system

Abstract

We provide the system. [Solution] A device that automatically generates financial plans based on personal information obtained from users, A device that uses information technology to monitor changes in social conditions and propose adjustments to financial plans, A device that collects expenditure information in conjunction with an expenditure management service and reflects it in an asset plan, A device that tracks users' income and expenses using a computer and updates their financial plans in real time, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Asset management is a complex and time-consuming task for many people, and it is not easy to consider an optimal management plan according to an individual's lifestyle and economic situation. Therefore, in order to aim for efficient asset formation, it is required to automatically provide an asset management plan suitable for each individual and perform rebalancing as needed. Also, managing modern diverse spending patterns and accurately reflecting them in the asset plan is also an issue.

Means for Solving the Problems

[0005] This invention provides a means for automatically generating asset management plans based on personal information obtained from users, thereby enabling investment tailored to individual needs. Furthermore, by introducing a means for continuously monitoring changes in social conditions and automatically proposing rebalancing of investment plans, it enables users to manage their assets appropriately in response to market fluctuations. In addition, by incorporating a means for linking with external services for expenditure management and reflecting expenditure data in asset planning, the invention aims to efficiently and reliably optimize users' asset formation strategies.

[0006] "Personal information obtained from users" refers to information entered by users, such as age, workplace, income, living situation, spending details, asset goals, and type of asset formation.

[0007] "Methods for automatically generating asset management plans" refers to a function that uses AI based on collected personal information to calculate and propose the optimal asset allocation and investment strategy.

[0008] "Means of monitoring changes in social conditions" refers to a system that continuously collects and analyzes economic indicators and market data to detect these changes.

[0009] "A means of proposing a rebalancing of asset management plans" refers to a system that takes into account social conditions and market changes, reviews asset allocation, and proposes a new asset management plan to the user.

[0010] "Means of integration with expense management services" refers to methods and protocols for exchanging data with external expense management platforms.

[0011] "Means of collecting expenditure data and reflecting it in asset planning" refers to the process of analyzing acquired expenditure data and adjusting and optimizing asset formation plans based on the results. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, a storage with a reference numeral is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, a communication I / F (Interface) with a reference numeral is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system designed to support users in building their assets, and it consists of multiple modules. Specific embodiments are described below.

[0034] Collection of user information

[0035] User:

[0036] Through the interface, users input information such as age, employer, income, living situation, expenses, asset goals, and asset building type. This information serves as foundational data for designing an optimal asset management plan based on each user's unique lifestyle and financial situation.

[0037] Terminal:

[0038] The system receives information entered by the user and securely transmits it to the server. At this stage, the information is accurately and completely retrieved and used to generate an asset management plan.

[0039] Generating an asset management plan

[0040] server:

[0041] The system stores the received user information in a database and uses an AI model to automatically generate asset management plans tailored to individual needs. This AI model analyzes historical market data and investment strategies to determine the asset allocation (e.g., stocks, bonds, and other investment products) that is estimated to be best suited to the user.

[0042] Rebalancing proposal

[0043] server:

[0044] By regularly monitoring changes in social conditions and market data, we detect changes and determine whether a rebalancing of the asset management plan is necessary. If a rebalancing is deemed necessary, we calculate the new allocation and prepare to notify the user.

[0045] Expense management and reporting

[0046] User:

[0047] It integrates with external expense management services and provides daily expense data to the system.

[0048] server:

[0049] The acquired spending data is analyzed and reflected in the user's budget and asset building plan. This enables the optimization of surplus funds and spending, supporting planned asset building.

[0050] Specific example

[0051] For example, let's say a 30-year-old office worker aims to accumulate 10 million yen in assets in 10 years. The user inputs their monthly income, current expenses, and asset-building aspirations.

[0052] server:

[0053] Based on this data, a balanced asset management plan with reduced risk is generated. For example, the allocation might be 50% stocks, 30% bonds, and 20% other diversified investments.

[0054] Subsequently, it detects changes in economic conditions and proposes rebalancing as needed. In particular, during periods of significant market fluctuations, it automatically implements proposals to enhance asset security.

[0055] Thus, the system of the present invention enables asset management optimized for the individual circumstances of each user, and automatically and efficiently supports long-term asset building.

[0056] The following describes the processing flow.

[0057] Step 1:

[0058] The user enters their age, employer, income, living situation, expenses, asset goals, and type of wealth accumulation through the interface. The device temporarily stores this information and prepares to securely transmit it to the server.

[0059] Step 2:

[0060] The server receives user information from the terminal, saves it to a database, and activates an AI model. The AI ​​model analyzes the user information, taking into account past market data and investment strategies, to generate an individualized asset management plan.

[0061] Step 3:

[0062] The server generates an asset management plan and sends it to the terminal, notifying the user. The terminal visualizes the plan details and provides the user with information including projected returns and risks.

[0063] Step 4:

[0064] The server monitors market data and economic indicators. If fluctuations or anomalies are detected, an AI model is used to re-evaluate the suitability of the current asset management plan and, if necessary, to generate rebalancing suggestions.

[0065] Step 5:

[0066] The device notifies the user of a rebalancing proposal and displays the proposal details. The user selects an option to approve or adjust the proposal and revise their asset allocation.

[0067] Step 6:

[0068] The user connects the expense management service and system to provide daily expense information. The server collects the expense data and begins analysis.

[0069] Step 7:

[0070] The server analyzes spending data to identify areas where savings can be made and surplus funds. Based on this, it adjusts the asset building plan and sends the results to the terminal.

[0071] Step 8:

[0072] The device notifies the user of the results of expenditure analysis and plan adjustments, displaying them in an easy-to-understand format. The user updates their asset building strategy as needed.

[0073] (Example 1)

[0074] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0075] Traditional asset management systems have difficulty automatically proposing optimal asset allocations based on individual user attribute information, and asset plans often have to be readjusted manually due to changes in the external environment, hindering efficient asset management. Furthermore, the lack of coordination between expenditure management and asset planning made it difficult for users to achieve optimal asset building.

[0076] 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.

[0077] In this invention, the server includes means for automatically generating an asset management plan based on attribute information obtained from the user, means for monitoring fluctuations in the external environment and proposing readjustments to the asset management plan, means for collecting expenditure data in cooperation with an expenditure management function and reflecting it in the asset plan, and means for proposing an optimal asset allocation based on prompt messages using generation AI technology. This makes it possible to propose an optimal asset allocation tailored to the individual attributes of the user, as well as to realize timely automatic readjustments to the asset plan and efficient expenditure management.

[0078] "User" refers to an individual or organization that uses the system to manage their own assets and expenses.

[0079] "Attribute information" refers to data specific to the user, such as age, income, living situation, and asset goals, and forms the basis of an asset management plan.

[0080] An "asset management plan" is a plan of asset allocation created to effectively build the user's assets, taking into account the balance between risk and return.

[0081] "External environment" includes external factors that affect asset management, such as social conditions and market trends.

[0082] "Re-adjustment" refers to the process of reviewing and optimizing a user's asset management plan in response to changes in external factors.

[0083] "Expense management function" refers to a system or tool that records and analyzes a user's daily expenses and provides information necessary for wealth building.

[0084] "Generative AI technology" refers to artificial intelligence technology that analyzes large amounts of data and calculates the optimal asset allocation based on user attribute information and market data.

[0085] A "prompt statement" is a sentence written in natural language to give instructions to the generation AI technology, and its purpose is to generate an asset management plan.

[0086] "Asset allocation" refers to the specific distribution of assets across investment targets, including stocks, bonds, and other investment products.

[0087] The embodiments for carrying out the invention are described below.

[0088] This invention is a system designed to efficiently support users in building their assets, and aims to integrate data collection from users, generation of asset management plans, monitoring of the external environment, and expenditure management.

[0089] First, the user uses a device to input attribute information such as age, income, living situation, and asset goals through the interface. This information serves as the foundational data for designing an asset management plan tailored to the user's individual lifestyle.

[0090] The terminal transmits the user's input information to the server in an encrypted form. During this process, the terminal's security protocol ensures the confidentiality of the user data.

[0091] The server stores the received attribute information in a database and uses a generative AI model to automatically generate asset management plans tailored to individual needs. This model analyzes historical market data and investment strategies to calculate the optimal asset allocation. The calculation uses generative AI technology, and commands are given to the AI ​​model using prompt statements. For example, a prompt statement might be: "I am a 30-year-old office worker aiming to accumulate 10 million yen in assets in 10 years. Please suggest the optimal asset allocation based on my monthly income and expenses, and my risk tolerance."

[0092] Furthermore, the server monitors fluctuations in the external environment and readjusts the asset management plan in accordance with market trends. This incorporates an AI-powered anomaly detection algorithm that can analyze market conditions in real time. This monitoring function helps ensure that asset allocation is always kept in an optimal state.

[0093] Furthermore, users synchronize their daily spending data with an external spending management system through the spending management function and send it to the server. The server analyzes this data and suggests budget adjustments and reinvestment of surplus funds. This enables planned wealth building and efficient spending management.

[0094] This system utilizes a generative AI model to automatically and efficiently provide personalized asset management strategies, supporting long-term wealth building.

[0095] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0096] Step 1:

[0097] The user inputs attribute information such as age, income, living situation, and asset goals through the interface. The input in this process is the user's own attribute information, and the output is the transfer of this information to the terminal.

[0098] Step 2:

[0099] The terminal encrypts the received attribute information and sends it to the server using a secure communication protocol. At this stage, the input is attribute information entered by the user, and the output is encrypted data securely sent to the server.

[0100] Step 3:

[0101] The server stores the received user information in a database and uses that information as a prompt for the generating AI model. Specifically, it generates prompt statements and calculates the optimal asset management plan based on the AI ​​model, which includes historical market data and investment strategies. The input for this step is the user information stored on the server, and the output is the generated asset management plan.

[0102] Step 4:

[0103] The server remotely monitors social conditions and market trends via external data sources and determines the need to readjust the asset management plan in real time. Specifically, it analyzes trends using anomaly detection algorithms and proposes new asset allocations to the user as needed. The input for this step is external environmental data and the existing asset management plan, and the output is the updated asset readjustment proposal.

[0104] Step 5:

[0105] Users input their daily spending data into the system using the spending management function. The input at this stage is the user's daily spending information, while the output is the spending data sent to the server.

[0106] Step 6:

[0107] The server analyzes the acquired spending data and incorporates it into the generated asset management plan. Specifically, the server uses a machine learning model to analyze spending patterns and proposes ways to reduce unnecessary spending and reinvest surplus funds. The input for this step is spending information from the user, and the output is a proposal for optimized asset building.

[0108] (Application Example 1)

[0109] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0110] In asset building and management, there is a need for a system that can properly manage individual income and expenditure information and respond in real time to changing social conditions. Traditional methods suffer from the problem of delayed information reflection, making rapid decision-making difficult. Furthermore, creating accurate financial plans tailored to individual users is currently difficult with conventional tools.

[0111] 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.

[0112] In this invention, the server includes a device that automatically generates a financial plan based on personal information obtained from the user; a device that uses information technology to monitor changes in social conditions and propose adjustments to the financial plan; a device that works in conjunction with an expenditure management service to collect expenditure information and reflect it in the asset plan; and a device that tracks the user's income and expenditures using a computer and updates the financial plan in real time. This makes it possible to create an optimal financial plan based on individual income and expenditure information and to make immediate plan adjustments.

[0113] A "user" is an entity that utilizes the system to build and manage personal assets.

[0114] "Personal information" refers to a series of data necessary for generating an asset management plan, such as the user's age, income, and asset status.

[0115] A "financial plan" is a plan that outlines the optimal investment strategy and asset allocation, created based on the user's financial situation and goals.

[0116] "Information technology" refers to all technologies used to acquire, process, and analyze data using computers and networks.

[0117] "Changes in social conditions" refer to phenomena that affect the market due to changes in the economic, political, and social environment.

[0118] An "electronic computer" is a device used to process digital data and analyze information; it generally refers to a computer.

[0119] A "spending management service" is an online or application-based service that tracks and records a user's payment and purchasing behavior.

[0120] To realize this invention, the server, terminal, and user each need to play specific roles. The server automatically generates an optimal financial plan based on personal information obtained from the user. This process utilizes a generative AI model to analyze historical market data and investment strategies. Specifically, the model is constructed using TENSORFLOW® and PyTorch. The server also constantly monitors changes in social conditions using information technology and adjusts the financial plan as needed.

[0121] The terminal has a software interface for sending user-entered data to a server. This allows users to easily input information about their income, expenses, and goals using smartphones or other digital devices. The terminal securely transfers information to cloud servers on AWS® and Microsoft® Azure®. Furthermore, it can be linked with expense management services to continuously collect user expense information.

[0122] Through these processes, users can receive a financially optimized plan tailored to their individual needs. For example, users can set up automatic allocation of their monthly surplus funds into different investment products and receive notifications as they approach their goals. An example of a prompt to facilitate this process would be: "Please output the optimal allocation using historical market data, the user's income, and asset goals as the information needed for the AI ​​model that generates the user's asset management plan."

[0123] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0124] Step 1:

[0125] Users input personal information (age, income, expenses, asset goals, etc.) using their devices. This information is received by the device as input and output as data sent to the server.

[0126] Step 2:

[0127] The device encrypts the personal information entered by the user based on a protocol and sends this data to cloud servers such as AWS or Microsoft Azure. This ensures the security of the input data.

[0128] Step 3:

[0129] The server stores the received personal information in a database. The stored data is used as input by a generative AI model to generate an asset management plan. The generative AI model analyzes the input data and outputs an appropriate asset allocation.

[0130] Step 4:

[0131] The server uses information technology to monitor market trends and changes in social conditions. Using this change data as input, the generating AI model determines whether a revision of the financial plan is necessary and outputs a new asset allocation.

