changes also influence investment decisions. However, conventional systems do not adjust investment strategies to take user emotions into account, making it difficult to optimize wealth building.

[0850] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[0851] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user; means for providing investment guidance using artificial intelligence based on the investor's experience and knowledge; means for recognizing the user's emotions in real time and adjusting the investment strategy according to changes in those emotions; and means for periodically analyzing the user's asset status and notifying the user of the progress toward achieving investment goals. This makes it possible to provide flexible investment strategies that take into account changes in the user's emotions.

[0852] An "investment method" refers to the specific financial products or strategies chosen to increase one's assets.

[0853] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[0854] "Investment guidance methods" refer to methods for proposing optimal investment strategies to users and supporting their asset building.

[0855] "Emotion recognition means" refers to technology that detects a user's emotional state in real time and adjusts the system's operation based on that information.

[0856] "Asset analysis methods" refer to methods for periodically evaluating a user's asset situation and determining whether their investment goals are being achieved.

[0857] An "investment strategy" is a plan or set of guidelines established to effectively manage assets.

[0858] "Asset building" is the process by which individuals and organizations increase their assets and achieve financial stability.

[0859] The system for carrying out this invention includes a server, a user terminal, and an emotion recognition device. The server is equipped with artificial intelligence to periodically analyze the user's asset status and suggest the optimal investment method. The user terminal is a device such as a smartphone or computer, which receives notifications from the server and provides information to the user. The emotion recognition device detects the user's emotions in real time and transmits that data to the server.

[0860] The server analyzes the user's asset status based on information obtained from a financial database. Based on the analysis results, the server notifies the user of their progress toward investment goals and proposes new investment strategies. An emotion recognition device detects the user's emotional state and sends this information to the server, which is used to adjust the investment strategy.

[0861] As a concrete example, if a user is experiencing stress, the emotion recognition device sends this information to a server. The server considers the user's emotional state and proposes a safety-oriented investment strategy. Using a generative AI model, it generates the optimal strategy based on the prompt, "What investment strategy should be proposed if the user is experiencing stress?"

[0862] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[0863] Step 1:

[0864] The server retrieves user asset information from a financial database. It uses the user's account information as input. The output is user asset status data. Based on this data, the server prepares to analyze the user's asset status.

[0865] Step 2:

[0866] The server analyzes the acquired asset status data and evaluates the user's progress toward achieving their investment goals. Asset status data is used as input. An evaluation result showing the progress toward investment goals is obtained as output. Based on this evaluation result, the server determines what to notify the user about.

[0867] Step 3:

[0868] Emotion recognition devices detect a user's emotional state in real time. They use the user's biometric information and behavioral data as input. The output is the user's emotional state data. This data is sent to a server to help adjust investment strategies based on emotions.

[0869] Step 4:

[0870] The server receives emotional state data and generates an investment strategy tailored to the user's emotions. It uses emotional state data and asset status evaluation results as input. The output is an adjusted investment strategy. Using a generative AI model, it generates the optimal strategy based on the prompt, "What investment strategy should be proposed if the user is experiencing stress?"

[0871] Step 5:

[0872] The server notifies the user terminal of the adjusted investment strategy. It uses the adjusted investment strategy as input and generates a notification message for the user as output. The user receives this notification and can consider changing their investment strategy.

[0873] (Other examples)

[0874] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[0875] 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.

[0876] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> 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.

[0877] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[0878] 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.

[0879] [Third Embodiment]

[0880] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0881] 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.

[0882] 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).

[0883] 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.

[0884] 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.

[0885] 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).

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[0892] "Example of form 1"

[0893] One embodiment of the present invention is an investment guidance AI system. This system has means for comparing multiple investment methods and proposing the optimal investment method to the user. Specifically, it compares investment methods such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA, and proposes the optimal investment method based on information such as the user's investment objectives and risk tolerance.

[0894] "Example of form 2"

[0895] Furthermore, one embodiment of this invention is an AI-powered investment guidance system based on the experience and intellect of legendary investors. This AI uses algorithms based on the investors' experience and intellect to support the user's asset building. Specifically, the AI ​​analyzes the user's investment history and market trends and proposes the optimal investment strategy.

[0896] "Example of form 3"

[0897] Furthermore, one embodiment of the present invention involves means of supporting the user's asset building. Specifically, the AI ​​periodically analyzes the user's asset status and adjusts investment strategies or suggests new investment opportunities. For example, if the user's assets reach a certain target, the AI ​​notifies the user of this information and assists in setting new investment targets.

[0898] The following describes the processing flow for each example of the form.

[0899] "Example of form 1"

[0900] Step 1: The user enters information such as their investment objectives and risk tolerance into the system.

[0901] Step 2: The system compares multiple investment methods (such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA).

[0902] Step 3: The system proposes the optimal investment method based on the user's information.

[0903] "Example of form 2"

[0904] Step 1: The AI ​​uses algorithms based on the experience and intellect of legendary investors to analyze the user's investment history and market trends.

[0905] Step 2: The AI ​​proposes the optimal investment strategy based on the analysis results.

[0906] "Example of form 3"

[0907] Step 1: The AI ​​periodically analyzes the user's asset status.

[0908] Step 2: The AI ​​adjusts investment strategies and suggests new investment opportunities.

[0909] Step 3: When the AI ​​reaches a certain target for the user's assets, it notifies the user of this information and helps them set new investment goals.

[0910] (Example 1)

[0911] Next, we will describe Embodiment 1 of Embodiment 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."

[0912] In today's financial markets, users are required to make the optimal choices from a diverse range of financial products, which necessitates specialized knowledge and analysis. In particular, selecting the most suitable financial product based on a user's financial goals and risk tolerance is challenging, and there is a need for a system that can provide efficient and accurate recommendations.

[0913] 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.

[0914] In this invention, the server includes means for comparing multiple financial products and suggesting the most suitable financial product to the user, means for data analysis using historical market data and machine learning algorithms, and means for supporting the user's financial goals. This enables the user to efficiently select the most suitable financial product based on their own profile.

[0915] "Financial products" refer to products that are the subject of investment or asset management, and include individual defined contribution pension plans, small-amount investment tax exemption schemes, installment investment schemes, and junior investment schemes.

[0916] "User" refers to an individual or corporation that selects financial products and engages in investment or asset management.

[0917] "Means of proposing the optimal financial product" refers to the methods and processes for comparing multiple financial products based on the user's financial goals and risk tolerance, and selecting the most suitable product.

[0918] "Data analysis methods" refer to methods and processes for analyzing data using machine learning algorithms based on past market data and user input information, in order to provide users with useful information.

[0919] "Means to support financial goals" refers to methods and processes that provide the information and suggestions necessary to achieve the financial goals set by the user, and that support asset building.

[0920] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze user profiles and market data to propose the most suitable financial products.

[0921] As an embodiment for carrying out this invention, the investment guidance AI system is constructed as follows.

[0922] The server generates a program for an investment guidance AI system. This program is designed to suggest the most suitable financial products to the user. The server uses programming languages ​​such as Python and R to analyze historical market data and user input information. This allows for data analysis based on the user's risk tolerance and financial goals.

[0923] The server uses a generative AI model to create a user profile. This profile includes information such as the user's age, investment objectives, risk tolerance, and investment period. Based on this information, the server compares multiple financial products and selects the most suitable one.

[0924] The terminal provides an interface for users to access the system and enter necessary information. Users can enter prompt messages through the terminal, such as the following:

[0925] "I'm in my 40s and want to increase my assets while minimizing risk. Could you please tell me which investment method is best?"

[0926] "I want to save money for my child's college education. What investment method would be suitable?"

[0927] Upon receiving these prompts, the server suggests the most suitable financial products based on the user's profile. This suggestion is then communicated to the user via their terminal. This allows the user to efficiently make investments that align with their financial goals.

[0928] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0929] Step 1:

[0930] Users access the system through their terminals and enter information such as their investment objectives, age, risk tolerance, and investment period. This information is sent to the server and serves as the basis for creating the user's profile.

[0931] Step 2:

[0932] The server creates a profile based on the user information it receives. Using programming languages ​​such as Python or R, the server analyzes the input data and quantifies the user's risk tolerance and financial targets. This profile is then used for subsequent data analysis.

[0933] Step 3:

[0934] The server uses a generative AI model to analyze historical market data and user profiles. The server applies machine learning algorithms to perform data analysis to identify the most suitable financial products for the user. During this process, the risk and return of each financial product are evaluated.

[0935] Step 4:

[0936] Based on the analysis results, the server suggests the most suitable financial products to the user. These suggestions are then communicated to the user via their terminal. Specifically, if the user has a low risk tolerance, financial products that offer stable returns may be suggested.

[0937] Step 5:

[0938] Users review the suggested financial products on their devices and make investment decisions as needed. Based on these suggestions, users can make investment decisions that align with their financial goals.

[0939] (Application Example 1)

[0940] Next, we will describe Application Example 1 of Form 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."

