System

Abstract

An object of the system according to the embodiment is to generate a long-term plan on the basis of basic setting information of a user and correct the long-term plan in accordance with a situation or a goal.SOLUTION: A system includes a setting information acquisition part, a plan generation part, and a plan correction part. The setting information acquisition unit acquires basic setting information of a user. The plan generation unit generates a plan related to education, house purchase, and life events on the basis of the setting information acquired by the setting information acquisition unit. The plan correction unit corrects the plan generated by the plan generation unit in accordance with the user's current situation and goal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem that they do not adequately generate long-term plans based on the user's basic setting information and modify them according to the situation and goals.

[0005] The system according to the embodiment aims to generate a long-term plan based on the user's basic setting information and to modify the plan according to the situation and goals. [Means for solving the problem]

[0006] The system according to the embodiment includes a setting information acquisition unit, a plan generation unit, and a plan modification unit. The setting information acquisition unit acquires basic setting information of a user. The plan generation unit generates plans related to education, home purchase, and life events based on the setting information acquired by the setting information acquisition unit. The plan modification unit modifies the plan generated by the plan generation unit in accordance with the user's current situation and goals. [Effects of the Invention]

[0007] The system according to the embodiment generates a long-term plan based on the user's basic settings and can modify it depending on the situation and goals. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, 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), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The financial planner system according to the embodiment of the present invention acquires basic setting information from a user, generates a plan using a generation AI, and modifies the plan according to the user's situation and goals. This allows the financial planner system to provide an optimal financial plan tailored to the user's life.

[0029] A financial planner system according to an embodiment includes a setting information acquisition unit, a plan generation unit, and a plan correction unit. The setting information acquisition unit acquires basic setting information about a user. For example, the setting information acquisition unit collects information such as age, income, and family structure by inputting the information. The plan generation unit generates plans related to education, home purchase, and life events based on the setting information acquired by the setting information acquisition unit. For example, if a user inputs, "I want to plan my children's education expenses," the plan generation unit proposes an estimated education expense and a savings plan based on the information. The plan correction unit corrects the plan generated by the plan generation unit according to the user's current situation and goals. For example, if the user's income increases or their family structure changes, the plan correction unit reevaluates the plan and provides an optimal plan. This allows the financial planner system according to an embodiment to provide an optimal financial plan tailored to the user's life. For example, the user can plan their children's education expenses while preparing for home purchases and life events. Furthermore, even if the situation changes, the optimal plan can be maintained by making appropriate corrections.

[0030] The plan generation unit uses the generation AI to analyze the user's past financial behavior data and provide a more accurate plan. For example, the plan generation unit uses the generation AI to analyze the user's past bank transaction history and credit card usage history to understand spending patterns and savings tendencies. This allows for a more accurate plan based on the user's actual financial behavior. The plan generation unit also uses the generation AI to analyze the user's past investment history and risk tolerance to propose an optimal investment strategy. For example, it provides a plan that minimizes risk based on past investment successes and failures. The plan generation unit also uses the generation AI to analyze the user's past income fluctuations and spending tendencies to create future income forecasts and spending plans. This allows for a realistic plan tailored to the user's lifestyle. This allows for a more accurate plan to be provided by analyzing the user's past financial behavior data.

[0031] The plan generation unit can add questions that reflect the user's lifestyle and values ​​and generate a personalized plan. The plan generation unit, for example, adds questions about the user's hobbies, interests, and values ​​and customizes the plan based on them. For example, a user who likes to travel is suggested a savings plan that takes travel expenses into account. The plan generation unit also adds questions about the user's lifestyle (e.g., health-consciousness, eco-consciousness) and personalizes the plan based on them. For example, a health-conscious user is provided with a plan that takes health-related expenses into account. The plan generation unit also adds questions about the user's future goals and dreams and generates a plan based on them. For example, a user who wants to start a business is suggested methods for preparing startup funds. In this way, personalized plans can be generated by adding questions that reflect the user's lifestyle and values.