[0132] Step 5:

[0133] The server sends the updated financial plan to the terminal and notifies the user. The user can review the new asset allocation sent as output data and accept adjustments as needed.

[0134] Step 6:

[0135] The asset allocation confirmed by the user is linked to the expense management service via the device, creating a dynamic asset plan that reflects daily expenses. This operation updates the user's overall financial situation in real time.

[0136] 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.

[0137] This invention is a system that incorporates an emotional engine to support users' asset building in a more personalized way. Specific embodiments are described below.

[0138] Collection of user information and sentiment data

[0139] User:

[0140] Basic personal information (age, workplace, income, living situation, expenses, asset goals, and asset formation type) is entered through the interface. The application also collects emotional data through the user's facial expressions, voice, and input patterns.

[0141] Terminal:

[0142] The entered personal information and emotional data obtained by the emotion engine are temporarily stored and prepared for transmission to the server.

[0143] Generating and customizing asset management plans

[0144] server:

[0145] The system receives basic user information and emotional data. An AI model analyzes this information and automatically generates an optimal investment plan for the user. Based on the emotional data, the plan is customized to take into account the user's risk tolerance. For example, if the user is feeling anxious, a more conservative investment strategy may be suggested.

[0146] Rebalancing proposals and monitoring of emotional changes

[0147] server:

[0148] We monitor fluctuations in social conditions and market data, as well as continuously monitor users' emotional states. This allows us to dynamically adjust asset management plan rebalancing suggestions in response to changes in users' emotions. If optimism increases, we may suggest more risky strategies.

[0149] Spending management and emotional reflection

[0150] User:

[0151] By integrating with expense management services and systems, it provides daily spending data. In addition, it may also record the emotions associated with the purchase.

[0152] server:

[0153] We analyze spending trends based on emotional data and use it to adjust asset building plans. For example, we provide specific suggestions to reduce impulsive buying tendencies during stressful situations.

[0154] Specific example

[0155] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. In addition to the usual input, the system checks the user's emotional state, and if anxiety or tension is detected, it presents a safety-oriented plan that reduces the proportion of stocks and increases the proportion of bonds and cash.

[0156] In the rebalancing proposal, the emotional changes of the user while using the application are reflected, and appropriate risk adjustments are made according to the situation. This closed-loop approach enables asset building in a less stressful environment for the user.

[0157] Thus, the system of the present invention reflects the user's emotions and automatically and efficiently supports the asset building process in a more personalized manner.

[0158] The following describes the processing flow.

[0159] Step 1:

[0160] The user enters information about their age, employer, income, living situation, expenses, asset goals, and asset building type through the interface. The device temporarily stores this information and prepares it for transmission to the server.

[0161] Step 2:

[0162] The device activates an emotion engine that analyzes the user's facial expressions, voice, and operation patterns to collect emotional data. This emotional data quantifies the user's current emotional state and is reflected in the asset management plan.

[0163] Step 3:

[0164] The server receives personal information and emotional data collected from the terminal and stores it in a database. Using an AI model, the collected information is analyzed and an asset management plan tailored to the user's needs and emotions is automatically generated. Here, risk tolerance is adjusted based on the emotional data.

[0165] Step 4:

[0166] The server sends the details of the asset management plan it generates to the terminal and notifies the user. The terminal visually displays information about risk allocation and projected returns, making it easy for the user to review the plan.

[0167] Step 5:

[0168] The server continuously monitors market data and economic indicators to detect changes in social conditions. At the same time, it continuously monitors changes in user sentiment and automatically re-evaluates the plan when a rebalancing is necessary.

[0169] Step 6:

[0170] The device notifies the user of a rebalancing proposal and displays details of the plan adjustments. The user then has the option to approve the proposal or make adjustments themselves.

[0171] Step 7:

[0172] Allow users to perform the necessary actions to connect with the expense management service and system, and to provide the system with their daily spending data.

[0173] Step 8:

[0174] The server analyzes spending data and combines it with emotional data to evaluate consumption trends. Based on this, it generates personalized suggestions to prevent impulse buying and wasteful spending.

[0175] Step 9:

[0176] The device presents the user with the results of its spending analysis and suggestions for adjusting their asset plan based on those results. It visually displays specific savings strategies and suggestions for asset building, and seeks the user's consent to optimize their strategy.

[0177] (Example 2)

[0178] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0179] Traditional asset management systems mechanically generated investment plans based on users' personal information, making it impossible to provide appropriate suggestions that considered users' emotional states and risk tolerance. Furthermore, they lacked sufficient dynamic response to fluctuations in social conditions and market data, making it difficult for users to build their assets without stress.

[0180] 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.

[0181] This invention includes a server that automatically generates an asset management strategy based on attribute information and emotional information acquired from the user, and uses a generating AI model to reflect the emotional information and evaluate risk tolerance; a server that monitors fluctuations in social conditions and market data and dynamically proposes rebalancing according to the attribute information and emotional information; and a server that cooperates with an expenditure management platform to collect consumption information and reflect it in an asset plan that takes into account the user's emotional state. This makes it possible to propose an individualized asset management strategy that corresponds to the user's emotional state.

[0182] "Attribute information" refers to basic personal information of an individual, such as the user's age, income, and asset goals, and is fundamental data for determining an asset management strategy.

[0183] "Emotional information" refers to data indicating the emotional state obtained from the user's facial expressions and voice data, and is used to evaluate risk tolerance.

[0184] A "generative AI model" is an artificial intelligence program that analyzes attribute information and emotional information to automatically generate the optimal asset management strategy.

[0185] "Risk tolerance" refers to the degree of risk that a user is willing to accept in asset management, and is dynamically evaluated based on emotional information.

[0186] "Social conditions and market data" refers to information regarding economic conditions and fluctuations in financial markets, and is a factor that influences the rebalancing of asset management strategies.

[0187] "Rebalancing" refers to the process of reviewing asset allocation in an asset management plan, and is proposed in response to changes in the user's attribute information and emotional information.

[0188] "Consumer information" refers to data on the user's daily spending and is used to adjust asset planning.

[0189] This invention is a system for providing personalized support to users when they are building their assets. The following describes in detail the configurations for implementing this system.

[0190] Hardware and software to be used

[0191] hardware

[0192] Terminals: Users access the system through an interface using smartphones or PCs. These terminals are equipped with devices such as cameras and microphones to collect facial expressions and voice data.

[0193] Server: This is a computer system used for generating asset management strategies and performing data analysis. By executing the generated AI model, it generates asset management plans based on the received data and makes dynamic rebalancing suggestions.

[0194] software

[0195] Generative AI Model: This is software implemented on a server that analyzes user attribute and sentiment information to generate personalized asset management strategies.

[0196] Data processing and calculation

[0197] User: Through the interface, users input attribute information such as age and income, and provide emotional information using a camera and microphone. This allows for real-time monitoring of the user's emotional state.

[0198] Terminal: Formats and temporarily stores attribute and sentiment information obtained from the user. This data is sent to the server and used as input data for analysis.

[0199] Server: The server uses a generative AI model to automatically generate asset management strategies based on received data. It utilizes emotional information to assess the user's risk tolerance and proposes a more suitable strategy. Prompts are used to generate plans, and the strategy is dynamically adjusted based on the data.

[0200] Specific example

[0201] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. When this user logs into the system and provides attribute information along with an emotional state indicating tension, the server uses a generative AI model to automatically generate a conservative asset management strategy. This process involves adjustments such as reducing the weighting of stocks and increasing the weighting of bonds and cash. In this way, the strategy provided by the system is constantly updated based on the user's changing emotions.

[0202] Example of a prompt

[0203] "A 30-year-old with an annual income of 5 million yen and a savings goal of 10 million yen in 10 years. Please generate a safe-minded asset management plan for a user who feels anxious about their finances."

[0204] This system efficiently utilizes user attribute and emotional information to provide support for optimal asset building for each user.

[0205] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0206] Step 1:

[0207] Users access the system interface using a smartphone or PC and input attribute information such as age, income, and asset goals. Simultaneously, they use camera and microphone devices to capture facial expressions and voice, providing emotional information. The input attribute and emotional information is organized and stored as digital data on the device.

[0208] Step 2:

[0209] The device prepares to send the collected attribute and sentiment information to the server. Specifically, it converts the data into a structured data format such as JSON and stores it temporarily. This process verifies the format integrity to ensure that the data is correctly transferred to the server.

[0210] Step 3:

[0211] The server receives data sent from the terminal and stores it in the database. At this time, attribute information and sentiment information are input into a generating AI model, and analysis based on this information begins. The analysis process uses prompts to automatically generate the optimal asset management strategy for the user. In this step, a risk assessment is performed based on the input, and the most suitable plan is selected.

[0212] Step 4:

[0213] The server generates a specific asset management strategy based on the analysis results of the generated AI model. The model takes emotional information into account and customizes the plan according to the user's risk tolerance. Specifically, it adjusts the asset allocation, such as stocks and bonds, to create an appropriately structured output.

[0214] Step 5:

[0215] The server monitors market data and changes in social conditions in real time and tracks changes in the user's emotions. If necessary, it proposes rebalancing of asset management strategies. This involves a generative AI model receiving new input, reanalyzing it, and feeding back dynamic suggestions to the user.

[0216] Step 6:

[0217] Users receive feedback from the server through the application and review their asset management plan. Based on the suggestions provided by the server, they can take necessary actions and proceed with asset building. This step provides specific information to support the user's decision-making.

[0218] (Application Example 2)

[0219] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0220] Modern consumers often make purchasing decisions based on emotions, which can lead to impulsive purchases and inappropriate investment choices. Furthermore, traditional investment plans often fail to consider the emotional state of the user, making it difficult to effectively build wealth while reducing mental stress. Therefore, it is necessary to utilize user emotional data to provide more personalized investment plans and improve purchasing behavior.

[0221] 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.

[0222] In this invention, the server includes means for automatically generating an asset management plan based on personal information obtained from the user, means for monitoring changes in social conditions and proposing rebalancing of the asset management plan, means for collecting expenditure data in cooperation with an expenditure management service and reflecting it in the asset plan, and means for collecting the user's emotional data and making adjustments to the asset management plan that take the emotional state into account. This makes it possible to dynamically adjust the asset management plan according to the user's emotional state.

[0223] "Personal information" refers to basic data about a user, including information such as age, occupation, income, and living situation.

[0224] An "asset management plan" is an investment strategy generated based on the user's personal information, which includes information on asset allocation and predicted returns and risks.

[0225] "Social conditions" refer to external circumstances and changes related to the economy, politics, environment, etc., and the impact of these on asset management is taken into consideration.

[0226] "Rebalancing" refers to reviewing the contents of an asset management plan and readjusting investment ratios according to fluctuating market conditions and individual circumstances.

[0227] An "expense management service" is a system or platform that collects data on users' consumption behavior and incorporates it into their financial planning.

[0228] "Emotional data" refers to information about a user's emotions obtained from their facial expressions, voice, and behavioral patterns.

[0229] Personalization refers to optimizing services and products according to the individual characteristics and needs of each user.

[0230] To implement this invention, it is necessary to build a smartphone application and a server system. Here, we will explain a specific example of customizing asset management plans based on users' personal information and emotional data to improve purchasing behavior.

[0231] User

[0232] Users access the asset management application via their smartphones. First, they enter personal information (age, occupation, income, etc.). Additionally, the app utilizes emotion recognition technology to capture facial expressions and voice data in real time using the camera and microphone, collecting this data as emotional data.

[0233] terminal

[0234] The device temporarily stores collected personal information and emotional data, preparing it for transmission to the server. This enables immediate data analysis. The hardware used includes the smartphone's default camera and microphone, while the software includes a TensorFlow-based program for emotion recognition.

[0235] server

[0236] The server receives data sent from the terminal and performs analysis using an AI model. Based on emotional data and personal information, it generates an asset management plan optimized for the user. It also suggests rebalancing in real time if changes are needed. To achieve this, the server runs a program built in Python and uses TensorFlow for data analysis.

[0237] If a user shows a change in emotion during a purchase, the app provides immediate feedback based on that information. For example, it might advise the user to reconsider their purchase to avoid buying it in a stressful situation.

[0238] Specific example

[0239] When a user visits a department store during a pre-Christmas sale, the app detects their stress level and sends a notification suggesting they "take a break and reconsider their purchase decision," encouraging them to make a calmer purchasing decision.

[0240] Example of a prompt

[0241] "A user is about to make an online purchase. Analyze their current emotional state and generate specific suggestions to help them avoid impulse buying."

[0242] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0243] Step 1:

[0244] Users enter personal information into the app using their smartphones. This information includes age, occupation, and income, and this data is stored on the device as the user's personal information.

[0245] Step 2:

[0246] The device uses its camera and microphone to capture the user's facial expressions and voice, collecting emotional data. The collected data is analyzed by an emotion recognition program using TensorFlow to identify the user's emotional state (e.g., stress level and degree of joy). The analysis results are stored on the device as emotional data.

[0247] Step 3:

[0248] The device sends the collected personal information and emotional data to the server. At this stage, the data is pre-formatted and securely transmitted to the server using a transmission protocol.

[0249] Step 4:

[0250] The server uses an AI model to analyze the received personal information and sentiment data. This analysis generates an asset management plan optimized for the user. Based on the personal information and sentiment data used as input, a customized investment strategy is output.

[0251] Step 5:

[0252] The server monitors market data and social conditions, and proposes rebalancing as needed. This process is continuous, dynamically adjusting the generated investment plan in response to changes in the user's sentiment. New rebalancing information is output by analyzing the input market data and sentiment data and evaluating risk and return.

[0253] Step 6:

[0254] When a user initiates a purchase, the device recollects and re-evaluates their emotions in real time. Based on this emotional data, if the risk of impulse buying is high, the app sends a notification to the user. This notification encourages the user to make a calm and rational decision.