[0941] In today's investment environment, it is difficult for individual investors to select the optimal investment method that suits their investment objectives and risk tolerance. Furthermore, there is a lack of support for investors to effectively compare the diverse range of available investment options and make the best choices. Therefore, there is a need for a system that enables investors to build wealth efficiently and effectively.

[0942] 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.

[0943] In this invention, the server includes means for comparing multiple investment options and suggesting the optimal investment option to the user; means for analyzing past investment data and suggesting the optimal investment option based on the user's investment history and spending patterns; means for collecting the user's financial data and formatting and analyzing the data; means for using a machine learning model to predict the optimal investment option based on the user's risk tolerance and investment objectives; and means for providing a user interface that allows the user to compare and select investment plans. This makes it possible for the user to easily select the optimal investment option according to their own investment objectives and risk tolerance.

[0944] "Investment methods" is a general term for financial products and systems used to increase assets, and includes individual defined contribution pension plans and small-amount investment tax exemption schemes.

[0945] "User" refers to an individual or legal entity that uses the system to select and manage investments.

[0946] "Investment history" refers to a record of past investment activities, including information such as investment amount, investment destination, and investment period.

[0947] "Spending patterns" indicate the user's spending habits and show how much money they spend on what items.

[0948] "Financial data" refers to financial information such as a user's assets, liabilities, income, and expenses, and is the basic data necessary for investment decisions.

[0949] A "machine learning model" is a computational model that uses algorithms to learn patterns from data and perform predictions and classifications.

[0950] "Risk tolerance" is an indicator that shows the range of risk an investor can tolerate, and it represents an individual investor's attitude and ability to handle risk.

[0951] "Investment objectives" refer to the specific goals and intentions when making an investment, and include increasing assets, diversifying risk, and preparing for future funding needs.

[0952] A "user interface" refers to the screens and operating methods that allow users to interact with a system, and is a means of inputting information and displaying results.

[0953] To implement this invention, it is necessary to build a system in which a server plays a central role. The server will be programmed using Python, and the backend will be built using the Flask framework. Pandas and Scikit-learn will be used for data analysis. This will enable the server to collect users' financial data and to format and analyze the data.

[0954] Specifically, the server analyzes the user's investment history and spending patterns, and uses machine learning models to predict the optimal investment strategy based on the user's risk tolerance and investment objectives. This allows users to easily select the most suitable investment strategy according to their own investment objectives and risk tolerance.

[0955] The terminal provides a user interface, allowing users to compare and select investment plans. Users can receive information from the server via their smartphone or computer and make investment choices.

[0956] For example, if a user enters "I want to invest 50,000 yen per month," the server analyzes past spending data and assesses their risk tolerance. As a result, it can suggest that Tsumitate NISA (a type of tax-advantaged investment account) is the optimal option.

[0957] An example of a prompt to input into the generating AI model is: "The user's monthly investment limit is 50,000 yen, and their risk tolerance is moderate. Please suggest the optimal investment method."

[0958] In this way, by coordinating servers, terminals, and users, an efficient and effective investment support system can be realized.

[0959] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0960] Step 1:

[0961] The server receives input data from the user. This input data includes the user's available investment amount, risk tolerance, and investment objectives. Based on this data, the server understands the user's investment needs.

[0962] Step 2:

[0963] The server uses Pandas to retrieve users' past investment history and spending patterns from a database, then formats and analyzes the data. Input includes past transaction history and spending records, which are used to extract trends in the user's investment behavior. The output provides characteristics of the user's investment behavior.

[0964] Step 3:

[0965] The server uses Scikit-learn to run a machine learning model and predict the optimal investment strategy based on the user's risk tolerance and investment objectives. The input consists of formatted investment history data and the user's risk tolerance, which are used to calculate the optimal investment strategy. The output is a list of recommended investment strategies.

[0966] Step 4:

[0967] The server generates prompt messages using a generative AI model. The input includes the user's investment needs and predicted investment methods, and the server creates prompt messages based on this information. The output is a prompt message to be presented to the user.

[0968] Step 5:

[0969] The terminal displays prompt messages received from the server and recommended investment options to the user. The user can review the information presented through the terminal and make an investment choice.

[0970] Step 6:

[0971] The user selects an investment option presented through the terminal and executes the investment as needed. The input is recommended information from the server, which the user uses to make investment decisions. The output is the selected investment option.

[0972] In this way, servers, terminals, and users work together to achieve efficient and effective investment support.

[0973] (Example 2)

[0974] Next, we will describe Example 2 of the morphological example. 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."

[0975] Conventional investment support systems have been unable to fully utilize users' investment history and market trends, making it difficult to propose optimal investment strategies. Furthermore, they have not been able to use algorithms that leverage the experience of legendary investors, thus failing to effectively support users' asset building.

[0976] 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.

[0977] In this invention, the server includes means for receiving investment history entered by the user, means for collecting market data, and means for analyzing the collected data and generating an optimal investment strategy. This makes it possible to propose an optimal investment strategy based on the user's investment history and market trends.

[0978] "A means of receiving user-entered investment history" refers to a function that allows users to input records of their past investment activities into the system and retrieve that information.

[0979] "Means for collecting market data" refers to a function that obtains information about financial markets from external information services and makes it available within the system.

[0980] "A means of analyzing collected data and generating the optimal investment strategy" refers to a function that analyzes the user's acquired investment history and market data to calculate and propose the most suitable investment method for the user.

[0981] "A method that uses algorithms based on the experience and knowledge of legendary investors" refers to a function that uses computational methods built on the past success stories and insights of prominent investors to formulate investment strategies.

[0982] "Means of supporting users' asset building" refers to functions that provide advice and strategies for users to efficiently increase their assets and support their asset management.

[0983] To implement this invention, it is first necessary to generate a program on the server that receives investment history from users. This program has the function of receiving investment history entered by the user through a dedicated terminal or web application. Users can enter information such as past stock purchase and sale history and investment amount.

[0984] Next, the server collects market data. This data collection utilizes data from financial information services. Specifically, it obtains market data such as stock indices, exchange rates, and economic indicators from services like Yahoo Finance and Bloomberg.

[0985] The server uses machine learning libraries such as Python's Pandas library and Scikit-learn to analyze the user's investment history and market data. This makes it possible to identify past investment patterns and compare them with current market trends.

[0986] Based on the analysis results, the server uses a generative AI model to generate the optimal investment strategy. This generated strategy is designed to maximize returns while minimizing risk.

[0987] Finally, the server proposes the generated investment strategy to the user. The user can review the proposed strategy and make adjustments as needed.

[0988] As a concrete example, a user might enter a prompt message such as, "Based on my investment history over the past five years, please suggest a future investment strategy." Upon receiving this prompt, the server analyzes the user's investment history and market data, generates a specific investment strategy such as, "You should focus on technology stocks for the next six months," and proposes it to the user.

[0989] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0990] Step 1:

[0991] The user enters their investment history.

[0992] Users input their past investment history through a dedicated terminal or web application. This data includes stock purchase and sale history, investment amounts, and other information. This input data is sent to a server and stored in a database.

[0993] Step 2:

[0994] The server collects market data.

[0995] The server collects market data from financial information services. Specifically, it obtains data such as stock indices, exchange rates, and economic indicators via APIs. This data is updated in real time and stored in a database on the server.

[0996] Step 3:

[0997] The server analyzes the data.

[0998] The server uses the Python Pandas library to analyze the user's investment history and collected market data. The input data consists of the user's investment history and market data. Based on this data, the server identifies past investment patterns and compares them to current market trends. The analysis results are used in the next step.

[0999] Step 4:

[1000] The server generates the investment strategy.

[1001] The server uses a generative AI model to generate the optimal investment strategy based on the analysis results. The analysis results are used as input. The server calculates a strategy to maximize returns while minimizing risk and creates specific investment proposals.

[1002] Step 5:

[1003] The server proposes investment strategies to the user.

[1004] The server notifies the user of the generated investment strategy. The specific investment strategy is sent to the user's terminal as output. The user can review the proposed strategy and make adjustments as needed.

[1005] (Application Example 2)

[1006] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server," and the headset-type terminal 314 will be referred to as a "terminal."

[1007] In today's investment environment, it is difficult for individual investors to formulate optimal investment strategies based on vast amounts of information. Furthermore, there is a lack of means to receive real-time advice based on investors' experience and knowledge. Therefore, there is a need for support systems that enable investors to build wealth efficiently and effectively.

[1008] 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.

[1009] This invention includes a server that compares multiple investment methods and proposes the optimal investment method to the user, an artificial intelligence-based investment support method based on the experience and knowledge of legendary investors, and a method that analyzes the user's investment history and market trends and proposes the optimal investment strategy in real time. This enables the user to efficiently develop an investment strategy.

[1010] An "investment method" refers to the specific methods and strategies used to increase one's assets.

[1011] A "user" refers to an individual or legal entity that uses this system to conduct investment activities.

[1012] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and perform learning and reasoning.

[1013] "Investment support measures" refer to support functions provided to help users make optimal investment decisions.

[1014] "Investment history" refers to a record of the user's past investment activities.