[0032] The setting information acquisition unit allows the user to provide setting information by voice input, thereby improving convenience. The setting information acquisition unit, for example, allows the user to input basic information (age, income, family composition, etc.) by voice. For example, the user inputs "I am 35 years old and my annual income is 5 million yen." The setting information acquisition unit also uses voice recognition technology to build a system that can provide setting information by the user answering questions by voice. For example, the user inputs "I would like to plan my children's education expenses." The setting information acquisition unit also uses voice input to develop an interface that allows the user to easily provide setting information. For example, the voice input content is converted into text in real time and a confirmation screen is displayed. This allows the user to provide setting information by voice input, thereby improving convenience.

[0033] The setting information acquisition unit can work in conjunction with other financial services to automatically acquire setting information. The setting information acquisition unit, for example, works in conjunction with the user's bank account or credit card account to automatically acquire transaction history and balance information. This allows for an accurate understanding of the user's financial situation. The setting information acquisition unit also works in conjunction with investment accounts to automatically acquire the user's investment portfolio and risk tolerance. This allows for the proposal of an optimal investment strategy. The setting information acquisition unit also works in conjunction with other financial services (for example, insurance accounts) to automatically acquire the user's insurance contract information. This allows for the provision of plans that take into account insurance premiums and coverage details. This allows for the automatic acquisition of setting information by working in conjunction with other financial services.

[0034] The plan generation unit can use the generation AI to predict fluctuations in education costs by region and propose an optimal savings plan. For example, the plan generation unit uses the generation AI to analyze past data on education costs by region and predict future cost fluctuations. For example, it proposes a savings plan that takes into account differences in education costs between urban and rural areas. The plan generation unit also predicts fluctuations in education costs by region and builds a system that proposes an optimal savings plan based on that prediction. For example, it advises users in regions where education costs are rising to start saving early. The plan generation unit also uses the generation AI to predict future education costs by region and provide users with an optimal savings plan. For example, it proposes a savings plan with reduced risk in regions where education costs are stable. This makes it possible to predict fluctuations in education costs by region and propose an optimal savings plan.

[0035] The plan generation unit can provide an educational plan that takes into account the academic performance and interests of the user's child. For example, the plan generation unit inputs the user's child's academic performance and interests and provides an educational plan based on the input. For example, for a child interested in science, a plan aimed at entering a science university is proposed. The plan generation unit also builds a system that generates an optimal educational plan taking into account the child's academic performance and interests. For example, for a child interested in a specific field, an educational plan specialized for that field is provided. The plan generation unit also proposes an educational plan that takes into account the user's child's future path and career based on the user's child's academic performance and interests. For example, for a child interested in music, a plan aimed at entering a music university is provided. In this way, an educational plan that takes into account the user's child's academic performance and interests can be provided.

[0036] The plan generation unit can provide a plan that also takes into account the costs of studying abroad or at an international school. For example, the plan generation unit provides an educational plan that takes into account the costs required for studying abroad. For example, it estimates tuition fees and living expenses at the destination and proposes a savings plan based on these. The plan generation unit also provides an educational plan that takes into account the costs of international schools. For example, it estimates tuition fees, textbook fees, and other related expenses and proposes a savings plan based on these. The plan generation unit also builds a system that takes into account the costs of studying abroad or at an international school and provides an optimal educational plan. For example, it suggests how to select a study abroad destination and how to use scholarships. This makes it possible to provide a plan that also takes into account the costs of studying abroad or at an international school.

[0037] The plan generation unit can automate the application procedures for educational loans or scholarships and propose them to users. The plan generation unit, for example, builds a system that automates the application procedures for educational loans and proposes them to users. For example, it automatically generates the necessary documents and completes the application procedures online. The plan generation unit also develops a system that automates the application procedures for scholarships and proposes them to users. For example, it automatically searches for scholarships that meet the user's conditions and supports the application procedures. The plan generation unit also builds a system that automates the application procedures for educational loans and scholarships and proposes the most suitable options to users. For example, it provides a comparison of multiple loans and scholarships and proposes the most suitable option. In this way, the application procedures for educational loans and scholarships can be automated and proposed to users.