[0255] Step 7:

[0256] After a user completes their purchase, the terminal collects spending data and sends it to a server. This data is used to adjust long-term asset plans. The input spending data is used to analyze past trends and generate output that can be reflected in future plans.

[0257] 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.

[0258] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0259] 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.

[0260] [Second Embodiment]

[0261] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0262] 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.

[0263] 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).

[0264] 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.

[0265] 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.

[0266] 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).

[0267] 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.

[0268] 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.

[0269] 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.

[0270] 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.

[0271] 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.

[0272] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0273] This invention is a system designed to support users in building their assets, and it consists of multiple modules. Specific embodiments are described below.

[0274] Collection of user information

[0275] User:

[0276] Through the interface, users input information such as age, employer, income, living situation, expenses, asset goals, and asset building type. This information serves as foundational data for designing an optimal asset management plan based on each user's unique lifestyle and financial situation.

[0277] Terminal:

[0278] Receives the information input by the user and securely transmits it to the server. At this stage, the information is accurately and completely acquired and used for generating the asset management plan.

[0279] Generation of Asset Management Plan

[0280] Server:

[0281] Stores the received user information in the database and automatically generates an asset management plan according to individual needs using an AI model. This AI model analyzes past market data and investment strategies and determines the asset allocation (e.g., stocks, bonds, other investment products) that is estimated to be most suitable for the user.

[0282] Proposal of Rebalancing

[0283] Server:

[0284] By regularly monitoring changes in the social situation and market data, detects changes and determines whether rebalancing of the asset management plan is necessary. If it is determined that rebalancing is necessary, calculates a new allocation and prepares to notify the user.

[0285] Expense Management and Reflection

[0286] User:

[0287] Collaborates with an external expense management service and provides daily expense data to the system.

[0288] Server:

[0289] Analyzes the acquired expense data and reflects it in the user's budget and asset formation plan. This enables the operation of surplus funds and the optimization of expenses, and supports planned asset formation.

[0290] Specific Example

[0291] For example, let's say a 30-year-old office worker aims to accumulate 10 million yen in assets in 10 years. The user inputs their monthly income, current expenses, and asset-building aspirations.

[0292] server:

[0293] Based on this data, a balanced asset management plan with reduced risk is generated. For example, the allocation might be 50% stocks, 30% bonds, and 20% other diversified investments.

[0294] Subsequently, it detects changes in economic conditions and proposes rebalancing as needed. In particular, during periods of significant market fluctuations, it automatically implements proposals to enhance asset security.

[0295] Thus, the system of the present invention enables asset management optimized for the individual circumstances of each user, and automatically and efficiently supports long-term asset building.

[0296] The following describes the processing flow.

[0297] Step 1:

[0298] The user enters their age, employer, income, living situation, expenses, asset goals, and type of wealth accumulation through the interface. The device temporarily stores this information and prepares to securely transmit it to the server.

[0299] Step 2:

[0300] The server receives user information from the terminal, saves it to a database, and activates an AI model. The AI ​​model analyzes the user information, taking into account past market data and investment strategies, to generate an individualized asset management plan.

[0301] Step 3:

[0302] The server sends the asset management plan it generated to the terminal and notifies the user. The terminal visualizes the details of the plan and provides the user with information including predicted returns and risk-related information.

[0303] Step 4:

[0304] The server monitors market data and economic indicators. When fluctuations or anomalies are detected, it re-evaluates the suitability of the current asset management plan using an AI model and creates a proposal for rebalancing if necessary.

[0305] Step 5:

[0306] The terminal notifies the user of the rebalancing proposal and displays the details of the proposal in detail. The user selects the option to approve or adjust the proposal and reviews the asset allocation.

[0307] Step 6:

[0308] The user links the expenditure management service and system and provides daily expenditure information. The server collects the expenditure data and starts the analysis.

[0309] Step 7:

[0310] The server analyzes based on the expenditure data, identifies areas where savings can be made and surplus funds. Based on this, it adjusts the asset formation plan and sends the results to the terminal.

[0311] Step 8:

[0312] The terminal notifies the user of the results of the expenditure analysis and plan adjustment and displays them in an easy-to-understand format. The user updates the asset formation strategy if necessary.

[0313] (Example 1)

[0314] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] Traditional asset management systems have difficulty automatically proposing optimal asset allocations based on individual user attribute information, and asset plans often have to be readjusted manually due to changes in the external environment, hindering efficient asset management. Furthermore, the lack of coordination between expenditure management and asset planning made it difficult for users to achieve optimal asset building.

[0316] 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.

[0317] In this invention, the server includes means for automatically generating an asset management plan based on attribute information obtained from the user, means for monitoring fluctuations in the external environment and proposing readjustments to the asset management plan, means for collecting expenditure data in cooperation with an expenditure management function and reflecting it in the asset plan, and means for proposing an optimal asset allocation based on prompt messages using generation AI technology. This makes it possible to propose an optimal asset allocation tailored to the individual attributes of the user, as well as to realize timely automatic readjustments to the asset plan and efficient expenditure management.

[0318] "User" refers to an individual or organization that uses the system to manage their own assets and expenses.

[0319] "Attribute information" refers to data specific to the user, such as age, income, living situation, and asset goals, and forms the basis of an asset management plan.

[0320] An "asset management plan" is a plan of asset allocation created to effectively build the user's assets, taking into account the balance between risk and return.

[0321] "External environment" includes external factors that affect asset management, such as social conditions and market trends.

[0322] "Re-adjustment" refers to the process of reviewing and optimizing a user's asset management plan in response to changes in external factors.

[0323] "Expense management function" refers to a system or tool that records and analyzes a user's daily expenses and provides information necessary for wealth building.

[0324] "Generative AI technology" refers to artificial intelligence technology that analyzes large amounts of data and calculates the optimal asset allocation based on user attribute information and market data.

[0325] A "prompt statement" is a sentence written in natural language to give instructions to the generation AI technology, and its purpose is to generate an asset management plan.

[0326] "Asset allocation" refers to the specific distribution of assets across investment targets, including stocks, bonds, and other investment products.

[0327] The embodiments for carrying out the invention are described below.

[0328] This invention is a system designed to efficiently support users in building their assets, and aims to integrate data collection from users, generation of asset management plans, monitoring of the external environment, and expenditure management.

[0329] First, the user uses a device to input attribute information such as age, income, living situation, and asset goals through the interface. This information serves as the foundational data for designing an asset management plan tailored to the user's individual lifestyle.

[0330] The terminal transmits the user's input information to the server in an encrypted form. During this process, the terminal's security protocol ensures the confidentiality of the user data.

[0331] The server stores the received attribute information in a database and uses a generative AI model to automatically generate asset management plans tailored to individual needs. This model analyzes historical market data and investment strategies to calculate the optimal asset allocation. The calculation uses generative AI technology, and commands are given to the AI ​​model using prompt statements. For example, a prompt statement might be: "I am a 30-year-old office worker aiming to accumulate 10 million yen in assets in 10 years. Please suggest the optimal asset allocation based on my monthly income and expenses, and my risk tolerance."

[0332] Furthermore, the server monitors fluctuations in the external environment and readjusts the asset management plan in accordance with market trends. This incorporates an AI-powered anomaly detection algorithm that can analyze market conditions in real time. This monitoring function helps ensure that asset allocation is always kept in an optimal state.

[0333] Furthermore, users synchronize their daily spending data with an external spending management system through the spending management function and send it to the server. The server analyzes this data and suggests budget adjustments and reinvestment of surplus funds. This enables planned wealth building and efficient spending management.

[0334] This system utilizes a generative AI model to automatically and efficiently provide personalized asset management strategies, supporting long-term wealth building.

[0335] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0336] Step 1:

[0337] The user inputs attribute information such as age, income, living situation, and asset goals through the interface. The input in this process is the user's own attribute information, and the output is the transfer of this information to the terminal.

[0338] Step 2:

[0339] The terminal encrypts the received attribute information and sends it to the server using a secure communication protocol. At this stage, the input is attribute information entered by the user, and the output is encrypted data securely sent to the server.

[0340] Step 3:

[0341] The server stores the received user information in a database and uses that information as a prompt for the generating AI model. Specifically, it generates prompt statements and calculates the optimal asset management plan based on the AI ​​model, which includes historical market data and investment strategies. The input for this step is the user information stored on the server, and the output is the generated asset management plan.

[0342] Step 4:

[0343] The server remotely monitors social conditions and market trends via external data sources and determines the need to readjust the asset management plan in real time. Specifically, it analyzes trends using anomaly detection algorithms and proposes new asset allocations to the user as needed. The input for this step is external environmental data and the existing asset management plan, and the output is the updated asset readjustment proposal.

[0344] Step 5:

[0345] Users input their daily spending data into the system using the spending management function. The input at this stage is the user's daily spending information, while the output is the spending data sent to the server.

[0346] Step 6:

[0347] The server analyzes the acquired spending data and incorporates it into the generated asset management plan. Specifically, the server uses a machine learning model to analyze spending patterns and proposes ways to reduce unnecessary spending and reinvest surplus funds. The input for this step is spending information from the user, and the output is a proposal for optimized asset building.

[0348] (Application Example 1)

[0349] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0350] In asset building and management, there is a need for a system that can properly manage individual income and expenditure information and respond in real time to changing social conditions. Traditional methods suffer from the problem of delayed information reflection, making rapid decision-making difficult. Furthermore, creating accurate financial plans tailored to individual users is currently difficult with conventional tools.

[0351] 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.

[0352] In this invention, the server includes a device that automatically generates a financial plan based on personal information obtained from the user; a device that uses information technology to monitor changes in social conditions and propose adjustments to the financial plan; a device that works in conjunction with an expenditure management service to collect expenditure information and reflect it in the asset plan; and a device that tracks the user's income and expenditures using a computer and updates the financial plan in real time. This makes it possible to create an optimal financial plan based on individual income and expenditure information and to make immediate plan adjustments.

[0353] A "user" is an entity that utilizes the system to build and manage personal assets.

[0354] "Personal information" refers to a series of data necessary for generating an asset management plan, such as the user's age, income, and asset status.

[0355] A "financial plan" is a plan that outlines the optimal investment strategy and asset allocation, created based on the user's financial situation and goals.

[0356] "Information technology" refers to all technologies used to acquire, process, and analyze data using computers and networks.

[0357] "Changes in social conditions" refer to phenomena that affect the market due to changes in the economic, political, and social environment.

[0358] An "electronic computer" is a device used to process digital data and analyze information; it generally refers to a computer.

[0359] A "spending management service" is an online or application-based service that tracks and records a user's payment and purchasing behavior.

[0360] To realize this invention, the server, terminal, and user each need to play specific roles. The server automatically generates an optimal financial plan based on personal information obtained from the user. This process utilizes a generative AI model to analyze historical market data and investment strategies. Specifically, the model is built using TensorFlow or PyTorch. The server also constantly monitors changes in social conditions using information technology and adjusts the financial plan as needed.

[0361] The terminal has a software interface for sending user-entered data to a server. This allows users to easily input information about their income, expenses, and goals using smartphones or other digital devices. The terminal securely transfers information to cloud servers on AWS or Microsoft Azure. Furthermore, it can be linked with expense management services to continuously collect user expense information.

[0362] Through these processes, users can receive a financially optimized plan tailored to their individual needs. For example, users can set up automatic allocation of their monthly surplus funds into different investment products and receive notifications as they approach their goals. An example of a prompt to facilitate this process would be: "Please output the optimal allocation using historical market data, the user's income, and asset goals as the information needed for the AI ​​model that generates the user's asset management plan."

[0363] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0364] Step 1:

[0365] Users input personal information (age, income, expenses, asset goals, etc.) using their devices. This information is received by the device as input and output as data sent to the server.

[0366] Step 2:

[0367] The device encrypts the personal information entered by the user based on a protocol and sends this data to cloud servers such as AWS or Microsoft Azure. This ensures the security of the input data.

[0368] Step 3:

[0369] The server stores the received personal information in a database. The stored data is used as input by a generative AI model to generate an asset management plan. The generative AI model analyzes the input data and outputs an appropriate asset allocation.

[0370] Step 4:

[0371] The server uses information technology to monitor market trends and changes in social conditions. Using this change data as input, the generating AI model determines whether a revision of the financial plan is necessary and outputs a new asset allocation.

[0372] Step 5:

[0373] The server sends the updated financial plan to the terminal and notifies the user. The user can review the new asset allocation sent as output data and accept adjustments as needed.

[0374] Step 6:

[0375] The asset allocation confirmed by the user is linked to the expense management service via the device, creating a dynamic asset plan that reflects daily expenses. This operation updates the user's overall financial situation in real time.

[0376] 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.

[0377] This invention is a system that incorporates an emotional engine to support users' asset building in a more personalized way. Specific embodiments are described below.

[0378] Collection of user information and sentiment data

[0379] User:

[0380] Basic personal information (age, workplace, income, living situation, expenses, asset goals, and asset formation type) is entered through the interface. The application also collects emotional data through the user's facial expressions, voice, and input patterns.

[0381] Terminal:

[0382] The entered personal information and emotional data obtained by the emotion engine are temporarily stored and prepared for transmission to the server.

[0383] Generating and customizing asset management plans

[0384] server:

[0385] The system receives basic user information and emotional data. An AI model analyzes this information and automatically generates an optimal investment plan for the user. Based on the emotional data, the plan is customized to take into account the user's risk tolerance. For example, if the user is feeling anxious, a more conservative investment strategy may be suggested.

[0386] Rebalancing proposals and monitoring of emotional changes

[0387] server:

[0388] We monitor fluctuations in social conditions and market data, as well as continuously monitor users' emotional states. This allows us to dynamically adjust asset management plan rebalancing suggestions in response to changes in users' emotions. If optimism increases, we may suggest more risky strategies.