[1015] "Market trends" refer to price fluctuations and trends in financial markets.

[1016] "Real-time" refers to information being processed instantly the moment it is generated.

[1017] An "investment strategy" is a set of action plans designed to achieve specific investment objectives.

[1018] A "smartphone" is a portable device that, in addition to the functions of a mobile phone, possesses multiple functions similar to those of a computer.

[1019] An "application" is a software program designed to provide a specific function or service.

[1020] The system for implementing this invention consists of a server and a user's terminal (smartphone). The server runs a generative AI model built using Python and calculates investment strategies using TensorFlow. The server provides an API using Flask and accepts requests from the user's terminal. SQLite is used as the database to manage the user's investment history and market trend data.

[1021] The user's device communicates with a server via a dedicated application, allowing them to receive real-time investment advice. This application sends the user's investment history to the server and displays the investment strategies received from the server.

[1022] For example, if a user has previously invested heavily in technology-related assets, the server will analyze market trends in the technology sector and propose future investment strategies. Based on these suggestions, the user can then decide on their next investment actions.

[1023] An example of a prompt message is: "Based on the user's past investment history, please suggest the optimal investment strategy considering current market trends."

[1024] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1025] Step 1:

[1026] The user's device collects investment history data as input. This data includes past investment amounts, investment destinations, and investment periods. The collected data is sent to the server.

[1027] Step 2:

[1028] The server receives the investment history data as input and stores it in a database. Next, it preprocesses the data and converts it into a format suitable for the generative AI model. This preprocessing includes data normalization and imputation of missing values.

[1029] Step 3:

[1030] The server inputs pre-processed investment history data and market trend data into a generating AI model. The model analyzes the data using TensorFlow and outputs the optimal investment strategy. This analysis includes analysis of past market trends and risk assessment.

[1031] Step 4:

[1032] The server sends the investment strategy generated by the AI ​​model to the user's terminal. This investment strategy includes recommended investment targets, investment amounts, and risk assessments.

[1033] Step 5:

[1034] The user's device displays the investment strategy received from the server. Based on this information, the user can decide on their next investment action. Specifically, the application visually displays the investment strategy to make it easy for the user to understand.

[1035] (Example 3)

[1036] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[1037] Conventional asset building support systems have struggled to effectively utilize users' financial information and propose optimal investment strategies tailored to their individual asset situations. Furthermore, they were unable to evaluate users' progress toward asset goals in real time and adjust investment strategies at appropriate times.

[1038] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1039] In this invention, the server includes means for collecting and storing the user's financial information in a database, means for preprocessing the collected financial information and converting it into an analyzable format, and means for analyzing the user's asset status using a generative AI model and predicting future asset trends. This makes it possible to propose an optimal investment strategy tailored to the user's individual asset situation.

[1040] "User" refers to an individual or legal entity that provides financial information and utilizes the asset building support system.

[1041] "Financial information" refers to data necessary to understand a user's asset status, such as their account balance, investment portfolio details, and transaction history.

[1042] A "database" refers to an information management system that stores collected financial information and makes it accessible as needed.

[1043] "Preprocessing" refers to processes such as data cleaning and normalization performed to convert collected financial information into an analyzable format.

[1044] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to analyze a user's asset situation and predict future asset trends.

[1045] "Asset status" refers to information that shows the current state and composition of a user's assets.

[1046] An "investment strategy" refers to specific investment policies and action plans proposed to optimize a user's asset building.

[1047] To implement this invention, a server must first collect the user's financial information and store it in a database. The server retrieves data such as account balances, investment portfolio details, and transaction history from financial institutions via an API. This data is stored in the database for later analysis.

[1048] Next, the server preprocesses the collected financial information. Specifically, it cleans and normalizes the data and imputes missing values. This process transforms the data into a format suitable for analysis by generative AI models. Data analysis libraries such as "Pandas" and "NumPy" are sometimes used for preprocessing.

[1049] Subsequently, the server analyzes the user's asset status using a generative AI model. This AI model is built using machine learning frameworks such as "TensorFlow" and "PyTorch," and predicts future asset trends based on the user's past data. The AI ​​model evaluates how well the user's assets are progressing towards their set goals and proposes the optimal investment strategy.

[1050] For example, if a user sets a goal of "doubling their assets within five years," the server will periodically collect asset data and analyze it using an AI model. The AI ​​model may suggest a shift to a lower-risk investment strategy once the user's assets reach 80% of their goal. This suggestion may include recommendations for specific investment targets and amounts.

[1051] An example of a prompt to be input to the generating AI model is, "Please suggest the next steps once the user's assets reach their target." This prompt prompts the AI ​​to generate specific advice to help the user set new investment goals. The specific processing flow in Example 3 is explained using Figure 15.

[1052] Step 1:

[1053] The server collects users' financial information. As input, it uses the user's authentication credentials to access financial institutions' APIs and retrieve data such as account balances, investment portfolio details, and transaction history. As output, it stores the retrieved data in a database. Specifically, the server periodically executes scheduled jobs to collect the latest financial information.

[1054] Step 2:

[1055] The server preprocesses the collected financial information. It uses raw data stored in a database as input. The output is data converted into an analyzable format. Specific data processing involves cleaning the data, imputing missing values, and normalizing the data as needed. This makes the data suitable for analysis by AI models.

[1056] Step 3:

[1057] The server analyzes the user's asset status using a generative AI model. Pre-processed data is supplied to the AI ​​model as input. The output is a prediction of the user's asset trends. Specifically, the AI ​​model uses machine learning algorithms to predict future asset trends based on past data. This prediction shows how well the user's assets are progressing towards their goals.

[1058] Step 4:

[1059] The server proposes the optimal investment strategy to the user based on the analysis results. It uses the prediction results of an AI model as input and generates specific investment strategy suggestions as output. Specifically, the server selects investment targets with reduced risk and presents investment opportunities in emerging markets, depending on the user's risk tolerance and investment goals.

[1060] Step 5:

[1061] The server notifies the user of the proposed investment strategy. It uses the generated investment strategy proposal as input and generates a notification message for the user as output. Specifically, the server communicates the details of the investment strategy to the user via email or in-app notifications. The user can then set new investment goals based on this information.

[1062] (Application Example 3)

[1063] Next, we will describe application example 3 of form example 3. 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."

[1064] In modern asset management, users need to adapt to diverse investment methods and market fluctuations, but there is a lack of support systems to efficiently handle these challenges. Furthermore, there is a need to monitor progress toward asset goals in real time and appropriately suggest new investment opportunities. Therefore, the challenge lies in providing a system that enables users to manage their assets optimally and effectively advance their wealth building.

[1065] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1066] In this invention, the server includes means for comparing multiple asset management methods and proposing the optimal asset management method to the user; means for providing asset management support using artificial intelligence based on past investment experience and knowledge; means for periodically analyzing the user's asset status and notifying the user of the progress toward achieving asset goals; and means for analyzing market trends and proposing new investment opportunities. This enables the user to manage their assets efficiently and effectively and advance their wealth accumulation.

[1067] "Asset management methods" refer to investment and savings methods used by individuals and corporations to increase their assets, and specifically include stocks, bonds, investment trusts, real estate, etc.

[1068] "User" refers to an individual or legal entity that uses this system for asset management.

[1069] "Artificial intelligence" is a technology in which computer systems imitate human intelligence to learn and reason, and in particular, in asset management, it is used to propose investment strategies and perform market analysis.

[1070] "Asset status" refers to information such as the type, quantity, and appraised value of assets held by the user, and serves as basic data for asset management.

[1071] "Asset targets" refer to the purpose of asset management and the amount of assets that users wish to achieve, and serve as guidelines for asset building.

[1072] "Market trends" refer to price fluctuations and trends in financial markets, changes in economic indicators, etc., and serve as a basis for making investment decisions.

[1073] An "investment opportunity" refers to a situation or condition under which one can make new investments to increase their assets, and represents an investment option that is advantageous to the user.

[1074] The system for implementing this invention consists of a network environment including a server and user terminals. The server executes programs developed using Python and consists of a backend using Flask and a frontend using React Native. TensorFlow is used for the artificial intelligence model.

[1075] The server retrieves data from users' bank and investment accounts via APIs. This data represents the user's asset status, and the server uses it to analyze asset management strategies. Specifically, an artificial intelligence model using TensorFlow evaluates the user's asset status and market trends, and proposes the optimal asset management method.

[1076] The user's device runs an application built with React Native and receives notifications from the server. When the user's asset goals are achieved, the server notifies the user via push notification. The server also analyzes market trends and suggests new investment opportunities to the user.

[1077] For example, if a user has set an asset goal of 1 million yen, the server will send a notification saying, "You are 50,000 yen away from your goal. Would you like to explore new investment opportunities?" when the user's assets reach 950,000 yen. An example of a prompt to input into the generating AI model would be, "Analyze the user's asset situation and suggest the optimal investment strategy. Current assets are 950,000 yen, and the goal is 1 million yen."

[1078] The flow of the specific processing in Application Example 3 will be explained using Figure 16.