[0038] The plan generation unit can use the generation AI to predict trends in the real estate market for each region and suggest the optimal time to purchase. For example, the plan generation unit uses the generation AI to analyze past data on the real estate market for each region and predict future market trends. For example, it analyzes rising and falling price trends and suggests the optimal time to purchase. The plan generation unit also predicts trends in the real estate market for each region and builds a system that suggests the optimal time to purchase based on that. For example, it suggests purchasing during periods when prices are stable or when demand is low. The plan generation unit also uses the generation AI to predict the future real estate market for each region and provide the user with the optimal time to purchase. For example, it proposes a plan that recommends purchasing before prices rise. This makes it possible to predict trends in the real estate market for each region and suggest the optimal time to purchase.

[0039] The plan generation unit can provide a home plan that takes into account the user's lifestyle and future plans. The plan generation unit, for example, takes into account the user's lifestyle (e.g., whether they have a pet or like the outdoors) and provides a home plan based on that. For example, it can propose a pet-friendly home or a home with plenty of outdoor facilities. The plan generation unit also takes into account the user's future plans (e.g., whether they plan to have a larger family or continue working remotely) and provides a home plan based on that. For example, it can propose a home with many rooms or a home that can accommodate a home office. The plan generation unit also builds a system that provides an optimal home plan based on the user's lifestyle and future plans. For example, it can propose a customizable home plan that meets the user's needs. This makes it possible to provide a home plan that takes into account the user's lifestyle and future plans.

[0040] The plan generation unit can provide a comprehensive home plan that also includes the cost of remodeling or renovation. The plan generation unit provides, for example, a comprehensive home plan that takes into account the cost of remodeling or renovation after purchasing a home. For example, it proposes a plan that includes a remodeling estimate and a renovation plan. The plan generation unit also builds a system that provides a comprehensive home plan that includes the cost of remodeling or renovation. For example, it proposes the selection of a remodeling contractor and a renovation schedule. The plan generation unit also takes into account the cost of remodeling or renovation after purchasing a home and provides an optimal home plan. For example, it proposes a plan that takes into account the need for remodeling and the effects of renovation. This makes it possible to provide a comprehensive home plan that also includes the cost of remodeling or renovation.

[0041] The plan generation unit can provide a long-term plan that also takes into account maintenance costs or taxes after purchasing a home. The plan generation unit provides, for example, a long-term plan that takes into account maintenance costs (e.g., repair costs, management fees) and taxes (property taxes, etc.) after purchasing a home. For example, it estimates annual maintenance costs and taxes and proposes a savings plan based on them. The plan generation unit also builds a system that provides a long-term plan that takes into account maintenance costs and taxes after purchasing a home. For example, it proposes a payment schedule for maintenance costs and taxes. The plan generation unit also takes into account maintenance costs and taxes after purchasing a home and provides an optimal long-term plan. For example, it provides advice on how to reduce the burden of maintenance costs and taxes. This makes it possible to provide a long-term plan that takes into account maintenance costs and taxes after purchasing a home.

[0042] The plan generation unit can use the generation AI to analyze the user's past life event data and propose an optimal financial plan. For example, the plan generation unit can use the generation AI to analyze the user's past life event data (e.g., marriage, childbirth, retirement, etc.) and propose an optimal financial plan for future life events. For example, a savings plan can be created based on past spending patterns. The plan generation unit can also analyze the user's past life event data and build a system that provides an optimal financial plan based on that data. For example, a savings plan for future events can be proposed based on the expenses incurred for past events. The plan generation unit can also use the generation AI to analyze the user's past life event data and provide a specific financial plan for future life events. For example, the plan generation unit can estimate the expenses for marriage and childbirth and propose a savings plan based on that. In this way, the user's past life event data can be analyzed and an optimal financial plan can be proposed.

[0043] The plan generation unit can provide an individualized life event plan that reflects the user's values ​​and lifestyle. The plan generation unit provides an individualized life event plan that reflects, for example, the user's values ​​(e.g., family-oriented, career-oriented, etc.) and lifestyle (e.g., health-conscious, eco-conscious). For example, a plan that emphasizes family events is proposed to a family-conscious user. The plan generation unit also builds a system that provides an optimal life event plan based on the user's values ​​and lifestyle. For example, a plan that emphasizes health-related events is proposed to a health-conscious user. The plan generation unit also provides an individualized life event plan that reflects the user's values ​​and lifestyle. For example, an environmentally conscious event plan is proposed to an eco-conscious user. In this way, an individualized life event plan that reflects the user's values ​​and lifestyle can be provided.