[0389] Spending management and emotional reflection

[0390] User:

[0391] By integrating with expense management services and systems, it provides daily spending data. In addition, it may also record the emotions associated with the purchase.

[0392] server:

[0393] We analyze spending trends based on emotional data and use it to adjust asset building plans. For example, we provide specific suggestions to reduce impulsive buying tendencies during stressful situations.

[0394] Specific example

[0395] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. In addition to the usual input, the system checks the user's emotional state, and if anxiety or tension is detected, it presents a safety-oriented plan that reduces the proportion of stocks and increases the proportion of bonds and cash.

[0396] In the rebalancing proposal, the emotional changes of the user while using the application are reflected, and appropriate risk adjustments are made according to the situation. This closed-loop approach enables asset building in a less stressful environment for the user.

[0397] Thus, the system of the present invention reflects the user's emotions and automatically and efficiently supports the asset building process in a more personalized manner.

[0398] The following describes the processing flow.

[0399] Step 1:

[0400] The user enters information about their age, employer, income, living situation, expenses, asset goals, and asset building type through the interface. The device temporarily stores this information and prepares it for transmission to the server.

[0401] Step 2:

[0402] The device activates an emotion engine that analyzes the user's facial expressions, voice, and operation patterns to collect emotional data. This emotional data quantifies the user's current emotional state and is reflected in the asset management plan.

[0403] Step 3:

[0404] The server receives personal information and emotional data collected from the terminal and stores it in a database. Using an AI model, the collected information is analyzed and an asset management plan tailored to the user's needs and emotions is automatically generated. Here, risk tolerance is adjusted based on the emotional data.

[0405] Step 4:

[0406] The server sends the details of the asset management plan it generates to the terminal and notifies the user. The terminal visually displays information about risk allocation and projected returns, making it easy for the user to review the plan.

[0407] Step 5:

[0408] The server continuously monitors market data and economic indicators to detect changes in social conditions. At the same time, it continuously monitors changes in user sentiment and automatically re-evaluates the plan when a rebalancing is necessary.

[0409] Step 6:

[0410] The device notifies the user of a rebalancing proposal and displays details of the plan adjustments. The user then has the option to approve the proposal or make adjustments themselves.

[0411] Step 7:

[0412] Allow users to perform the necessary actions to connect with the expense management service and system, and to provide the system with their daily spending data.

[0413] Step 8:

[0414] The server analyzes spending data and combines it with emotional data to evaluate consumption trends. Based on this, it generates personalized suggestions to prevent impulse buying and wasteful spending.

[0415] Step 9:

[0416] The device presents the user with the results of its spending analysis and suggestions for adjusting their asset plan based on those results. It visually displays specific savings strategies and suggestions for asset building, and seeks the user's consent to optimize their strategy.

[0417] (Example 2)

[0418] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0419] Traditional asset management systems mechanically generated investment plans based on users' personal information, making it impossible to provide appropriate suggestions that considered users' emotional states and risk tolerance. Furthermore, they lacked sufficient dynamic response to fluctuations in social conditions and market data, making it difficult for users to build their assets without stress.

[0420] 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.

[0421] This invention includes a server that automatically generates an asset management strategy based on attribute information and emotional information acquired from the user, and uses a generating AI model to reflect the emotional information and evaluate risk tolerance; a server that monitors fluctuations in social conditions and market data and dynamically proposes rebalancing according to the attribute information and emotional information; and a server that cooperates with an expenditure management platform to collect consumption information and reflect it in an asset plan that takes into account the user's emotional state. This makes it possible to propose an individualized asset management strategy that corresponds to the user's emotional state.

[0422] "Attribute information" refers to basic personal information of an individual, such as the user's age, income, and asset goals, and is fundamental data for determining an asset management strategy.

[0423] "Emotional information" refers to data indicating the emotional state obtained from the user's facial expressions and voice data, and is used to evaluate risk tolerance.

[0424] A "generative AI model" is an artificial intelligence program that analyzes attribute information and emotional information to automatically generate the optimal asset management strategy.

[0425] "Risk tolerance" refers to the degree of risk that a user is willing to accept in asset management, and is dynamically evaluated based on emotional information.

[0426] "Social conditions and market data" refers to information regarding economic conditions and fluctuations in financial markets, and is a factor that influences the rebalancing of asset management strategies.

[0427] "Rebalancing" refers to the process of reviewing asset allocation in an asset management plan, and is proposed in response to changes in the user's attribute information and emotional information.

[0428] "Consumer information" refers to data on the user's daily spending and is used to adjust asset planning.

[0429] This invention is a system for providing personalized support to users when they are building their assets. The following describes in detail the configurations for implementing this system.

[0430] Hardware and software to be used

[0431] hardware

[0432] Terminals: Users access the system through an interface using smartphones or PCs. These terminals are equipped with devices such as cameras and microphones to collect facial expressions and voice data.

[0433] Server: This is a computer system used for generating asset management strategies and performing data analysis. By executing the generated AI model, it generates asset management plans based on the received data and makes dynamic rebalancing suggestions.

[0434] software

[0435] Generative AI Model: This is software implemented on a server that analyzes user attribute and sentiment information to generate personalized asset management strategies.

[0436] Data processing and calculation

[0437] User: Through the interface, users input attribute information such as age and income, and provide emotional information using a camera and microphone. This allows for real-time monitoring of the user's emotional state.

[0438] Terminal: Formats and temporarily stores attribute and sentiment information obtained from the user. This data is sent to the server and used as input data for analysis.

[0439] Server: The server uses a generative AI model to automatically generate asset management strategies based on received data. It utilizes emotional information to assess the user's risk tolerance and proposes a more suitable strategy. Prompts are used to generate plans, and the strategy is dynamically adjusted based on the data.

[0440] Specific example

[0441] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. When this user logs into the system and provides attribute information along with an emotional state indicating tension, the server uses a generative AI model to automatically generate a conservative asset management strategy. This process involves adjustments such as reducing the weighting of stocks and increasing the weighting of bonds and cash. In this way, the strategy provided by the system is constantly updated based on the user's changing emotions.

[0442] Example of a prompt

[0443] "A 30-year-old with an annual income of 5 million yen and a savings goal of 10 million yen in 10 years. Please generate a safe-minded asset management plan for a user who feels anxious about their finances."

[0444] This system efficiently utilizes user attribute and emotional information to provide support for optimal asset building for each user.

[0445] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0446] Step 1:

[0447] Users access the system interface using a smartphone or PC and input attribute information such as age, income, and asset goals. Simultaneously, they use camera and microphone devices to capture facial expressions and voice, providing emotional information. The input attribute and emotional information is organized and stored as digital data on the device.

[0448] Step 2:

[0449] The device prepares to send the collected attribute and sentiment information to the server. Specifically, it converts the data into a structured data format such as JSON and stores it temporarily. This process verifies the format integrity to ensure that the data is correctly transferred to the server.

[0450] Step 3:

[0451] The server receives data sent from the terminal and stores it in the database. At this time, attribute information and sentiment information are input into a generating AI model, and analysis based on this information begins. The analysis process uses prompts to automatically generate the optimal asset management strategy for the user. In this step, a risk assessment is performed based on the input, and the most suitable plan is selected.

[0452] Step 4:

[0453] The server generates a specific asset management strategy based on the analysis results of the generated AI model. The model takes emotional information into account and customizes the plan according to the user's risk tolerance. Specifically, it adjusts the asset allocation, such as stocks and bonds, to create an appropriately structured output.

[0454] Step 5:

[0455] The server monitors market data and changes in social conditions in real time and tracks changes in the user's emotions. If necessary, it proposes rebalancing of asset management strategies. This involves a generative AI model receiving new input, reanalyzing it, and feeding back dynamic suggestions to the user.

[0456] Step 6:

[0457] Users receive feedback from the server through the application and review their asset management plan. Based on the suggestions provided by the server, they can take necessary actions and proceed with asset building. This step provides specific information to support the user's decision-making.

[0458] (Application Example 2)

[0459] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0460] Modern consumers often make purchasing decisions based on emotions, which can lead to impulsive purchases and inappropriate investment choices. Furthermore, traditional investment plans often fail to consider the emotional state of the user, making it difficult to effectively build wealth while reducing mental stress. Therefore, it is necessary to utilize user emotional data to provide more personalized investment plans and improve purchasing behavior.

[0461] 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.

[0462] In this invention, the server includes means for automatically generating an asset management plan based on personal information obtained from the user, means for monitoring changes in social conditions and proposing rebalancing of the asset management plan, means for collecting expenditure data in cooperation with an expenditure management service and reflecting it in the asset plan, and means for collecting the user's emotional data and making adjustments to the asset management plan that take the emotional state into account. This makes it possible to dynamically adjust the asset management plan according to the user's emotional state.

[0463] "Personal information" refers to basic data about a user, including information such as age, occupation, income, and living situation.

[0464] An "asset management plan" is an investment strategy generated based on the user's personal information, which includes information on asset allocation and predicted returns and risks.

[0465] "Social conditions" refer to external circumstances and changes related to the economy, politics, environment, etc., and the impact of these on asset management is taken into consideration.

[0466] "Rebalancing" refers to reviewing the contents of an asset management plan and readjusting investment ratios according to fluctuating market conditions and individual circumstances.

[0467] An "expense management service" is a system or platform that collects data on users' consumption behavior and incorporates it into their financial planning.

[0468] "Emotional data" refers to information about a user's emotions obtained from their facial expressions, voice, and behavioral patterns.

[0469] Personalization refers to optimizing services and products according to the individual characteristics and needs of each user.

[0470] To implement this invention, it is necessary to build a smartphone application and a server system. Here, we will explain a specific example of customizing asset management plans based on users' personal information and emotional data to improve purchasing behavior.

[0471] User

[0472] Users access the asset management application via their smartphones. First, they enter personal information (age, occupation, income, etc.). Additionally, the app utilizes emotion recognition technology to capture facial expressions and voice data in real time using the camera and microphone, collecting this data as emotional data.

[0473] terminal

[0474] The device temporarily stores collected personal information and emotional data, preparing it for transmission to the server. This enables immediate data analysis. The hardware used includes the smartphone's default camera and microphone, while the software includes a TensorFlow-based program for emotion recognition.

[0475] server

[0476] The server receives data sent from the terminal and performs analysis using an AI model. Based on emotional data and personal information, it generates an asset management plan optimized for the user. It also suggests rebalancing in real time if changes are needed. To achieve this, the server runs a program built in Python and uses TensorFlow for data analysis.

[0477] If a user shows a change in emotion during a purchase, the app provides immediate feedback based on that information. For example, it might advise the user to reconsider their purchase to avoid buying it in a stressful situation.

[0478] Specific example

[0479] When a user visits a department store during a pre-Christmas sale, the app detects their stress level and sends a notification suggesting they "take a break and reconsider their purchase decision," encouraging them to make a calmer purchasing decision.

[0480] Example of a prompt

[0481] "A user is about to make an online purchase. Analyze their current emotional state and generate specific suggestions to help them avoid impulse buying."

[0482] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0483] Step 1:

[0484] Users enter personal information into the app using their smartphones. This information includes age, occupation, and income, and this data is stored on the device as the user's personal information.

[0485] Step 2:

[0486] The device uses its camera and microphone to capture the user's facial expressions and voice, collecting emotional data. The collected data is analyzed by an emotion recognition program using TensorFlow to identify the user's emotional state (e.g., stress level and degree of joy). The analysis results are stored on the device as emotional data.

[0487] Step 3:

[0488] The device sends the collected personal information and emotional data to the server. At this stage, the data is pre-formatted and securely transmitted to the server using a transmission protocol.

[0489] Step 4:

[0490] The server uses an AI model to analyze the received personal information and sentiment data. This analysis generates an asset management plan optimized for the user. Based on the personal information and sentiment data used as input, a customized investment strategy is output.

[0491] Step 5:

[0492] The server monitors market data and social conditions, and proposes rebalancing as needed. This process is continuous, dynamically adjusting the generated investment plan in response to changes in the user's sentiment. New rebalancing information is output by analyzing the input market data and sentiment data and evaluating risk and return.

[0493] Step 6:

[0494] When a user initiates a purchase, the device recollects and re-evaluates their emotions in real time. Based on this emotional data, if the risk of impulse buying is high, the app sends a notification to the user. This notification encourages the user to make a calm and rational decision.

[0495] Step 7:

[0496] After a user completes their purchase, the terminal collects spending data and sends it to a server. This data is used to adjust long-term asset plans. The input spending data is used to analyze past trends and generate output that can be reflected in future plans.

[0497] 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.

[0498] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0499] 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.

[0500] [Third Embodiment]

[0501] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0502] 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.

[0503] 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).

[0504] 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.

[0505] 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.

[0506] 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).

[0507] 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.

[0508] 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.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0513] This invention is a system designed to support users in building their assets, and it consists of multiple modules. Specific embodiments are described below.

[0514] Collection of user information

[0515] User:

[0516] Through the interface, users input information such as age, employer, income, living situation, expenses, asset goals, and asset building type. This information serves as foundational data for designing an optimal asset management plan based on each user's unique lifestyle and financial situation.

[0517] Terminal:

[0518] The system receives information entered by the user and securely transmits it to the server. At this stage, the information is accurately and completely retrieved and used to generate an asset management plan.

[0519] Generating an asset management plan

[0520] server:

[0521] The system stores the received user information in a database and uses an AI model to automatically generate asset management plans tailored to individual needs. This AI model analyzes historical market data and investment strategies to determine the asset allocation (e.g., stocks, bonds, and other investment products) that is estimated to be best suited to the user.

[0522] Rebalancing proposal

[0523] server:

[0524] By regularly monitoring changes in social conditions and market data, we detect changes and determine whether a rebalancing of the asset management plan is necessary. If a rebalancing is deemed necessary, we calculate the new allocation and prepare to notify the user.