[1079] Step 1:

[1080] The server retrieves data from users' bank and investment accounts via an API. The input is the user's authentication information, and the output is data showing the user's asset status. This data includes the type and value of the user's assets. The server stores this data in a database.

[1081] Step 2:

[1082] The server executes a generative AI model using TensorFlow and analyzes the user's asset status data as input. The input is the asset status data obtained in step 1, and the output is a proposal for the optimal asset management method. The server generates the optimal investment strategy considering the user's asset goals and risk tolerance.

[1083] Step 3:

[1084] The server evaluates whether the user's assets are approaching their set target. The input is the user's current asset amount and the set asset target, and the output is the evaluation result of the target achievement status. The server calculates the remaining amount to reach the target and prepares to notify the user.

[1085] Step 4:

[1086] The server analyzes market trends and proposes new investment opportunities. The input is real-time market data, and the output is a list of investment opportunities favorable to the user. The server uses a generative AI model to analyze market data and identify investment opportunities.

[1087] Step 5:

[1088] The device receives notifications from the server and displays them to the user. The input is notification data sent from the server, and the output is a push notification to the user. The device displays the user's progress toward their asset goals and new investment opportunities, prompting the user to take the next action.

[1089] 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.

[1090] "Example of form 1"

[1091] One embodiment of the present invention is a system incorporating an emotion engine. This system recognizes the user's emotions and adjusts the investment strategy based on that emotional state. Specifically, when the user is feeling stressed, it avoids high-risk investments and recommends stable investments. Conversely, when the user is relaxed, it determines that they are willing to take risks and proposes high-return investments.

[1092] "Example of form 2"

[1093] Furthermore, the emotion engine makes investment suggestions that take the user's emotional state into account. For example, when a user is feeling happy, it suggests investments that will amplify that happiness. Conversely, when a user is feeling sad, it suggests investments that will alleviate that sadness.

[1094] "Example of form 3"

[1095] Furthermore, the emotion engine captures changes in the user's emotions in real time and instantly adjusts the investment strategy accordingly. For example, if a user suddenly experiences a situation that causes significant stress, the emotion engine immediately detects this change and switches the investment strategy to a more safety-oriented approach.

[1096] The following describes the processing flow for each example of the form.

[1097] "Example of form 1"

[1098] Step 1: The emotion engine recognizes the user's emotions in real time.

[1099] Step 2: Adjust investment strategies based on the emotional state recognized by the emotion engine. Specifically, when the user is feeling stressed, avoid high-risk investments and recommend stable investments.

[1100] Step 3: When the user is relaxed, we assume they are willing to take risks and propose high-return investments.

[1101] "Example of form 2"

[1102] Step 1: The emotion engine recognizes the user's emotions in real time.

[1103] Step 2: The emotion engine makes investment suggestions based on the emotional state it recognizes. For example, when a user is feeling happy, it suggests investments that will amplify that happiness.

[1104] Step 3: When a user is feeling sad, suggest an investment that will alleviate that sadness.

[1105] "Example of form 3"

[1106] Step 1: The emotion engine captures changes in the user's emotions in real time.

[1107] Step 2: Instantly adjust your investment strategy in response to the emotional changes detected by the emotional engine.

[1108] Step 3: For example, if a user suddenly experiences a situation that causes them significant stress, the emotion engine will immediately detect this change and switch to a safer investment strategy.

[1109] (Example 1)

[1110] Next, we will describe Embodiment 1 of Embodiment 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."

[1111] Conventional financial product selection systems did not take into account the emotional state of users, making it difficult to propose the most suitable financial products based on their psychological condition. Furthermore, there was a lack of effective means to collect and analyze user information, making it impossible to provide personalized recommendations to individual users.

[1112] 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.

[1113] In this invention, the server includes means for comparing multiple financial products and suggesting the most suitable financial product to the user, means for recognizing the user's emotional state and adjusting the financial strategy based on that state, and means for collecting user information and storing it in a database. This makes it possible to suggest the most suitable financial product according to the user's psychological state and to adjust the strategy to suit each individual user.

[1114] "Financial products" refer to products that are the subject of investment or asset management, and include individual defined contribution pension plans, tax-exempt schemes, savings plans, and junior plans.

[1115] "User" refers to an individual or legal entity that intends to use this system to select financial products.

[1116] "Emotional state" refers to the user's psychological state and includes emotions such as stress and relaxation.

[1117] A "financial strategy" refers to an asset management policy formulated based on the user's investment objectives and risk tolerance.

[1118] A "database" refers to an information management system that systematically stores user information and allows for searching and analysis as needed.

[1119] A "machine learning algorithm" refers to a computational method that performs predictions and classifications by analyzing data and learning patterns.

[1120] "Proposal" refers to the act of showing users the most suitable financial products or strategies based on the analysis results.

[1121] As an embodiment for carrying out this invention, the investment guidance AI system is configured as follows.

[1122] First, the user enters information about their investment objectives and risk tolerance through a web browser. This clarifies the user's investment needs and risk profile. The terminal then sends the entered information to the server.

[1123] The server stores the received user information in a database. A data management system such as MySQL is used for the database. The stored information is organized using the Python Pandas library.

[1124] Next, the server uses machine learning algorithms such as Scikit-learn to predict the optimal financial product based on the user's profile. This prediction includes analysis that takes historical data and market trends into account.

[1125] Furthermore, the device uses its camera and microphone to collect information about the user's emotional state. The server then uses TensorFlow to run an emotion recognition model to determine whether the user is stressed or relaxed.

[1126] The server comprehensively analyzes this information and proposes the most suitable financial product to the user. The proposal is customized according to the user's emotional state and risk tolerance.

[1127] For example, if a user provides information indicating they "want to minimize risk" and the system determines they are "feeling stressed," the server will suggest stable financial products.

[1128] Examples of prompts include, "Please suggest the best financial product for a user with a low risk tolerance," and "Please tell me the recommended financial strategy for a user who is experiencing stress."

[1129] The flow of the specific processing in Example 1 will be explained using Figure 17.

[1130] Step 1:

[1131] Users enter information about their investment objectives and risk tolerance through a web browser. This information includes age, investment period, and risk tolerance (low, medium, high). This information serves as foundational data to clarify the user's investment needs.

[1132] Step 2:

[1133] The terminal sends the information entered by the user to the server. The server stores the received information in a MySQL database. The information stored in the database is used for subsequent analysis.

[1134] Step 3:

[1135] The server organizes the stored user information using the Python Pandas library. The organized data is then ready for analysis by machine learning algorithms.

[1136] Step 4:

[1137] The server uses Scikit-learn to predict the optimal financial product based on the user's profile. The input is organized user information, and the output is a list of financial products suitable for the user.

[1138] Step 5:

[1139] The device uses its camera and microphone to collect information about the user's emotional state. This collected data includes the user's facial expressions and tone of voice. This data is used to assess the user's psychological state.

[1140] Step 6:

[1141] The server uses TensorFlow to run an emotion recognition model and analyze the user's emotional state. The input is emotion data sent from the device, and the output is a judgment on whether the user is stressed or relaxed.

[1142] Step 7:

[1143] The server comprehensively analyzes the user's investment information and emotional state to suggest the most suitable financial products. These suggestions are customized according to the user's risk tolerance and emotional state. The output includes the most suitable financial products for the user and the reasons for their selection.

[1144] Step 8:

[1145] The terminal displays the suggested results received from the server to the user. Specifically, the recommended financial products and the reasons for their recommendation are displayed on the web page. The user can then make investment decisions based on this information.

[1146] (Application Example 1)

[1147] Next, we will describe Application Example 1 of Form 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."

[1148] In modern asset management, investors need to choose the optimal investment method from a variety of options, but fully understanding the characteristics and risks of each method is difficult. Furthermore, investors' emotional states can influence their investment decisions, creating a need for emotionally-based investment strategy recommendations. Moreover, a system is needed that can propose the most suitable investment method to investors through real-time sentiment analysis.

[1149] 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.

[1150] In this invention, the server includes means for comparing multiple asset management methods and proposing the optimal asset management method to the user, means for providing asset management support using artificial intelligence based on the knowledge and experience of prominent investors, and means for analyzing the user's emotional state and adjusting the asset management strategy based on that state. This makes it possible to propose the optimal asset management method that takes the user's emotional state into consideration.

[1151] "Asset management methods" is a general term for the financial products and investment methods that individuals and corporations choose to increase their assets.

[1152] "User" refers to an individual or legal entity that uses an asset management system to build wealth.

[1153] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[1154] "Emotional state" refers to the psychological and emotional state of the user and is a factor that influences investment decision-making.

[1155] "Data collection means" refers to a device or method for acquiring information necessary to analyze a user's emotional state in real time.

[1156] "Asset management support tools" refer to a part of a system that provides information and analysis to help users select the optimal asset management method.

[1157] The system for implementing this invention operates in a network environment including a server and terminals. The server runs a program that compares multiple asset management methods and proposes the optimal asset management method to the user. Specifically, the server uses artificial intelligence based on the knowledge and experience of prominent investors to propose the optimal asset management method that takes into account the user's asset management objectives and risk tolerance.