[0044] The plan generation unit can provide a plan that takes into account special life events such as overseas travel or studying abroad. The plan generation unit provides a life event plan that takes into account the expenses required for overseas travel, for example. For example, it estimates the expenses at the travel destination and the cost of living, and proposes a savings plan based on that. The plan generation unit also provides a life event plan that takes into account the expenses required for studying abroad. For example, it estimates tuition fees, living expenses, and other related expenses, and proposes a savings plan based on that. The plan generation unit also builds a system that takes into account special life events such as overseas travel or studying abroad and provides an optimal plan. For example, it suggests how to select a travel destination and how to use scholarships. This makes it possible to provide a plan that takes into account special life events such as overseas travel or studying abroad.

[0045] The plan generation unit can automatically suggest insurance or financial products related to life events. The plan generation unit, for example, builds a system that automatically suggests insurance (e.g., wedding insurance, maternity insurance) or financial products (e.g., education loans, home loans) related to life events. For example, it automatically searches for and suggests insurance or financial products that meet the user's conditions. The plan generation unit also develops a system that automatically suggests insurance or financial products related to life events. For example, it automatically searches for insurance or financial products that meet the user's conditions and supports the application procedure. The plan generation unit also builds a system that automatically suggests insurance or financial products related to life events. For example, it provides a comparison result of multiple insurance or financial products and suggests the optimal option. This makes it possible to automatically suggest insurance or financial products related to life events.

[0046] The plan generation unit can use the generation AI to propose an optimal investment strategy for achieving the user's long-term goals. For example, the plan generation unit uses the generation AI to analyze the user's past investment history and risk tolerance and propose an optimal investment strategy. For example, it provides an investment portfolio that maximizes returns while minimizing risk. The plan generation unit also builds a system that proposes an optimal investment strategy based on the user's long-term goals (e.g., retirement living expenses and children's education expenses). For example, it specifically indicates the investment amount and period required to achieve the goal. The plan generation unit also uses the generation AI to update the investment strategy for achieving the user's long-term goals in real time and provide an optimal plan. For example, it adjusts the investment strategy in response to market fluctuations. This makes it possible to propose an optimal investment strategy for achieving the user's long-term goals.

[0047] The plan generation unit can provide a long-term plan that reflects the user's lifestyle and values. The plan generation unit provides, for example, a long-term plan that reflects the user's lifestyle (e.g., health-conscious, eco-conscious) and values ​​(e.g., family-oriented, career-oriented). For example, a plan that takes health-related expenses into consideration is proposed for a health-conscious user. The plan generation unit also builds a system that provides an optimal long-term plan based on the user's values ​​and lifestyle. For example, a plan that emphasizes family events is proposed for a family-oriented user. The plan generation unit also provides a long-term plan that reflects the user's lifestyle and values. For example, an environmentally friendly plan is proposed for an eco-conscious user. In this way, a long-term plan that reflects the user's lifestyle and values ​​can be provided.

[0048] The plan generation unit can provide a long-term plan according to the user's health condition and life stage. The plan generation unit provides, for example, a long-term plan that takes into account the user's health condition (e.g., whether or not the user has a chronic illness, health checkup results). For example, it proposes a savings plan that takes into account expenses for maintaining health. The plan generation unit also builds a system that provides long-term plans according to the user's life stage (e.g., marriage, childbirth, retirement). For example, it estimates expenses and income for each life stage and proposes a plan based on that. The plan generation unit also provides an optimal long-term plan based on the user's health condition and life stage. For example, it proposes an estimated medical expense according to the user's health condition and an expenditure plan according to the user's life stage. This makes it possible to provide a long-term plan according to the user's health condition and life stage.

[0049] The plan generation unit can automatically suggest insurance or financial products related to a long-term plan. The plan generation unit, for example, builds a system that automatically suggests insurance (e.g., life insurance, medical insurance) or financial products (e.g., pensions, investment trusts) related to a long-term plan. For example, it automatically searches for and suggests insurance or financial products that meet a user's conditions. The plan generation unit also develops a system that automatically suggests insurance or financial products related to a long-term plan. For example, it automatically searches for insurance or financial products that meet a user's conditions and supports application procedures. The plan generation unit also builds a system that automatically suggests insurance or financial products related to a long-term plan. For example, it provides a comparison result of multiple insurance or financial products and suggests the optimal option. This makes it possible to automatically suggest insurance or financial products related to a long-term plan.