[0525] Expense management and reporting

[0526] User:

[0527] It integrates with external expense management services and provides daily expense data to the system.

[0528] server:

[0529] The acquired spending data is analyzed and reflected in the user's budget and asset building plan. This enables the optimization of surplus funds and spending, supporting planned asset building.

[0530] Specific example

[0531] For example, let's say a 30-year-old office worker aims to accumulate 10 million yen in assets in 10 years. The user inputs their monthly income, current expenses, and asset-building aspirations.

[0532] server:

[0533] Based on this data, a balanced asset management plan with reduced risk is generated. For example, the allocation might be 50% stocks, 30% bonds, and 20% other diversified investments.

[0534] Subsequently, it detects changes in economic conditions and proposes rebalancing as needed. In particular, during periods of significant market fluctuations, it automatically implements proposals to enhance asset security.

[0535] Thus, the system of the present invention enables asset management optimized for the individual circumstances of each user, and automatically and efficiently supports long-term asset building.

[0536] The following describes the processing flow.

[0537] Step 1:

[0538] The user enters their age, employer, income, living situation, expenses, asset goals, and type of wealth accumulation through the interface. The device temporarily stores this information and prepares to securely transmit it to the server.

[0539] Step 2:

[0540] The server receives user information from the terminal, saves it to a database, and activates an AI model. The AI ​​model analyzes the user information, taking into account past market data and investment strategies, to generate an individualized asset management plan.

[0541] Step 3:

[0542] The server generates an asset management plan and sends it to the terminal, notifying the user. The terminal visualizes the plan details and provides the user with information including projected returns and risks.

[0543] Step 4:

[0544] The server monitors market data and economic indicators. If fluctuations or anomalies are detected, an AI model is used to re-evaluate the suitability of the current asset management plan and, if necessary, to generate rebalancing suggestions.

[0545] Step 5:

[0546] The device notifies the user of a rebalancing proposal and displays the proposal details. The user selects an option to approve or adjust the proposal and revise their asset allocation.

[0547] Step 6:

[0548] The user connects the expense management service and system to provide daily expense information. The server collects the expense data and begins analysis.

[0549] Step 7:

[0550] The server analyzes spending data to identify areas where savings can be made and surplus funds. Based on this, it adjusts the asset building plan and sends the results to the terminal.

[0551] Step 8:

[0552] The device notifies the user of the results of expenditure analysis and plan adjustments, displaying them in an easy-to-understand format. The user updates their asset building strategy as needed.

[0553] (Example 1)

[0554] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0555] Traditional asset management systems have difficulty automatically proposing optimal asset allocations based on individual user attribute information, and asset plans often have to be readjusted manually due to changes in the external environment, hindering efficient asset management. Furthermore, the lack of coordination between expenditure management and asset planning made it difficult for users to achieve optimal asset building.

[0556] 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.

[0557] In this invention, the server includes means for automatically generating an asset management plan based on attribute information obtained from the user, means for monitoring fluctuations in the external environment and proposing readjustments to the asset management plan, means for collecting expenditure data in cooperation with an expenditure management function and reflecting it in the asset plan, and means for proposing an optimal asset allocation based on prompt messages using generation AI technology. This makes it possible to propose an optimal asset allocation tailored to the individual attributes of the user, as well as to realize timely automatic readjustments to the asset plan and efficient expenditure management.

[0558] "User" refers to an individual or organization that uses the system to manage their own assets and expenses.

[0559] "Attribute information" refers to data specific to the user, such as age, income, living situation, and asset goals, and forms the basis of an asset management plan.

[0560] An "asset management plan" is a plan of asset allocation created to effectively build the user's assets, taking into account the balance between risk and return.

[0561] "External environment" includes external factors that affect asset management, such as social conditions and market trends.

[0562] "Re-adjustment" refers to the process of reviewing and optimizing a user's asset management plan in response to changes in external factors.

[0563] "Expense management function" refers to a system or tool that records and analyzes a user's daily expenses and provides information necessary for wealth building.

[0564] "Generative AI technology" refers to artificial intelligence technology that analyzes large amounts of data and calculates the optimal asset allocation based on user attribute information and market data.

[0565] A "prompt statement" is a sentence written in natural language to give instructions to the generation AI technology, and its purpose is to generate an asset management plan.

[0566] "Asset allocation" refers to the specific distribution of assets across investment targets, including stocks, bonds, and other investment products.

[0567] The embodiments for carrying out the invention are described below.

[0568] This invention is a system designed to efficiently support users in building their assets, and aims to integrate data collection from users, generation of asset management plans, monitoring of the external environment, and expenditure management.

[0569] First, the user uses a device to input attribute information such as age, income, living situation, and asset goals through the interface. This information serves as the foundational data for designing an asset management plan tailored to the user's individual lifestyle.

[0570] The terminal transmits the user's input information to the server in an encrypted form. During this process, the terminal's security protocol ensures the confidentiality of the user data.

[0571] The server stores the received attribute information in a database and uses a generative AI model to automatically generate asset management plans tailored to individual needs. This model analyzes historical market data and investment strategies to calculate the optimal asset allocation. The calculation uses generative AI technology, and commands are given to the AI ​​model using prompt statements. For example, a prompt statement might be: "I am a 30-year-old office worker aiming to accumulate 10 million yen in assets in 10 years. Please suggest the optimal asset allocation based on my monthly income and expenses, and my risk tolerance."

[0572] Furthermore, the server monitors fluctuations in the external environment and readjusts the asset management plan in accordance with market trends. This incorporates an AI-powered anomaly detection algorithm that can analyze market conditions in real time. This monitoring function helps ensure that asset allocation is always kept in an optimal state.

[0573] Furthermore, users synchronize their daily spending data with an external spending management system through the spending management function and send it to the server. The server analyzes this data and suggests budget adjustments and reinvestment of surplus funds. This enables planned wealth building and efficient spending management.

[0574] This system utilizes a generative AI model to automatically and efficiently provide personalized asset management strategies, supporting long-term wealth building.

[0575] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0576] Step 1:

[0577] The user inputs attribute information such as age, income, living situation, and asset goals through the interface. The input in this process is the user's own attribute information, and the output is the transfer of this information to the terminal.

[0578] Step 2:

[0579] The terminal encrypts the received attribute information and sends it to the server using a secure communication protocol. At this stage, the input is attribute information entered by the user, and the output is encrypted data securely sent to the server.

[0580] Step 3:

[0581] The server stores the received user information in a database and uses that information as a prompt for the generating AI model. Specifically, it generates prompt statements and calculates the optimal asset management plan based on the AI ​​model, which includes historical market data and investment strategies. The input for this step is the user information stored on the server, and the output is the generated asset management plan.

[0582] Step 4:

[0583] The server remotely monitors social conditions and market trends via external data sources and determines the need to readjust the asset management plan in real time. Specifically, it analyzes trends using anomaly detection algorithms and proposes new asset allocations to the user as needed. The input for this step is external environmental data and the existing asset management plan, and the output is the updated asset readjustment proposal.

[0584] Step 5:

[0585] Users input their daily spending data into the system using the spending management function. The input at this stage is the user's daily spending information, while the output is the spending data sent to the server.

[0586] Step 6:

[0587] The server analyzes the acquired spending data and incorporates it into the generated asset management plan. Specifically, the server uses a machine learning model to analyze spending patterns and proposes ways to reduce unnecessary spending and reinvest surplus funds. The input for this step is spending information from the user, and the output is a proposal for optimized asset building.

[0588] (Application Example 1)

[0589] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0590] In asset building and management, there is a need for a system that can properly manage individual income and expenditure information and respond in real time to changing social conditions. Traditional methods suffer from the problem of delayed information reflection, making rapid decision-making difficult. Furthermore, creating accurate financial plans tailored to individual users is currently difficult with conventional tools.

[0591] 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.

[0592] In this invention, the server includes a device that automatically generates a financial plan based on personal information obtained from the user; a device that uses information technology to monitor changes in social conditions and propose adjustments to the financial plan; a device that works in conjunction with an expenditure management service to collect expenditure information and reflect it in the asset plan; and a device that tracks the user's income and expenditures using a computer and updates the financial plan in real time. This makes it possible to create an optimal financial plan based on individual income and expenditure information and to make immediate plan adjustments.

[0593] A "user" is an entity that utilizes the system to build and manage personal assets.

[0594] "Personal information" refers to a series of data necessary for generating an asset management plan, such as the user's age, income, and asset status.

[0595] A "financial plan" is a plan that outlines the optimal investment strategy and asset allocation, created based on the user's financial situation and goals.

[0596] "Information technology" refers to all technologies used to acquire, process, and analyze data using computers and networks.

[0597] "Changes in social conditions" refer to phenomena that affect the market due to changes in the economic, political, and social environment.

[0598] An "electronic computer" is a device used to process digital data and analyze information; it generally refers to a computer.

[0599] A "spending management service" is an online or application-based service that tracks and records a user's payment and purchasing behavior.

[0600] To realize this invention, the server, terminal, and user each need to play specific roles. The server automatically generates an optimal financial plan based on personal information obtained from the user. This process utilizes a generative AI model to analyze historical market data and investment strategies. Specifically, the model is built using TensorFlow or PyTorch. The server also constantly monitors changes in social conditions using information technology and adjusts the financial plan as needed.

[0601] The terminal has a software interface for sending user-entered data to a server. This allows users to easily input information about their income, expenses, and goals using smartphones or other digital devices. The terminal securely transfers information to cloud servers on AWS or Microsoft Azure. Furthermore, it can be linked with expense management services to continuously collect user expense information.

[0602] Through these processes, users can receive a financially optimized plan tailored to their individual needs. For example, users can set up automatic allocation of their monthly surplus funds into different investment products and receive notifications as they approach their goals. An example of a prompt to facilitate this process would be: "Please output the optimal allocation using historical market data, the user's income, and asset goals as the information needed for the AI ​​model that generates the user's asset management plan."

[0603] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0604] Step 1:

[0605] Users input personal information (age, income, expenses, asset goals, etc.) using their devices. This information is received by the device as input and output as data sent to the server.

[0606] Step 2:

[0607] The device encrypts the personal information entered by the user based on a protocol and sends this data to cloud servers such as AWS or Microsoft Azure. This ensures the security of the input data.

[0608] Step 3:

[0609] The server stores the received personal information in a database. The stored data is used as input by a generative AI model to generate an asset management plan. The generative AI model analyzes the input data and outputs an appropriate asset allocation.

[0610] Step 4:

[0611] The server uses information technology to monitor market trends and changes in social conditions. Using this change data as input, the generating AI model determines whether a revision of the financial plan is necessary and outputs a new asset allocation.

[0612] Step 5:

[0613] The server sends the updated financial plan to the terminal and notifies the user. The user can review the new asset allocation sent as output data and accept adjustments as needed.

[0614] Step 6:

[0615] The asset allocation confirmed by the user is linked to the expense management service via the device, creating a dynamic asset plan that reflects daily expenses. This operation updates the user's overall financial situation in real time.

[0616] 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.

[0617] This invention is a system that incorporates an emotional engine to support users' asset building in a more personalized way. Specific embodiments are described below.

[0618] Collection of user information and sentiment data

[0619] User:

[0620] Basic personal information (age, workplace, income, living situation, expenses, asset goals, and asset formation type) is entered through the interface. The application also collects emotional data through the user's facial expressions, voice, and input patterns.

[0621] Terminal:

[0622] The entered personal information and emotional data obtained by the emotion engine are temporarily stored and prepared for transmission to the server.

[0623] Generating and customizing asset management plans

[0624] server:

[0625] The system receives basic user information and emotional data. An AI model analyzes this information and automatically generates an optimal investment plan for the user. Based on the emotional data, the plan is customized to take into account the user's risk tolerance. For example, if the user is feeling anxious, a more conservative investment strategy may be suggested.

[0626] Rebalancing proposals and monitoring of emotional changes

[0627] server:

[0628] We monitor fluctuations in social conditions and market data, as well as continuously monitor users' emotional states. This allows us to dynamically adjust asset management plan rebalancing suggestions in response to changes in users' emotions. If optimism increases, we may suggest more risky strategies.

[0629] Spending management and emotional reflection

[0630] User:

[0631] By integrating with expense management services and systems, it provides daily spending data. In addition, it may also record the emotions associated with the purchase.

[0632] server:

[0633] We analyze spending trends based on emotional data and use it to adjust asset building plans. For example, we provide specific suggestions to reduce impulsive buying tendencies during stressful situations.

[0634] Specific example

[0635] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. In addition to the usual input, the system checks the user's emotional state, and if anxiety or tension is detected, it presents a safety-oriented plan that reduces the proportion of stocks and increases the proportion of bonds and cash.

[0636] In the rebalancing proposal, the emotional changes of the user while using the application are reflected, and appropriate risk adjustments are made according to the situation. This closed-loop approach enables asset building in a less stressful environment for the user.

[0637] Thus, the system of the present invention reflects the user's emotions and automatically and efficiently supports the asset building process in a more personalized manner.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] The user enters information about their age, employer, income, living situation, expenses, asset goals, and asset building type through the interface. The device temporarily stores this information and prepares it for transmission to the server.

[0641] Step 2:

[0642] The device activates an emotion engine that analyzes the user's facial expressions, voice, and operation patterns to collect emotional data. This emotional data quantifies the user's current emotional state and is reflected in the asset management plan.

[0643] Step 3:

[0644] The server receives personal information and emotional data collected from the terminal and stores it in a database. Using an AI model, the collected information is analyzed and an asset management plan tailored to the user's needs and emotions is automatically generated. Here, risk tolerance is adjusted based on the emotional data.

[0645] Step 4:

[0646] The server sends the details of the asset management plan it generates to the terminal and notifies the user. The terminal visually displays information about risk allocation and projected returns, making it easy for the user to review the plan.