[1158] The device is equipped with data collection capabilities for real-time analysis of the user's emotional state. Specifically, it uses the device's camera and microphone to capture the user's facial expressions and voice tone, and uses an emotion recognition AI model (e.g., Microsoft Azure's Emotion API) to determine their emotional state. This information is sent to a server and used to adjust asset management strategies.

[1159] For example, while a user is using their smartphone, the device's camera captures the user's facial expressions and the microphone analyzes their voice tone. If the emotion recognition AI model detects "stress," the server notifies the device with a message saying, "Based on your current emotional state, we recommend a stable investment strategy."

[1160] An example of a prompt for the generating AI model is, "If the user's emotional state is stress, please suggest a stable investment strategy." Based on this prompt, the server generates an appropriate investment strategy and proposes it to the user.

[1161] The flow of a specific process in Application Example 1 will be explained using Figure 18.

[1162] Step 1:

[1163] The device uses a camera and microphone to collect data in order to analyze the user's emotional state in real time. The input consists of images of the user's facial expressions and audio data. This data is sent to an emotion recognition AI model.

[1164] Step 2:

[1165] The device uses an emotion recognition AI model to determine the user's emotional state from collected facial images and audio data. The input is the data collected in step 1, and the output is the user's emotional state (e.g., stressed, relaxed). This process uses the Microsoft Azure Emotion API to analyze emotions.

[1166] Step 3:

[1167] The terminal sends the determined emotional state to the server. The input is the emotional state obtained in step 2, and the output is the transmission of data to the server.

[1168] Step 4:

[1169] The server uses an AI model to generate optimal investment strategies, taking into account the user's investment goals and risk tolerance, based on the received emotional state. The input is the emotional state and the user's investment information, and the output is a proposal for the optimal investment strategy.

[1170] Step 5:

[1171] The server sends the generated asset management proposal to the terminal. The input is the proposal generated in step 4, and the output is the data transmission to the terminal.

[1172] Step 6:

[1173] The terminal notifies the user of the asset management suggestions received from the server. The input is the suggestions received in step 5, and the output is the notification to the user. Specifically, the terminal screen displays the message, "Based on your current emotional state, we recommend a stable asset management method."

[1174] (Example 2)

[1175] Next, we will describe Example 2 of the morphological example. 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."

[1176] Conventional investment support systems have the drawback of not considering the emotional state of the user when making investment suggestions, making it difficult to increase user psychological satisfaction. Furthermore, they lack the ability to propose sophisticated investment strategies that utilize the experience of past investors, and therefore could not effectively support users' asset building.

[1177] 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.

[1178] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user, means for investment support using artificial intelligence based on the experience and knowledge of past investors, and means for analyzing the user's emotional state and making investment suggestions that correspond to those emotions. This makes it possible to make investment suggestions that take the user's emotional state into consideration, thereby increasing psychological satisfaction and supporting effective asset building.

[1179] "Investment methods" is a general term for specific methods and strategies used to increase assets.

[1180] "User" refers to an individual or legal entity that uses the system to conduct investment activities.

[1181] "Artificial intelligence" is a technology that allows computers to mimic human intelligence and perform learning and reasoning.

[1182] "Investment support measures" refer to functions that provide advice and suggestions to help users manage their assets effectively.

[1183] "Emotional state" refers to the psychological state and mood of the user and is a factor that influences investment decisions.

[1184] "Investment proposal" refers to recommendations or advice on specific investment actions given to users.

[1185] An "investment strategy" refers to a set of investment actions or policies planned to achieve a specific objective.

[1186] The following system is constructed as an embodiment of this invention.

[1187] The server first collects the user's investment history and market trend data. Specifically, it retrieves the user's past transaction data from the database and obtains the latest market data using external financial information services. This allows the server to understand the user's investment patterns and market trends.

[1188] Next, the server organizes the data using the Python Pandas library and extracts data features using Scikit-learn. This prepares the foundational data for investment strategies. Furthermore, the server uses a machine learning model built with TensorFlow to predict investment strategies suitable for the user. This model implements an algorithm based on the experience and knowledge of past investors.

[1189] The device analyzes the user's emotional state in real time. Specifically, it captures the user's facial expressions with its camera and analyzes the user's emotions using OpenCV and an emotion analysis library. This allows the device to determine the user's current emotional state.

[1190] The server customizes the generated investment strategy according to the user's emotional state. For example, if the user is happy, it suggests aggressive investments that involve taking risks, while if they are sad, it suggests investments that prioritize safety.

[1191] Users can receive investment suggestions from AI through their devices. Specifically, users can review the suggested investment strategies on their device screens and, if necessary, input prompts into the AI ​​model to request further suggestions. For example, by inputting a prompt such as "Tell me more about a low-risk investment strategy," the AI ​​will present a detailed strategy.

[1192] The flow of the specific processing in Example 2 will be explained using Figure 19.

[1193] Step 1:

[1194] The server collects users' investment history and market trend data. It uses past transaction data from the database and market data from external financial information services as input. Based on this data, the server prepares foundational data to understand users' investment patterns and market trends. The output consists of organized investment history data and market trend data.

[1195] Step 2:

[1196] The server uses the Python Pandas library to organize the collected data and Scikit-learn to extract data features. The input consists of investment history data and market trend data obtained in step 1. Data organization and feature extraction generate foundational data for investment strategies. The output is a dataset with extracted features.

[1197] Step 3:

[1198] The server uses a machine learning model built with TensorFlow to predict an investment strategy suitable for the user. The input is a dataset from which features obtained in step 2 have been extracted. The machine learning model implements an algorithm based on the past experience and knowledge of investors, thereby generating the optimal investment strategy. The output is the investment strategy proposed to the user.

[1199] Step 4:

[1200] The device analyzes the user's emotional state in real time. It uses facial expression data captured by the device's camera as input. Using OpenCV and an emotion analysis library, it analyzes the user's emotions and determines their current emotional state. The output provides information about the user's emotional state.

[1201] Step 5:

[1202] The server customizes the generated investment strategy according to the user's emotional state. The inputs used are the investment strategy obtained in step 3 and the emotional state information obtained in step 4. If the user is happy, it suggests a risky, aggressive investment; if they are sad, it suggests a safety-oriented investment. The output is an investment strategy adjusted according to the user's emotions.

[1203] Step 6:

[1204] The user receives investment proposals from the AI ​​via their device. The adjusted investment strategy obtained in step 5 is used as input. The user can review the proposed investment strategy on the device screen and, if necessary, input prompt sentences into the AI ​​model to request further suggestions. The output is the investment strategy presented to the user, along with additional suggestions based on the prompt sentences entered by the user.

[1205] (Application Example 2)

[1206] Next, we will describe application example 2 of form example 2. In the following description, the data processing device 12 will be referred to as a "server," and the headset-type terminal 314 will be referred to as a "terminal."

[1207] In today's investment environment, it is difficult for individual investors to select the optimal investment strategy. Furthermore, an investor's emotional state can influence investment decisions, posing a risk to wealth creation. Moreover, there is a demand for swift and efficient methods in executing investments. To address these challenges, a sophisticated investment support system that takes into account investors' experience and emotions is necessary.

[1208] 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.

[1209] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user; means for investment support using artificial intelligence based on the experience and knowledge of legendary investors; means including an emotion engine that estimates the user's emotional state and makes investment suggestions based on those emotions; and means for coordinating with an electronic payment service to immediately execute the proposed investment. As a result, the user can receive optimal investment suggestions tailored to their emotions and execute investments quickly.

[1210] An "investment method" refers to the specific investment methods and strategies used to increase one's assets.

[1211] "Users" refers to individual investors or customers who use this system.

[1212] "Artificial intelligence" is a technology that allows computers to mimic human intelligence and perform learning and reasoning.

[1213] "Investment support measures" refer to functions and technologies that support users in making optimal investments.

[1214] The "emotional engine" is part of a system that analyzes the emotional state of users and makes investment recommendations based on the results.

[1215] An "electronic payment service" is an online payment system that allows for the sending and receiving of funds via the internet.

[1216] "Suggested investments" refer to specific investment options or strategies that the system recommends to the user.

[1217] The system for carrying out this invention includes a server, a user terminal, and an electronic payment service. The server runs a program to compare multiple investment methods and propose the optimal investment method to the user. The server analyzes the user's investment history and market trends using artificial intelligence based on the experience and knowledge of legendary investors. Furthermore, the server uses an emotion engine to estimate the user's emotional state obtained from the user terminal and makes investment suggestions based on that emotion.

[1218] The user terminal is a device such as a smartphone or tablet that receives investment proposals from the server and notifies the user. The user terminal uses cameras and sensors to capture the user's facial expressions and voice, and sends data to the server to estimate their emotional state.

[1219] Electronic payment services work in conjunction with servers to provide online payment functionality for immediately executing proposed investments. This allows users to invest quickly and efficiently.