[0647] Step 5:

[0648] The server continuously monitors market data and economic indicators to detect changes in social conditions. At the same time, it continuously monitors changes in user sentiment and automatically re-evaluates the plan when a rebalancing is necessary.

[0649] Step 6:

[0650] The device notifies the user of a rebalancing proposal and displays details of the plan adjustments. The user then has the option to approve the proposal or make adjustments themselves.

[0651] Step 7:

[0652] Allow users to perform the necessary actions to connect with the expense management service and system, and to provide the system with their daily spending data.

[0653] Step 8:

[0654] The server analyzes spending data and combines it with emotional data to evaluate consumption trends. Based on this, it generates personalized suggestions to prevent impulse buying and wasteful spending.

[0655] Step 9:

[0656] The device presents the user with the results of its spending analysis and suggestions for adjusting their asset plan based on those results. It visually displays specific savings strategies and suggestions for asset building, and seeks the user's consent to optimize their strategy.

[0657] (Example 2)

[0658] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0659] Traditional asset management systems mechanically generated investment plans based on users' personal information, making it impossible to provide appropriate suggestions that considered users' emotional states and risk tolerance. Furthermore, they lacked sufficient dynamic response to fluctuations in social conditions and market data, making it difficult for users to build their assets without stress.

[0660] 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.

[0661] This invention includes a server that automatically generates an asset management strategy based on attribute information and emotional information acquired from the user, and uses a generating AI model to reflect the emotional information and evaluate risk tolerance; a server that monitors fluctuations in social conditions and market data and dynamically proposes rebalancing according to the attribute information and emotional information; and a server that cooperates with an expenditure management platform to collect consumption information and reflect it in an asset plan that takes into account the user's emotional state. This makes it possible to propose an individualized asset management strategy that corresponds to the user's emotional state.

[0662] "Attribute information" refers to basic personal information of an individual, such as the user's age, income, and asset goals, and is fundamental data for determining an asset management strategy.

[0663] "Emotional information" refers to data indicating the emotional state obtained from the user's facial expressions and voice data, and is used to evaluate risk tolerance.

[0664] A "generative AI model" is an artificial intelligence program that analyzes attribute information and emotional information to automatically generate the optimal asset management strategy.

[0665] "Risk tolerance" refers to the degree of risk that a user is willing to accept in asset management, and is dynamically evaluated based on emotional information.

[0666] "Social conditions and market data" refers to information regarding economic conditions and fluctuations in financial markets, and is a factor that influences the rebalancing of asset management strategies.

[0667] "Rebalancing" refers to the process of reviewing asset allocation in an asset management plan, and is proposed in response to changes in the user's attribute information and emotional information.

[0668] "Consumer information" refers to data on the user's daily spending and is used to adjust asset planning.

[0669] This invention is a system for providing personalized support to users when they are building their assets. The following describes in detail the configurations for implementing this system.

[0670] Hardware and software to be used

[0671] hardware

[0672] Terminals: Users access the system through an interface using smartphones or PCs. These terminals are equipped with devices such as cameras and microphones to collect facial expressions and voice data.

[0673] Server: This is a computer system used for generating asset management strategies and performing data analysis. By executing the generated AI model, it generates asset management plans based on the received data and makes dynamic rebalancing suggestions.

[0674] software

[0675] Generative AI Model: This is software implemented on a server that analyzes user attribute and sentiment information to generate personalized asset management strategies.

[0676] Data processing and calculation

[0677] User: Through the interface, users input attribute information such as age and income, and provide emotional information using a camera and microphone. This allows for real-time monitoring of the user's emotional state.

[0678] Terminal: Formats and temporarily stores attribute and sentiment information obtained from the user. This data is sent to the server and used as input data for analysis.

[0679] Server: The server uses a generative AI model to automatically generate asset management strategies based on received data. It utilizes emotional information to assess the user's risk tolerance and proposes a more suitable strategy. Prompts are used to generate plans, and the strategy is dynamically adjusted based on the data.

[0680] Specific example

[0681] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. When this user logs into the system and provides attribute information along with an emotional state indicating tension, the server uses a generative AI model to automatically generate a conservative asset management strategy. This process involves adjustments such as reducing the weighting of stocks and increasing the weighting of bonds and cash. In this way, the strategy provided by the system is constantly updated based on the user's changing emotions.

[0682] Example of a prompt

[0683] "A 30-year-old with an annual income of 5 million yen and a savings goal of 10 million yen in 10 years. Please generate a safe-minded asset management plan for a user who feels anxious about their finances."

[0684] This system efficiently utilizes user attribute and emotional information to provide support for optimal asset building for each user.

[0685] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0686] Step 1:

[0687] Users access the system interface using a smartphone or PC and input attribute information such as age, income, and asset goals. Simultaneously, they use camera and microphone devices to capture facial expressions and voice, providing emotional information. The input attribute and emotional information is organized and stored as digital data on the device.

[0688] Step 2:

[0689] The device prepares to send the collected attribute and sentiment information to the server. Specifically, it converts the data into a structured data format such as JSON and stores it temporarily. This process verifies the format integrity to ensure that the data is correctly transferred to the server.

[0690] Step 3:

[0691] The server receives data sent from the terminal and stores it in the database. At this time, attribute information and sentiment information are input into a generating AI model, and analysis based on this information begins. The analysis process uses prompts to automatically generate the optimal asset management strategy for the user. In this step, a risk assessment is performed based on the input, and the most suitable plan is selected.

[0692] Step 4:

[0693] The server generates a specific asset management strategy based on the analysis results of the generated AI model. The model takes emotional information into account and customizes the plan according to the user's risk tolerance. Specifically, it adjusts the asset allocation, such as stocks and bonds, to create an appropriately structured output.

[0694] Step 5:

[0695] The server monitors market data and changes in social conditions in real time and tracks changes in the user's emotions. If necessary, it proposes rebalancing of asset management strategies. This involves a generative AI model receiving new input, reanalyzing it, and feeding back dynamic suggestions to the user.

[0696] Step 6:

[0697] Users receive feedback from the server through the application and review their asset management plan. Based on the suggestions provided by the server, they can take necessary actions and proceed with asset building. This step provides specific information to support the user's decision-making.

[0698] (Application Example 2)

[0699] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0700] Modern consumers often make purchasing decisions based on emotions, which can lead to impulsive purchases and inappropriate investment choices. Furthermore, traditional investment plans often fail to consider the emotional state of the user, making it difficult to effectively build wealth while reducing mental stress. Therefore, it is necessary to utilize user emotional data to provide more personalized investment plans and improve purchasing behavior.

[0701] 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.

[0702] In this invention, the server includes means for automatically generating an asset management plan based on personal information obtained from the user, means for monitoring changes in social conditions and proposing rebalancing of the asset management plan, means for collecting expenditure data in cooperation with an expenditure management service and reflecting it in the asset plan, and means for collecting the user's emotional data and making adjustments to the asset management plan that take the emotional state into account. This makes it possible to dynamically adjust the asset management plan according to the user's emotional state.

[0703] "Personal information" refers to basic data about a user, including information such as age, occupation, income, and living situation.

[0704] An "asset management plan" is an investment strategy generated based on the user's personal information, which includes information on asset allocation and predicted returns and risks.

[0705] "Social conditions" refer to external circumstances and changes related to the economy, politics, environment, etc., and the impact of these on asset management is taken into consideration.

[0706] "Rebalancing" refers to reviewing the contents of an asset management plan and readjusting investment ratios according to fluctuating market conditions and individual circumstances.

[0707] An "expense management service" is a system or platform that collects data on users' consumption behavior and incorporates it into their financial planning.

[0708] "Emotional data" refers to information about a user's emotions obtained from their facial expressions, voice, and behavioral patterns.

[0709] Personalization refers to optimizing services and products according to the individual characteristics and needs of each user.

[0710] To implement this invention, it is necessary to build a smartphone application and a server system. Here, we will explain a specific example of customizing asset management plans based on users' personal information and emotional data to improve purchasing behavior.

[0711] User

[0712] Users access the asset management application via their smartphones. First, they enter personal information (age, occupation, income, etc.). Additionally, the app utilizes emotion recognition technology to capture facial expressions and voice data in real time using the camera and microphone, collecting this data as emotional data.

[0713] terminal

[0714] The device temporarily stores collected personal information and emotional data, preparing it for transmission to the server. This enables immediate data analysis. The hardware used includes the smartphone's default camera and microphone, while the software includes a TensorFlow-based program for emotion recognition.

[0715] server

[0716] The server receives data sent from the terminal and performs analysis using an AI model. Based on emotional data and personal information, it generates an asset management plan optimized for the user. It also suggests rebalancing in real time if changes are needed. To achieve this, the server runs a program built in Python and uses TensorFlow for data analysis.

[0717] If a user shows a change in emotion during a purchase, the app provides immediate feedback based on that information. For example, it might advise the user to reconsider their purchase to avoid buying it in a stressful situation.

[0718] Specific example

[0719] When a user visits a department store during a pre-Christmas sale, the app detects their stress level and sends a notification suggesting they "take a break and reconsider their purchase decision," encouraging them to make a calmer purchasing decision.

[0720] Example of a prompt

[0721] "A user is about to make an online purchase. Analyze their current emotional state and generate specific suggestions to help them avoid impulse buying."

[0722] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0723] Step 1:

[0724] Users enter personal information into the app using their smartphones. This information includes age, occupation, and income, and this data is stored on the device as the user's personal information.

[0725] Step 2:

[0726] The device uses its camera and microphone to capture the user's facial expressions and voice, collecting emotional data. The collected data is analyzed by an emotion recognition program using TensorFlow to identify the user's emotional state (e.g., stress level and degree of joy). The analysis results are stored on the device as emotional data.

[0727] Step 3:

[0728] The device sends the collected personal information and emotional data to the server. At this stage, the data is pre-formatted and securely transmitted to the server using a transmission protocol.

[0729] Step 4:

[0730] The server uses an AI model to analyze the received personal information and sentiment data. This analysis generates an asset management plan optimized for the user. Based on the personal information and sentiment data used as input, a customized investment strategy is output.

[0731] Step 5:

[0732] The server monitors market data and social conditions, and proposes rebalancing as needed. This process is continuous, dynamically adjusting the generated investment plan in response to changes in the user's sentiment. New rebalancing information is output by analyzing the input market data and sentiment data and evaluating risk and return.

[0733] Step 6:

[0734] When a user initiates a purchase, the device recollects and re-evaluates their emotions in real time. Based on this emotional data, if the risk of impulse buying is high, the app sends a notification to the user. This notification encourages the user to make a calm and rational decision.

[0735] Step 7:

[0736] After a user completes their purchase, the terminal collects spending data and sends it to a server. This data is used to adjust long-term asset plans. The input spending data is used to analyze past trends and generate output that can be reflected in future plans.

[0737] 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.

[0738] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0739] 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.

[0740] [Fourth Embodiment]

[0741] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0742] 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.

[0743] 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).

[0744] 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.

[0745] 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.

[0746] 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).

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0754] This invention is a system designed to support users in building their assets, and it consists of multiple modules. Specific embodiments are described below.

[0755] Collection of user information

[0756] User:

[0757] Through the interface, users input information such as age, employer, income, living situation, expenses, asset goals, and asset building type. This information serves as foundational data for designing an optimal asset management plan based on each user's unique lifestyle and financial situation.

[0758] Terminal:

[0759] The system receives information entered by the user and securely transmits it to the server. At this stage, the information is accurately and completely retrieved and used to generate an asset management plan.

[0760] Generating an asset management plan

[0761] server:

[0762] The system stores the received user information in a database and uses an AI model to automatically generate asset management plans tailored to individual needs. This AI model analyzes historical market data and investment strategies to determine the asset allocation (e.g., stocks, bonds, and other investment products) that is estimated to be best suited to the user.

[0763] Rebalancing proposal

[0764] server:

[0765] By regularly monitoring changes in social conditions and market data, we detect changes and determine whether a rebalancing of the asset management plan is necessary. If a rebalancing is deemed necessary, we calculate the new allocation and prepare to notify the user.

[0766] Expense management and reporting

[0767] User:

[0768] It integrates with external expense management services and provides daily expense data to the system.

[0769] server:

[0770] The acquired spending data is analyzed and reflected in the user's budget and asset building plan. This enables the optimization of surplus funds and spending, supporting planned asset building.

[0771] Specific example

[0772] For example, let's say a 30-year-old office worker aims to accumulate 10 million yen in assets in 10 years. The user inputs their monthly income, current expenses, and asset-building aspirations.

[0773] server:

[0774] Based on this data, a balanced asset management plan with reduced risk is generated. For example, the allocation might be 50% stocks, 30% bonds, and 20% other diversified investments.

[0775] Subsequently, it detects changes in economic conditions and proposes rebalancing as needed. In particular, during periods of significant market fluctuations, it automatically implements proposals to enhance asset security.

[0776] Thus, the system of the present invention enables asset management optimized for the individual circumstances of each user, and automatically and efficiently supports long-term asset building.

[0777] The following describes the processing flow.

[0778] Step 1:

[0779] The user enters their age, employer, income, living situation, expenses, asset goals, and type of wealth accumulation through the interface. The device temporarily stores this information and prepares to securely transmit it to the server.

[0780] Step 2:

[0781] The server receives user information from the terminal, saves it to a database, and activates an AI model. The AI ​​model analyzes the user information, taking into account past market data and investment strategies, to generate an individualized asset management plan.

[0782] Step 3:

[0783] The server generates an asset management plan and sends it to the terminal, notifying the user. The terminal visualizes the plan details and provides the user with information including projected returns and risks.

[0784] Step 4:

[0785] The server monitors market data and economic indicators. If fluctuations or anomalies are detected, an AI model is used to re-evaluate the suitability of the current asset management plan and, if necessary, to generate rebalancing suggestions.

[0786] Step 5:

[0787] The device notifies the user of a rebalancing proposal and displays the proposal details. The user selects an option to approve or adjust the proposal and revise their asset allocation.

[0788] Step 6:

[0789] The user connects the expense management service and system to provide daily expense information. The server collects the expense data and begins analysis.

[0790] Step 7:

[0791] The server analyzes spending data to identify areas where savings can be made and surplus funds. Based on this, it adjusts the asset building plan and sends the results to the terminal.

[0792] Step 8:

[0793] The device notifies the user of the results of expenditure analysis and plan adjustments, displaying them in an easy-to-understand format. The user updates their asset building strategy as needed.

[0794] (Example 1)

[0795] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0796] Traditional asset management systems have difficulty automatically proposing optimal asset allocations based on individual user attribute information, and asset plans often have to be readjusted manually due to changes in the external environment, hindering efficient asset management. Furthermore, the lack of coordination between expenditure management and asset planning made it difficult for users to achieve optimal asset building.

[0797] 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.

[0798] In this invention, the server includes means for automatically generating an asset management plan based on attribute information obtained from the user, means for monitoring fluctuations in the external environment and proposing readjustments to the asset management plan, means for collecting expenditure data in cooperation with an expenditure management function and reflecting it in the asset plan, and means for proposing an optimal asset allocation based on prompt messages using generation AI technology. This makes it possible to propose an optimal asset allocation tailored to the individual attributes of the user, as well as to realize timely automatic readjustments to the asset plan and efficient expenditure management.

[0799] "User" refers to an individual or organization that uses the system to manage their own assets and expenses.

[0800] "Attribute information" refers to data specific to the user, such as age, income, living situation, and asset goals, and forms the basis of an asset management plan.

[0801] An "asset management plan" is a plan of asset allocation created to effectively build the user's assets, taking into account the balance between risk and return.

[0802] "External environment" includes external factors that affect asset management, such as social conditions and market trends.

[0803] "Re-adjustment" refers to the process of reviewing and optimizing a user's asset management plan in response to changes in external factors.

[0804] "Expense management function" refers to a system or tool that records and analyzes a user's daily expenses and provides information necessary for wealth building.

[0805] "Generative AI technology" refers to artificial intelligence technology that analyzes large amounts of data and calculates the optimal asset allocation based on user attribute information and market data.

[0806] A "prompt statement" is a sentence written in natural language to give instructions to the generation AI technology, and its purpose is to generate an asset management plan.

[0807] "Asset allocation" refers to the specific distribution of assets across investment targets, including stocks, bonds, and other investment products.

[0808] The embodiments for carrying out the invention are described below.

[0809] This invention is a system designed to efficiently support users in building their assets, and aims to integrate data collection from users, generation of asset management plans, monitoring of the external environment, and expenditure management.

[0810] First, the user uses a device to input attribute information such as age, income, living situation, and asset goals through the interface. This information serves as the foundational data for designing an asset management plan tailored to the user's individual lifestyle.

[0811] The terminal transmits the user's input information to the server in an encrypted form. During this process, the terminal's security protocol ensures the confidentiality of the user data.

[0812] The server stores the received attribute information in a database and uses a generative AI model to automatically generate asset management plans tailored to individual needs. This model analyzes historical market data and investment strategies to calculate the optimal asset allocation. The calculation uses generative AI technology, and commands are given to the AI ​​model using prompt statements. For example, a prompt statement might be: "I am a 30-year-old office worker aiming to accumulate 10 million yen in assets in 10 years. Please suggest the optimal asset allocation based on my monthly income and expenses, and my risk tolerance."

[0813] Furthermore, the server monitors fluctuations in the external environment and readjusts the asset management plan in accordance with market trends. This incorporates an AI-powered anomaly detection algorithm that can analyze market conditions in real time. This monitoring function helps ensure that asset allocation is always kept in an optimal state.

[0814] Furthermore, users synchronize their daily spending data with an external spending management system through the spending management function and send it to the server. The server analyzes this data and suggests budget adjustments and reinvestment of surplus funds. This enables planned wealth building and efficient spending management.

[0815] This system utilizes a generative AI model to automatically and efficiently provide personalized asset management strategies, supporting long-term wealth building.

[0816] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0817] Step 1:

[0818] The user inputs attribute information such as age, income, living situation, and asset goals through the interface. The input in this process is the user's own attribute information, and the output is the transfer of this information to the terminal.

[0819] Step 2:

[0820] The terminal encrypts the received attribute information and sends it to the server using a secure communication protocol. At this stage, the input is attribute information entered by the user, and the output is encrypted data securely sent to the server.

[0821] Step 3:

[0822] The server stores the received user information in a database and uses that information as a prompt for the generating AI model. Specifically, it generates prompt statements and calculates the optimal asset management plan based on the AI ​​model, which includes historical market data and investment strategies. The input for this step is the user information stored on the server, and the output is the generated asset management plan.

[0823] Step 4:

[0824] The server remotely monitors social conditions and market trends via external data sources and determines the need to readjust the asset management plan in real time. Specifically, it analyzes trends using anomaly detection algorithms and proposes new asset allocations to the user as needed. The input for this step is external environmental data and the existing asset management plan, and the output is the updated asset readjustment proposal.

[0825] Step 5:

[0826] Users input their daily spending data into the system using the spending management function. The input at this stage is the user's daily spending information, while the output is the spending data sent to the server.

[0827] Step 6:

[0828] The server analyzes the acquired spending data and incorporates it into the generated asset management plan. Specifically, the server uses a machine learning model to analyze spending patterns and proposes ways to reduce unnecessary spending and reinvest surplus funds. The input for this step is spending information from the user, and the output is a proposal for optimized asset building.

[0829] (Application Example 1)

[0830] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0831] In asset building and management, there is a need for a system that can properly manage individual income and expenditure information and respond in real time to changing social conditions. Traditional methods suffer from the problem of delayed information reflection, making rapid decision-making difficult. Furthermore, creating accurate financial plans tailored to individual users is currently difficult with conventional tools.

[0832] 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.

[0833] In this invention, the server includes a device that automatically generates a financial plan based on personal information obtained from the user; a device that uses information technology to monitor changes in social conditions and propose adjustments to the financial plan; a device that works in conjunction with an expenditure management service to collect expenditure information and reflect it in the asset plan; and a device that tracks the user's income and expenditures using a computer and updates the financial plan in real time. This makes it possible to create an optimal financial plan based on individual income and expenditure information and to make immediate plan adjustments.

[0834] A "user" is an entity that utilizes the system to build and manage personal assets.

[0835] "Personal information" refers to a series of data necessary for generating an asset management plan, such as the user's age, income, and asset status.

[0836] A "financial plan" is a plan that outlines the optimal investment strategy and asset allocation, created based on the user's financial situation and goals.

[0837] "Information technology" refers to all technologies used to acquire, process, and analyze data using computers and networks.

[0838] "Changes in social conditions" refer to phenomena that affect the market due to changes in the economic, political, and social environment.

[0839] An "electronic computer" is a device used to process digital data and analyze information; it generally refers to a computer.

[0840] A "spending management service" is an online or application-based service that tracks and records a user's payment and purchasing behavior.

[0841] To realize this invention, the server, terminal, and user each need to play specific roles. The server automatically generates an optimal financial plan based on personal information obtained from the user. This process utilizes a generative AI model to analyze historical market data and investment strategies. Specifically, the model is built using TensorFlow or PyTorch. The server also constantly monitors changes in social conditions using information technology and adjusts the financial plan as needed.

[0842] The terminal has a software interface for sending user-entered data to a server. This allows users to easily input information about their income, expenses, and goals using smartphones or other digital devices. The terminal securely transfers information to cloud servers on AWS or Microsoft Azure. Furthermore, it can be linked with expense management services to continuously collect user expense information.

[0843] Through these processes, users can receive a financially optimized plan tailored to their individual needs. For example, users can set up automatic allocation of their monthly surplus funds into different investment products and receive notifications as they approach their goals. An example of a prompt to facilitate this process would be: "Please output the optimal allocation using historical market data, the user's income, and asset goals as the information needed for the AI ​​model that generates the user's asset management plan."

[0844] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0845] Step 1:

[0846] Users input personal information (age, income, expenses, asset goals, etc.) using their devices. This information is received by the device as input and output as data sent to the server.

[0847] Step 2:

[0848] The device encrypts the personal information entered by the user based on a protocol and sends this data to cloud servers such as AWS or Microsoft Azure. This ensures the security of the input data.

[0849] Step 3:

[0850] The server stores the received personal information in a database. The stored data is used as input by a generative AI model to generate an asset management plan. The generative AI model analyzes the input data and outputs an appropriate asset allocation.

[0851] Step 4:

[0852] The server uses information technology to monitor market trends and changes in social conditions. Using this change data as input, the generating AI model determines whether a revision of the financial plan is necessary and outputs a new asset allocation.

[0853] Step 5:

[0854] The server sends the updated financial plan to the terminal and notifies the user. The user can review the new asset allocation sent as output data and accept adjustments as needed.

[0855] Step 6:

[0856] The asset allocation confirmed by the user is linked to the expense management service via the device, creating a dynamic asset plan that reflects daily expenses. This operation updates the user's overall financial situation in real time.

[0857] 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.

[0858] This invention is a system that incorporates an emotional engine to support users' asset building in a more personalized way. Specific embodiments are described below.

[0859] Collection of user information and sentiment data

[0860] User:

[0861] Basic personal information (age, workplace, income, living situation, expenses, asset goals, and asset formation type) is entered through the interface. The application also collects emotional data through the user's facial expressions, voice, and input patterns.

[0862] Terminal:

[0863] The entered personal information and emotional data obtained by the emotion engine are temporarily stored and prepared for transmission to the server.

[0864] Generating and customizing asset management plans

[0865] server:

[0866] The system receives basic user information and emotional data. An AI model analyzes this information and automatically generates an optimal investment plan for the user. Based on the emotional data, the plan is customized to take into account the user's risk tolerance. For example, if the user is feeling anxious, a more conservative investment strategy may be suggested.

[0867] Rebalancing proposals and monitoring of emotional changes

[0868] server:

[0869] We monitor fluctuations in social conditions and market data, as well as continuously monitor users' emotional states. This allows us to dynamically adjust asset management plan rebalancing suggestions in response to changes in users' emotions. If optimism increases, we may suggest more risky strategies.

[0870] Spending management and emotional reflection

[0871] User:

[0872] By integrating with expense management services and systems, it provides daily spending data. In addition, it may also record the emotions associated with the purchase.

[0873] server:

[0874] We analyze spending trends based on emotional data and use it to adjust asset building plans. For example, we provide specific suggestions to reduce impulsive buying tendencies during stressful situations.

[0875] Specific example

[0876] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. In addition to the usual input, the system checks the user's emotional state, and if anxiety or tension is detected, it presents a safety-oriented plan that reduces the proportion of stocks and increases the proportion of bonds and cash.

[0877] In the rebalancing proposal, the emotional changes of the user while using the application are reflected, and appropriate risk adjustments are made according to the situation. This closed-loop approach enables asset building in a less stressful environment for the user.

[0878] Thus, the system of the present invention reflects the user's emotions and automatically and efficiently supports the asset building process in a more personalized manner.

[0879] The following describes the processing flow.

[0880] Step 1:

[0881] The user enters information about their age, employer, income, living situation, expenses, asset goals, and asset building type through the interface. The device temporarily stores this information and prepares it for transmission to the server.

[0882] Step 2:

[0883] The device activates an emotion engine that analyzes the user's facial expressions, voice, and operation patterns to collect emotional data. This emotional data quantifies the user's current emotional state and is reflected in the asset management plan.

[0884] Step 3:

[0885] The server receives personal information and emotional data collected from the terminal and stores it in a database. Using an AI model, the collected information is analyzed and an asset management plan tailored to the user's needs and emotions is automatically generated. Here, risk tolerance is adjusted based on the emotional data.

[0886] Step 4:

[0887] The server sends the details of the asset management plan it generates to the terminal and notifies the user. The terminal visually displays information about risk allocation and projected returns, making it easy for the user to review the plan.

[0888] Step 5:

[0889] The server continuously monitors market data and economic indicators to detect changes in social conditions. At the same time, it continuously monitors changes in user sentiment and automatically re-evaluates the plan when a rebalancing is necessary.

[0890] Step 6:

[0891] The device notifies the user of a rebalancing proposal and displays details of the plan adjustments. The user then has the option to approve the proposal or make adjustments themselves.

[0892] Step 7:

[0893] Allow users to perform the necessary actions to connect with the expense management service and system, and to provide the system with their daily spending data.

[0894] Step 8:

[0895] The server analyzes spending data and combines it with emotional data to evaluate consumption trends. Based on this, it generates personalized suggestions to prevent impulse buying and wasteful spending.

[0896] Step 9:

[0897] The device presents the user with the results of its spending analysis and suggestions for adjusting their asset plan based on those results. It visually displays specific savings strategies and suggestions for asset building, and seeks the user's consent to optimize their strategy.

[0898] (Example 2)

[0899] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0900] Traditional asset management systems mechanically generated investment plans based on users' personal information, making it impossible to provide appropriate suggestions that considered users' emotional states and risk tolerance. Furthermore, they lacked sufficient dynamic response to fluctuations in social conditions and market data, making it difficult for users to build their assets without stress.

[0901] 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.

[0902] This invention includes a server that automatically generates an asset management strategy based on attribute information and emotional information acquired from the user, and uses a generating AI model to reflect the emotional information and evaluate risk tolerance; a server that monitors fluctuations in social conditions and market data and dynamically proposes rebalancing according to the attribute information and emotional information; and a server that cooperates with an expenditure management platform to collect consumption information and reflect it in an asset plan that takes into account the user's emotional state. This makes it possible to propose an individualized asset management strategy that corresponds to the user's emotional state.