[1220] As a concrete example, the server analyzes the user's investment history and current market trends and generates a prompt message saying, "We have analyzed your investment history and current market trends. Now is a good time to invest. Do you want to proceed with the investment?" This prompt message is sent to the user's terminal, and if the user selects "Yes," the investment is executed through the electronic payment service.

[1221] The flow of a specific process in Application Example 2 will be explained using Figure 20.

[1222] Step 1:

[1223] The server collects user investment history data and market trend data. It receives the user's past investment history and current market data as input, and feeds this data into a generating AI model. Data processing involves pattern analysis of investment history and extraction of market trends to generate foundational data for proposing optimal investment strategies. The analysis results are obtained as output.

[1224] Step 2:

[1225] The server receives emotion data from the user terminal. It receives facial expression data and voice data transmitted from the user terminal as input and feeds them into the emotion engine. As data processing, it estimates the user's emotional state using an emotion recognition algorithm. The output is data indicating the user's emotional state.

[1226] Step 3:

[1227] The server integrates analysis results and emotional state data to generate optimal investment recommendations for the user. It receives the analysis results from Step 1 and the emotional state data from Step 2 as input, and uses a generative AI model to generate prompt messages. Specifically, it creates a prompt message such as, "We have analyzed your investment history and current market trends. Now is a good time to invest. Do you wish to proceed?" The output is the generated prompt message.

[1228] Step 4:

[1229] The server sends the generated prompt message to the user terminal. It receives the prompt message generated in step 3 as input and sends it to the user terminal. The output is the prompt message displayed on the user terminal.

[1230] Step 5:

[1231] The user reviews the prompt displayed on the terminal and selects whether to proceed with the investment. The user selects "Yes" or "No" in response to the prompt as input. The output is response data based on the user's selection.

[1232] Step 6:

[1233] The server executes the investment through an electronic payment service based on the user's selection. It receives user selection data as input and calls the electronic payment service's API. As data calculations, it calculates the investment amount and processes the payment. As output, it sends a confirmation message to the user's terminal.

[1234] (Example 3)

[1235] Next, we will describe Embodiment 3 of Embodiment Example 3. 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."

[1236] Conventional asset building support systems have faced challenges in flexibly adjusting investment strategies in response to changes in users' financial situation and emotions, and therefore failing to propose optimal investment methods. In particular, the lack of adjustments to investment strategies that take into account changes in users' emotions resulted in insufficient risk management.

[1237] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 3 is realized by the following means.

[1238] In this invention, the server includes means for comparing multiple investment options and proposing the most suitable investment option to the user; means for providing investment guidance using artificial intelligence based on past investment experience and knowledge; means for supporting the user's asset building; means for periodically analyzing the user's asset information and adjusting the investment strategy; and means for detecting changes in the user's emotions in real time and adjusting the investment strategy. This makes it possible to propose flexible and optimal investment strategies that respond to the user's asset situation and emotional changes.

[1239] "Investment methods" is a general term for financial products and investment methods that users can choose to increase their assets.

[1240] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[1241] "Investment guidance tools" refer to systems and processes designed to propose optimal investment methods to users and support their asset building.

[1242] "Asset building" is the process by which users increase their assets over the long term and achieve their financial goals.

[1243] "Asset information" refers to data about a user's financial assets, including balances, investment amounts, and asset types.

[1244] An "investment strategy" is a plan or policy for efficiently managing assets and optimizing risk and return.

[1245] "Emotional change" refers to a change in the user's psychological state, including emotional shifts such as stress and feelings of relief.

[1246] A description of embodiments for carrying out this invention will be given.

[1247] The server runs a program that compares multiple investment options and proposes the optimal investment method to support users in building their assets. This program uses artificial intelligence to provide investment guidance based on past investment experience and knowledge. Specifically, the server periodically collects users' asset information and inputs it into an AI model for analysis. This AI model considers the user's investment objectives and risk tolerance to generate the optimal investment strategy.

[1248] The device uses sensors from a smartwatch or smartphone to detect changes in the user's emotions in real time. This collects data such as heart rate and voice tone, which is then input into the emotion engine. The emotion engine analyzes this data and adjusts the investment strategy according to the user's emotional changes.

[1249] For example, if a user sets a savings goal of 1 million yen, the server uses AI to detect when the user's assets reach 1 million yen and notifies the user. Furthermore, it can suggest a next savings goal of 2 million yen.

[1250] Examples of prompts for the generating AI model include "Generate a notification message when the user's assets reach their target amount" and "Suggest adjustments to the investment strategy based on the user's emotional changes."

[1251] In this way, the system can provide a flexible and optimal investment strategy that responds to the user's asset situation and emotional changes. The flow of the specific processing in Example 3 will be explained using Figure 21.

[1252] Step 1:

[1253] The server collects user asset information. Specifically, it retrieves data from bank accounts and investment accounts via APIs. This data includes balances, investment amounts, and asset types. Input is data from the user's financial institutions, and output is asset information stored on the server.

[1254] Step 2:

[1255] The server inputs the collected asset information into an AI model to analyze the asset status. The AI ​​model evaluates asset increases and decreases by comparing them with past data and determines whether the goals have been achieved. The input is the asset information obtained in step 1, and the output is the result of the asset status analysis.

[1256] Step 3:

[1257] The server adjusts investment strategies based on the analysis results and proposes new investment opportunities. Specifically, the AI ​​predicts market trends and selects investment targets considering risk and return. The input is the analysis results from step 2, and the output is investment proposals for the user.

[1258] Step 4:

[1259] The device collects the user's emotional data in real time. Using sensors in smartwatches and smartphones, it detects changes in emotion from data such as heart rate and voice tone. The input is data from sensors, and the output is emotional data.

[1260] Step 5:

[1261] The terminal uses an emotion engine to analyze the user's emotional changes and adjust the investment strategy as needed. For example, if the user is feeling stressed, the emotion engine instructs the server to switch to a lower-risk investment strategy. The input is the emotional data from step 4, and the output is the adjusted investment strategy.

[1262] Step 6:

[1263] The server integrates the analysis results of emotional and asset data and provides feedback to the user. Specifically, it generates and sends a report to the user explaining the achievement status of asset goals and the reasons for strategic changes based on emotions. The input is the output of steps 3 and 5, and the output is the feedback report to the user.

[1264] (Application Example 3)

[1265] Next, we will describe application example 3 of form example 3. 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."

[1266] In modern wealth building, users need to adapt to diverse investment methods and market fluctuations, but individual emotional changes also influence investment decisions. However, conventional systems do not adjust investment strategies to take user emotions into account, making it difficult to optimize wealth building.

[1267] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means.

[1268] In this invention, the server includes means for comparing multiple investment methods and proposing the optimal investment method to the user; means for providing investment guidance using artificial intelligence based on the investor's experience and knowledge; means for recognizing the user's emotions in real time and adjusting the investment strategy according to changes in those emotions; and means for periodically analyzing the user's asset status and notifying the user of the progress toward achieving investment goals. This makes it possible to provide flexible investment strategies that take into account changes in the user's emotions.

[1269] An "investment method" refers to the specific financial products or strategies chosen to increase one's assets.

[1270] "Artificial intelligence" is a technology in which computer systems imitate human intelligence and perform learning and reasoning.

[1271] "Investment guidance methods" refer to methods for proposing optimal investment strategies to users and supporting their asset building.

[1272] "Emotion recognition means" refers to technology that detects a user's emotional state in real time and adjusts the system's operation based on that information.

[1273] "Asset analysis methods" refer to methods for periodically evaluating a user's asset situation and determining whether their investment goals are being achieved.

[1274] An "investment strategy" is a plan or set of guidelines established to effectively manage assets.

[1275] "Asset building" is the process by which individuals and organizations increase their assets and achieve financial stability.

[1276] The system for carrying out this invention includes a server, a user terminal, and an emotion recognition device. The server is equipped with artificial intelligence to periodically analyze the user's asset status and suggest the optimal investment method. The user terminal is a device such as a smartphone or computer, which receives notifications from the server and provides information to the user. The emotion recognition device detects the user's emotions in real time and transmits that data to the server.

[1277] The server analyzes the user's asset status based on information obtained from a financial database. Based on the analysis results, the server notifies the user of their progress toward investment goals and proposes new investment strategies. An emotion recognition device detects the user's emotional state and sends this information to the server, which is used to adjust the investment strategy.

[1278] As a concrete example, if a user is experiencing stress, the emotion recognition device sends this information to a server. The server considers the user's emotional state and proposes a safety-oriented investment strategy. Using a generative AI model, it generates the optimal strategy based on the prompt, "What investment strategy should be proposed if the user is experiencing stress?"

[1279] The flow of the specific processing in Application Example 3 will be explained using Figure 22.

[1280] Step 1:

[1281] The server retrieves user asset information from a financial database. It uses the user's account information as input. The output is user asset status data. Based on this data, the server prepares to analyze the user's asset status.