[0903] "Attribute information" refers to basic personal information of an individual, such as the user's age, income, and asset goals, and is fundamental data for determining an asset management strategy.

[0904] "Emotional information" refers to data indicating the emotional state obtained from the user's facial expressions and voice data, and is used to evaluate risk tolerance.

[0905] A "generative AI model" is an artificial intelligence program that analyzes attribute information and emotional information to automatically generate the optimal asset management strategy.

[0906] "Risk tolerance" refers to the degree of risk that a user is willing to accept in asset management, and is dynamically evaluated based on emotional information.

[0907] "Social conditions and market data" refers to information regarding economic conditions and fluctuations in financial markets, and is a factor that influences the rebalancing of asset management strategies.

[0908] "Rebalancing" refers to the process of reviewing asset allocation in an asset management plan, and is proposed in response to changes in the user's attribute information and emotional information.

[0909] "Consumer information" refers to data on the user's daily spending and is used to adjust asset planning.

[0910] This invention is a system for providing personalized support to users when they are building their assets. The following describes in detail the configurations for implementing this system.

[0911] Hardware and software to be used

[0912] hardware

[0913] Terminals: Users access the system through an interface using smartphones or PCs. These terminals are equipped with devices such as cameras and microphones to collect facial expressions and voice data.

[0914] Server: This is a computer system used for generating asset management strategies and performing data analysis. By executing the generated AI model, it generates asset management plans based on the received data and makes dynamic rebalancing suggestions.

[0915] software

[0916] Generative AI Model: This is software implemented on a server that analyzes user attribute and sentiment information to generate personalized asset management strategies.

[0917] Data processing and calculation

[0918] User: Through the interface, users input attribute information such as age and income, and provide emotional information using a camera and microphone. This allows for real-time monitoring of the user's emotional state.

[0919] Terminal: Formats and temporarily stores attribute and sentiment information obtained from the user. This data is sent to the server and used as input data for analysis.

[0920] Server: The server uses a generative AI model to automatically generate asset management strategies based on received data. It utilizes emotional information to assess the user's risk tolerance and proposes a more suitable strategy. Prompts are used to generate plans, and the strategy is dynamically adjusted based on the data.

[0921] Specific example

[0922] For example, suppose a 30-year-old user aims to accumulate 10 million yen in assets in 10 years. When this user logs into the system and provides attribute information along with an emotional state indicating tension, the server uses a generative AI model to automatically generate a conservative asset management strategy. This process involves adjustments such as reducing the weighting of stocks and increasing the weighting of bonds and cash. In this way, the strategy provided by the system is constantly updated based on the user's changing emotions.

[0923] Example of a prompt

[0924] "A 30-year-old with an annual income of 5 million yen and a savings goal of 10 million yen in 10 years. Please generate a safe-minded asset management plan for a user who feels anxious about their finances."

[0925] This system efficiently utilizes user attribute and emotional information to provide support for optimal asset building for each user.

[0926] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0927] Step 1:

[0928] Users access the system interface using a smartphone or PC and input attribute information such as age, income, and asset goals. Simultaneously, they use camera and microphone devices to capture facial expressions and voice, providing emotional information. The input attribute and emotional information is organized and stored as digital data on the device.

[0929] Step 2:

[0930] The device prepares to send the collected attribute and sentiment information to the server. Specifically, it converts the data into a structured data format such as JSON and stores it temporarily. This process verifies the format integrity to ensure that the data is correctly transferred to the server.

[0931] Step 3:

[0932] The server receives data sent from the terminal and stores it in the database. At this time, attribute information and sentiment information are input into a generating AI model, and analysis based on this information begins. The analysis process uses prompts to automatically generate the optimal asset management strategy for the user. In this step, a risk assessment is performed based on the input, and the most suitable plan is selected.

[0933] Step 4:

[0934] The server generates a specific asset management strategy based on the analysis results of the generated AI model. The model takes emotional information into account and customizes the plan according to the user's risk tolerance. Specifically, it adjusts the asset allocation, such as stocks and bonds, to create an appropriately structured output.

[0935] Step 5:

[0936] The server monitors market data and changes in social conditions in real time and tracks changes in the user's emotions. If necessary, it proposes rebalancing of asset management strategies. This involves a generative AI model receiving new input, reanalyzing it, and feeding back dynamic suggestions to the user.

[0937] Step 6:

[0938] Users receive feedback from the server through the application and review their asset management plan. Based on the suggestions provided by the server, they can take necessary actions and proceed with asset building. This step provides specific information to support the user's decision-making.

[0939] (Application Example 2)

[0940] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0941] Modern consumers often make purchasing decisions based on emotions, which can lead to impulsive purchases and inappropriate investment choices. Furthermore, traditional investment plans often fail to consider the emotional state of the user, making it difficult to effectively build wealth while reducing mental stress. Therefore, it is necessary to utilize user emotional data to provide more personalized investment plans and improve purchasing behavior.

[0942] 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.

[0943] In this invention, the server includes means for automatically generating an asset management plan based on personal information obtained from the user, means for monitoring changes in social conditions and proposing rebalancing of the asset management plan, means for collecting expenditure data in cooperation with an expenditure management service and reflecting it in the asset plan, and means for collecting the user's emotional data and making adjustments to the asset management plan that take the emotional state into account. This makes it possible to dynamically adjust the asset management plan according to the user's emotional state.

[0944] "Personal information" refers to basic data about a user, including information such as age, occupation, income, and living situation.

[0945] An "asset management plan" is an investment strategy generated based on the user's personal information, which includes information on asset allocation and predicted returns and risks.

[0946] "Social conditions" refer to external circumstances and changes related to the economy, politics, environment, etc., and the impact of these on asset management is taken into consideration.

[0947] "Rebalancing" refers to reviewing the contents of an asset management plan and readjusting investment ratios according to fluctuating market conditions and individual circumstances.

[0948] An "expense management service" is a system or platform that collects data on users' consumption behavior and incorporates it into their financial planning.

[0949] "Emotional data" refers to information about a user's emotions obtained from their facial expressions, voice, and behavioral patterns.

[0950] Personalization refers to optimizing services and products according to the individual characteristics and needs of each user.

[0951] To implement this invention, it is necessary to build a smartphone application and a server system. Here, we will explain a specific example of customizing asset management plans based on users' personal information and emotional data to improve purchasing behavior.

[0952] User

[0953] Users access the asset management application via their smartphones. First, they enter personal information (age, occupation, income, etc.). Additionally, the app utilizes emotion recognition technology to capture facial expressions and voice data in real time using the camera and microphone, collecting this data as emotional data.

[0954] terminal

[0955] The device temporarily stores collected personal information and emotional data, preparing it for transmission to the server. This enables immediate data analysis. The hardware used includes the smartphone's default camera and microphone, while the software includes a TensorFlow-based program for emotion recognition.

[0956] server

[0957] The server receives data sent from the terminal and performs analysis using an AI model. Based on emotional data and personal information, it generates an asset management plan optimized for the user. It also suggests rebalancing in real time if changes are needed. To achieve this, the server runs a program built in Python and uses TensorFlow for data analysis.

[0958] If a user shows a change in emotion during a purchase, the app provides immediate feedback based on that information. For example, it might advise the user to reconsider their purchase to avoid buying it in a stressful situation.

[0959] Specific example

[0960] When a user visits a department store during a pre-Christmas sale, the app detects their stress level and sends a notification suggesting they "take a break and reconsider their purchase decision," encouraging them to make a calmer purchasing decision.

[0961] Example of a prompt

[0962] "A user is about to make an online purchase. Analyze their current emotional state and generate specific suggestions to help them avoid impulse buying."

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

[0964] Step 1:

[0965] Users enter personal information into the app using their smartphones. This information includes age, occupation, and income, and this data is stored on the device as the user's personal information.

[0966] Step 2:

[0967] The device uses its camera and microphone to capture the user's facial expressions and voice, collecting emotional data. The collected data is analyzed by an emotion recognition program using TensorFlow to identify the user's emotional state (e.g., stress level and degree of joy). The analysis results are stored on the device as emotional data.

[0968] Step 3:

[0969] The device sends the collected personal information and emotional data to the server. At this stage, the data is pre-formatted and securely transmitted to the server using a transmission protocol.

[0970] Step 4:

[0971] The server uses an AI model to analyze the received personal information and sentiment data. This analysis generates an asset management plan optimized for the user. Based on the personal information and sentiment data used as input, a customized investment strategy is output.

[0972] Step 5:

[0973] The server monitors market data and social conditions, and proposes rebalancing as needed. This process is continuous, dynamically adjusting the generated investment plan in response to changes in the user's sentiment. New rebalancing information is output by analyzing the input market data and sentiment data and evaluating risk and return.

[0974] Step 6:

[0975] When a user initiates a purchase, the device recollects and re-evaluates their emotions in real time. Based on this emotional data, if the risk of impulse buying is high, the app sends a notification to the user. This notification encourages the user to make a calm and rational decision.

[0976] Step 7:

[0977] After a user completes their purchase, the terminal collects spending data and sends it to a server. This data is used to adjust long-term asset plans. The input spending data is used to analyze past trends and generate output that can be reflected in future plans.

[0978] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0979] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0980] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0981] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0982] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0983] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0984] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0985] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0986] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0987] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0988] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0989] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0990] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0991] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0992] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0993] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0994] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0995] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0996] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0997] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0998] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0999] The following is further disclosed regarding the embodiments described above.

[1000] (Claim 1)

[1001] A method for automatically generating asset management plans based on personal information obtained from users,

[1002] A means of monitoring changes in social conditions and proposing rebalancing of asset management plans,

[1003] A means of collecting expenditure data by linking with an expense management service and reflecting it in asset planning,

[1004] A system that includes this.

[1005] (Claim 2)

[1006] The system according to claim 1, further comprising means for presenting an asset allocation including predicted return and risk information for the asset management plan.

[1007] (Claim 3)

[1008] The system according to claim 1, further comprising means for analyzing users' spending trends and using this analysis to adjust their asset formation strategies.

[1009] "Example 1"

[1010] (Claim 1)

[1011] A means of automatically generating an asset management plan based on attribute information obtained from users,

[1012] A means of monitoring fluctuations in the external environment and proposing readjustments to asset management plans,

[1013] A means of collecting expenditure data in conjunction with the expenditure management function and reflecting it in asset planning,

[1014] A method for proposing the optimal asset allocation based on prompt text using generative AI technology,

[1015] A system that includes this.

[1016] (Claim 2)

[1017] The system according to claim 1, further comprising means for presenting an allocation of assets including information on expected profits and risks in the asset management plan.

[1018] (Claim 3)

[1019] The system according to claim 1, further comprising means for analyzing the spending trends of users and using this analysis to adjust their asset formation methods.

[1020] "Application Example 1"

[1021] (Claim 1)

[1022] A device that automatically generates financial plans based on personal information obtained from users,

[1023] A device that uses information technology to monitor changes in social conditions and propose adjustments to financial plans,

[1024] A device that collects expenditure information in conjunction with an expenditure management service and reflects it in an asset plan,

[1025] A device that tracks users' income and expenses using a computer and updates their financial plans in real time,

[1026] A system that includes this.

[1027] (Claim 2)

[1028] The system according to claim 1, further comprising a device that indicates the allocation of assets including expected profit and risk information for the financial plan.

[1029] (Claim 3)

[1030] The system according to claim 1, further comprising a device for analyzing users' spending trends and using them to adjust asset formation strategies.

[1031] "Example 2 of combining an emotion engine"

[1032] (Claim 1)

[1033] A means of automatically generating asset management strategies based on attribute and emotional information obtained from users, and evaluating risk tolerance by reflecting emotional information using a generation AI model,

[1034] A means of monitoring fluctuations in social conditions and market data, and dynamically proposing rebalancing in accordance with attribute information and sentiment information,

[1035] A means of collecting consumption information in conjunction with an expenditure management platform and reflecting it in asset planning that takes into account the user's emotional state,

[1036] A means of providing suggestions for adjusting investment strategies based on changes in the user's emotions,

[1037] A system that includes this.

[1038] (Claim 2)

[1039] The system according to claim 1, further comprising means for presenting an asset allocation including predicted rate of return and risk information as part of the asset management strategy.

[1040] (Claim 3)

[1041] The system according to claim 1, further comprising means for analyzing users' consumption trends and adjusting asset formation plans based on emotional data.

[1042] "Application example 2 when combining with an emotional engine"

[1043] (Claim 1)

[1044] A method for automatically generating asset management plans based on personal information obtained from users,

[1045] A means of monitoring changes in social conditions and proposing rebalancing of asset management plans,

[1046] A means of collecting expenditure data by linking with an expense management service and reflecting it in asset planning,

[1047] A means of collecting user emotional data and making adjustments to asset management plans that take emotional states into account,

[1048] A system that includes this.

[1049] (Claim 2)

[1050] The system according to claim 1, further comprising means for presenting an asset allocation including predicted return and risk information for the asset management plan.

[1051] (Claim 3)

[1052] The system according to claim 1, further comprising means for analyzing users' spending trends and using this analysis to adjust their asset formation strategies. [Explanation of symbols]

[1053] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A device that automatically generates financial plans based on personal information obtained from users, A device that uses information technology to monitor changes in social conditions and propose adjustments to financial plans, A device that collects expenditure information in conjunction with an expenditure management service and reflects it in an asset plan, A device that tracks users' income and expenses using a computer and updates their financial plans in real time, A system that includes this.

2. The system according to claim 1, further comprising a device that indicates the allocation of assets including expected profit and risk information for the financial plan.

3. The system according to claim 1, further comprising a device for analyzing users' spending trends and using it to adjust their asset formation strategies.

Images