[1282] Step 2:

[1283] The server analyzes the acquired asset status data and evaluates the user's progress toward achieving their investment goals. Asset status data is used as input. An evaluation result showing the progress toward investment goals is obtained as output. Based on this evaluation result, the server determines what to notify the user about.

[1284] Step 3:

[1285] Emotion recognition devices detect a user's emotional state in real time. They use the user's biometric information and behavioral data as input. The output is the user's emotional state data. This data is sent to a server to help adjust investment strategies based on emotions.

[1286] Step 4:

[1287] The server receives emotional state data and generates an investment strategy tailored to the user's emotions. It uses emotional state data and asset status evaluation results as input. The output is an adjusted investment strategy. Using a generative AI model, it generates the optimal strategy based on the prompt, "What investment strategy should be proposed if the user is experiencing stress?"

[1288] Step 5:

[1289] The server notifies the user terminal of the adjusted investment strategy. It uses the adjusted investment strategy as input and generates a notification message for the user as output. The user receives this notification and can consider changing their investment strategy.

[1290] (Other examples)

[1291] Since this is the same as the specific processing described in the other embodiments of the first embodiment above, the explanation will be omitted.

[1292] 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.

[1293] The data generation model 58 is a form of so-called generative AI (Artificial Intelligence). One example of the data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> 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.

[1294] Other examples of generative AI include Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are some examples.

[1295] 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.

[1296] [Fourth Embodiment]

[1297] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1298] 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.

[1299] 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).

[1300] 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.

[1301] 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.

[1302] 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).

[1303] 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.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] 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.

[1309] Next, the identification process performed by the identification processing unit 290 of the data processing device 12 will be described.

[1310] "Example of form 1"

[1311] One embodiment of the present invention is an investment guidance AI system. This system has means for comparing multiple investment methods and proposing the optimal investment method to the user. Specifically, it compares investment methods such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA, and proposes the optimal investment method based on information such as the user's investment objectives and risk tolerance.

[1312] "Example of form 2"

[1313] Furthermore, one embodiment of this invention is an AI-powered investment guidance system based on the experience and intellect of legendary investors. This AI uses algorithms based on the investors' experience and intellect to support the user's asset building. Specifically, the AI ​​analyzes the user's investment history and market trends and proposes the optimal investment strategy.

[1314] "Example of form 3"

[1315] Furthermore, one embodiment of the present invention involves means of supporting the user's asset building. Specifically, the AI ​​periodically analyzes the user's asset status and adjusts investment strategies or suggests new investment opportunities. For example, if the user's assets reach a certain target, the AI ​​notifies the user of this information and assists in setting new investment targets.

[1316] The following describes the processing flow for each example of the form.

[1317] "Example of form 1"

[1318] Step 1: The user enters information such as their investment objectives and risk tolerance into the system.

[1319] Step 2: The system compares multiple investment methods (such as individual defined contribution pension plans (iDeCo), small-amount investment tax exemption schemes (NISA), Tsumitate NISA, and Junior NISA).

[1320] Step 3: The system proposes the optimal investment method based on the user's information.

[1321] "Example of form 2"

[1322] Step 1: The AI ​​uses algorithms based on the experience and intellect of legendary investors to analyze the user's investment history and market trends.

[1323] Step 2: The AI ​​proposes the optimal investment strategy based on the analysis results.

[1324] "Example of form 3"

[1325] Step 1: The AI ​​periodically analyzes the user's asset status.

[1326] Step 2: The AI ​​adjusts investment strategies and suggests new investment opportunities.

[1327] Step 3: When the AI ​​reaches a certain target for the user's assets, it notifies the user of this information and helps them set new investment goals.

[1328] (Example 1)

[1329] Next, we will describe Embodiment 1 of Example Form 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1330] In today's financial markets, users are required to make the optimal choices from a diverse range of financial products, which necessitates specialized knowledge and analysis. In particular, selecting the most suitable financial product based on a user's financial goals and risk tolerance is challenging, and there is a need for a system that can provide efficient and accurate recommendations.

[1331] 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.

[1332] In this invention, the server includes means for comparing multiple financial products and suggesting the most suitable financial product to the user, means for data analysis using historical market data and machine learning algorithms, and means for supporting the user's financial goals. This enables the user to efficiently select the most suitable financial product based on their own profile.

[1333] "Financial products" refer to products that are the subject of investment or asset management, and include individual defined contribution pension plans, small-amount investment tax exemption schemes, installment investment schemes, and junior investment schemes.

[1334] "User" refers to an individual or corporation that selects financial products and engages in investment or asset management.

[1335] "Means of proposing the optimal financial product" refers to the methods and processes for comparing multiple financial products based on the user's financial goals and risk tolerance, and selecting the most suitable product.

[1336] "Data analysis methods" refer to methods and processes for analyzing data using machine learning algorithms based on past market data and user input information, in order to provide users with useful information.

[1337] "Means to support financial goals" refers to methods and processes that provide the information and suggestions necessary to achieve the financial goals set by the user, and that support asset building.

[1338] A "generative AI model" refers to a model that uses artificial intelligence technology to analyze user profiles and market data to propose the most suitable financial products.

[1339] As an embodiment for carrying out this invention, the investment guidance AI system is constructed as follows.

[1340] The server generates a program for an investment guidance AI system. This program is designed to suggest the most suitable financial products to the user. The server uses programming languages ​​such as Python and R to analyze historical market data and user input information. This allows for data analysis based on the user's risk tolerance and financial goals.

[1341] The server uses a generative AI model to create a user profile. This profile includes information such as the user's age, investment objectives, risk tolerance, and investment period. Based on this information, the server compares multiple financial products and selects the most suitable one.

[1342] The terminal provides an interface for users to access the system and enter necessary information. Users can enter prompt messages through the terminal, such as the following:

[1343] "I'm in my 40s and want to increase my assets while minimizing risk. Could you please tell me which investment method is best?"

[1344] "I want to save money for my child's college education. What investment method would be suitable?"

[1345] Upon receiving these prompts, the server suggests the most suitable financial products based on the user's profile. This suggestion is then communicated to the user via their terminal. This allows the user to efficiently make investments that align with their financial goals.

[1346] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1347] Step 1:

[1348] Users access the system through their terminals and enter information such as their investment objectives, age, risk tolerance, and investment period. This information is sent to the server and serves as the basis for creating the user's profile.

[1349] Step 2:

[1350] The server creates a profile based on the user information it receives. Using programming languages ​​such as Python or R, the server analyzes the input data and quantifies the user's risk tolerance and financial targets. This profile is then used for subsequent data analysis.

[1351] Step 3:

[1352] The server uses a generative AI model to analyze historical market data and user profiles. The server applies machine learning algorithms to perform data analysis to identify the most suitable financial products for the user. During this process, the risk and return of each financial product are evaluated.

[1353] Step 4:

[1354] Based on the analysis results, the server suggests the most suitable financial products to the user. These suggestions are then communicated to the user via their terminal. Specifically, if the user has a low risk tolerance, financial products that offer stable returns may be suggested.

[1355] Step 5:

[1356] Users review the suggested financial products on their devices and make investment decisions as needed. Based on these suggestions, users can make investment decisions that align with their financial goals.

[1357] (Application Example 1)

[1358] Next, we will describe Application Example 1 of Form 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".

[1359] In today's investment environment, it is difficult for individual investors to select the optimal investment method that suits their investment objectives and risk tolerance. Furthermore, there is a lack of support for investors to effectively compare the diverse range of available investment options and make the best choices. Therefore, there is a need for a system that enables investors to build wealth efficiently and effectively.

[1360] 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.

[1361] In this invention, the server includes means for comparing multiple investment options and suggesting the optimal investment option to the user; means for analyzing past investment data and suggesting the optimal investment option based on the user's investment history and spending patterns; means for collecting the user's financial data and formatting and analyzing the data; means for using a machine learning model to predict the optimal investment option based on the user's risk tolerance and investment objectives; and means for providing a user interface that allows the user to compare and select investment plans. This makes it possible for the user to easily select the optimal investment option according to their own investment objectives and risk tolerance.

[1362] "Investment methods" is a general term for financial products and systems used to increase assets, and includes individual defined contribution pension plans and small-amount investment tax exemption schemes.

[1363] "User" refers to an individual or legal entity that uses the system to select and manage investments.

[1364] "Investment history" refers to a record of past investment activities, including information such as investment amount, investment destination, and investment period.

[1365] "Spending patterns" indicate the user's spending habits and show how much money they spend on what items.

[1366] "Financial data" refers to financial information such as a user's assets, liabilities, income, and expenses, and is the basic data necessary for investment decisions.

[1367] A "machine learning model" is a computational model that uses algorithms to learn patterns from data and perform predictions and classifications.

[1368] "Risk tolerance" is an indicator that shows the range of risk an investor can tolerate, and it represents an individual investor's attitude and ability to handle risk.

[1369] "Investment objectives" refer to the specific goals and intentions when making an investment, and include increasing assets, diversifying risk, and preparing for future funding needs.

[1370] A "user interface" refers to the screens and operating methods that allow users to interact with a system, and is a means of inputting information and displaying results.

[1371] To implement this invention, it is necessary to build a system in which a server plays a central role. The server will be programmed using Python, and the backend will be built using the Flask framework. Pandas and Scikit-learn will be used for data analysis. This will enable the server to collect users' financial data and to format and analyze the data.

[1372] Specifically, the server analyzes the user's investment history and spending patterns, and uses machine learning models to predict the optimal investment strategy based on the user's risk tolerance and investment objectives. This allows users to easily select the most suitable investment strategy according to their own investment objectives and risk tolerance.

[1373] The terminal provides a user interface, allowing users to compare and select investment plans. Users can receive information from the server via their smartphone or computer and make investment choices.

[1374] For example, if a user enters "I want to invest 50,000 yen per month," the server analyzes past spending data and assesses their risk tolerance. As a result, it can suggest that Tsumitate NISA (a type of tax-advantaged investment account) is the optimal option.

[1375] An example of a prompt to input into the generating AI model is: "The user's monthly investment limit is 50,000 yen, and their risk tolerance is moderate. Please suggest the optimal investment method."

[1376] In this way, by coordinating servers, terminals, and users, an efficient and effective investment support system can be realized.

[1377] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1378] Step 1:

[1379] The server receives input data from the user. This input data includes the user's available investment amount, risk tolerance, and investment objectives. Based on this data, the server understands the user's investment needs.

[1380] Step 2:

[1381] The server uses Pandas to retrieve users' past investment history and spending patterns from a database, then formats and analyzes the data. Input includes past transaction history and spending records, which are used to extract trends in the user's investment behavior. The output provides characteristics of the user's investment behavior.

[1382] Step 3:

[1383] The server uses Scikit-learn to run a machine learning model and predict the optimal investment strategy based on the user's risk tolerance and investment objectives. The input consists of formatted investment history data and the user's risk tolerance, which are used to calculate the optimal investment strategy. The output is a list of recommended investment strategies.

[1384] Step 4:

[1385] The server generates prompt messages using a generative AI model. The input includes the user's investment needs and predicted investment methods, and the server creates prompt messages based on this information. The output is a prompt message to be presented to the user.

[1386] Step 5:

[1387] The terminal displays prompt messages received from the server and recommended investment options to the user. The user can review the information presented through the terminal and make an investment choice.

[1388] Step 6:

[1389] The user selects an investment option presented through the terminal and executes the investment as needed. The input is recommended information from the server, which the user uses to make investment decisions. The output is the selected investment option.

[1390] In this way, servers, terminals, and users work together to achieve efficient and effective investment support.

[1391] (Example 2)

[1392] Next, we will describe Example 2 of the morphological example. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1393] Conventional investment support systems have been unable to fully utilize users' investment history and market trends, making it difficult to propose optimal investment strategies. Furthermore, they have not been able to use algorithms that leverage the experience of legendary investors, thus failing to effectively support users' asset building.

[1394] 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.

[1395] In this invention, the server includes means for receiving investment history entered by the user, means for collecting market data, and means for analyzing the collected data and generating an optimal investment strategy. This makes it possible to propose an optimal investment strategy based on the user's investment history and market trends.

[1396] "A means of receiving user-entered investment history" refers to a function that allows users to input records of their past investment activities into the system and retrieve that information.

[1397] "Means for collecting market data" refers to a function that obtains information about financial markets from external information services and makes it available within the system.

[1398] "A means of analyzing collected data and generating the optimal investment strategy" refers to a function that analyzes the user's acquired investment history and market data to calculate and propose the most suitable investment method for the user.

[1399] "A method that uses algorithms based on the experience and knowledge of legendary investors" refers to a function that uses computational methods built on the past success stories and insights of prominent investors to formulate investment strategies.

[1400] "Means of supporting users' asset building" refers to functions that provide advice and strategies for users to efficiently increase their assets and support their asset management.

[1401] To implement this invention, it is first necessary to generate a program on the server that receives investment history from users. This program has the function of receiving investment history entered by the user through a dedicated terminal or web application. Users can enter information such as past stock purchase and sale history and investment amount.

[1402] Next, the server collects market data. This data collection utilizes data from financial information services. Specifically, it obtains market data such as stock indices, exchange rates, and economic indicators from services like Yahoo Finance and Bloomberg.

[1403] The server uses machine learning libraries such as Python's Pandas library and Scikit-learn to analyze the user's investment history and market data. This makes it possible to identify past investment patterns and compare them with current market trends.

[1404] Based on the analysis results, the server uses a generative AI model to generate the optimal investment strategy. This generated strategy is designed to maximize returns while minimizing risk.

[1405] Finally, the server proposes the generated investment strategy to the user. The user can review the proposed strategy and make adjustments as needed.

[1406] As a concrete example, a user might enter a prompt message such as, "Based on my investment history over the past five years, please suggest a future investment strategy." Upon receiving this prompt, the server analyzes the user's investment history and market data, generates a specific investment strategy such as, "You should focus on technology stocks for the next six months," and proposes it to the user.

[1407] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1408] Step 1:

[1409] The user enters their investment history.

[1410] Users input their past investment history through a dedicated terminal or web application. This data includes stock purchase and sale history, investment amounts, and other information. This input data is sent to a server and stored in a database.

[1411] Step 2:

[1412] The server collects market data.

[1413] The server collects market data from financial information services. Specifically, it obtains data such as stock indices, exchange rates, and economic indicators via APIs. This data is updated in real time and stored in a database on the server.

[1414] Step 3:

[1415] The server analyzes the data.

[1416] The server uses the Python Pandas library to analyze the user's investment history and collected market data. The input data consists of the user's investment history and market data. Based on this data, the server identifies past investment patterns and compares them to current market trends. The analysis results are used in the next step.

[1417] Step 4:

[1418] The server generates the investment strategy.

[1419] The server uses a generative AI model to generate the optimal investment strategy based on the analysis results. The analysis results are used as input. The server calculates a strategy to maximize returns while minimizing risk and creates specific investment proposals.

[1420] Step 5:

[1421] The server proposes investment strategies to the user.

[1422] The server notifies the user of the generated investment strategy. The specific investment strategy is sent to the user's terminal as output. The user can review the proposed strategy and make adjustments as needed.

[1423] (Application Example 2)

[1424] Next, we will describe application example 2 of form 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".

[1425] In today's investment environment, it is difficult for individual investors to formulate optimal investment strategies based on vast amounts of information. Furthermore, there is a lack of means to receive real-time advice based on investors' experience and knowledge. Therefore, there is a need for support systems that enable investors to build wealth efficiently and effectively.

[1426] 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.

[1427] This invention includes a server that compares multiple investment methods and proposes the optimal investment method to the user, an artificial intelligence-based investment support method based on the experience and knowledge of legendary investors, and a method that analyzes the user's investment history and market trends and proposes the optimal investment strategy in real time. This enables the user to efficiently develop an investment strategy.

[1428] An "investment method" refers to the specific methods and strategies used to increase one's assets.

[1429] A "user" refers to an individual or legal entity that uses this system to conduct investment activities.

[1430] "Artificial intelligence" refers to the technology that enables computer systems to mimic human intelligence and perform learning and reasoning.

[1431] "Investment support measures" refer to support functions provided to help users make optimal investment decisions.

[1432] "Investment history" refers to a record of the user's past investment activities.

[1433] "Market trends" refer to price fluctuations and trends in financial markets.

[1434] "Real-time" refers to information being processed instantly the moment it is generated.

[1435] An "investment strategy" is a set of action plans designed to achieve specific investment objectives.

[1436] A "smartphone" is a portable device that, in addition to the functions of a mobile phone, possesses multiple functions similar to those of a computer.

[1437] An "application" is a software program designed to provide a specific function or service.

[1438] The system for implementing this invention consists of a server and a user's terminal (smartphone). The server runs a generative AI model built using Python and calculates investment strategies usin...

Claims

[Claim 1] Equipped with a processor, The aforementioned processor, From the input information including the user's investment objectives, a profile of the user is created. Based on the aforementioned profile, a prompt is generated instructing the generating AI model to compare multiple investment options and output a proposal suggesting the most suitable investment option for the user. By inputting the aforementioned prompt to the generating AI model, the proposed content output from the generating AI model is obtained. The proposed content is output to the user's terminal. The user's past transaction data and the latest market data are obtained, A machine learning model that generates basic data by extracting the characteristics of the acquired transaction data and market data, and implements an algorithm built on the experience and knowledge of past investors, inputs the basic data into the machine learning model that outputs an investment strategy based on the input data, and obtains the investment strategy output from the machine learning model. The device acquires the user's heart rate or voice tone detected through the sensor of the terminal. The heart rate or voice tone is analyzed by the emotion engine to determine whether the user is feeling stressed or relaxed. If it is determined that the user is experiencing stress, the investment strategy output from the machine learning model is adjusted to a safer investment strategy that avoids high-risk investments. If it is determined that the user is relaxed, the investment strategy output from the machine learning model is adjusted to a high-return investment strategy. The adjusted investment strategy is output to the terminal. system.

Images