[0050] The plan correction unit can use the generation AI to provide real-time plan corrections in response to changes in the user's situation. For example, the plan correction unit uses the generation AI to analyze fluctuations in the user's income and expenses in real time and revise the plan based on the results. For example, if income increases, the plan correction unit suggests increasing savings. The plan correction unit also builds a system that provides real-time plan corrections in response to changes in the user's situation (for example, changes in family composition or health condition). For example, if the number of family members increases, the plan correction unit suggests reviewing education expenses. The plan correction unit also uses the generation AI to provide real-time plan corrections in response to changes in the user's situation. For example, if the user's health condition worsens, the plan correction unit revise the estimated medical expenses. This makes it possible to provide real-time plan corrections in response to changes in the user's situation.

[0051] The plan correction unit can provide plan corrections that reflect changes in the user's lifestyle and values. The plan correction unit, for example, provides plan corrections that reflect changes in the user's lifestyle (e.g., health-consciousness, eco-consciousness). For example, if the user becomes more health-conscious, a suggestion is made to increase health-related spending. The plan correction unit also constructs a system that provides plan corrections that reflect changes in the user's values ​​(e.g., family-focused, career-focused). For example, if the user becomes more career-focused, a suggestion is made to increase spending for career advancement. The plan correction unit also provides plan corrections that reflect changes in the user's lifestyle and values. For example, if the user becomes more eco-conscious, a suggestion is made to increase environmentally friendly spending. In this way, it is possible to provide plan corrections that reflect changes in the user's lifestyle and values.

[0052] The plan correction unit can provide plan corrections in accordance with changes in the user's health condition or life stage. The plan correction unit, for example, provides plan corrections that reflect changes in the user's health condition (e.g., whether or not the user has a chronic illness, health checkup results). For example, if the user's health condition worsens, the plan correction unit corrects the estimated medical expenses. The plan correction unit also builds a system that provides plan corrections in accordance with changes in the user's life stage (e.g., marriage, childbirth, retirement). For example, it estimates expenses and income for each life stage and proposes a plan based on that. The plan correction unit also provides optimal plan corrections based on changes in the user's health condition or life stage. For example, it proposes estimated medical expenses according to the user's health condition and a spending plan according to the life stage. This makes it possible to provide plan corrections in accordance with changes in the user's health condition or life stage.

[0053] The plan adjustment unit can automatically suggest insurance or financial products related to the plan adjustment. The plan adjustment unit, for example, builds a system that automatically suggests insurance (e.g., life insurance, medical insurance) or financial products (e.g., pensions, investment trusts) related to the plan adjustment. For example, it automatically searches for and suggests insurance or financial products that meet the user's conditions. The plan adjustment unit also develops a system that automatically suggests insurance or financial products related to the plan adjustment. For example, it automatically searches for insurance or financial products that meet the user's conditions and supports the application procedure. The plan adjustment unit also builds a system that automatically suggests insurance or financial products related to the plan adjustment. For example, it provides a comparison result of multiple insurance or financial products and suggests the optimal option. This makes it possible to automatically suggest insurance or financial products related to the plan adjustment.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The setting information acquisition unit can also acquire information about the user's health condition. For example, if the user has a chronic illness, by inputting that information, a plan that takes health-related expenses into consideration can be provided. The setting information acquisition unit can also estimate future medical expenses by inputting the user's health checkup results. Furthermore, it can also propose a spending plan for maintaining health based on the user's health condition. This makes it possible to provide the user with an optimal financial plan tailored to their health condition.

[0056] The plan generation unit can also provide plans based on the user's hobbies and interests. For example, a savings plan that takes travel expenses into account is proposed for a user who enjoys traveling. Also, a plan that takes sports-related expenses into account is proposed for a user who enjoys sports. Furthermore, the plan generation unit can also propose savings plans for future life events based on the user's hobbies and interests. This makes it possible to provide a personalized plan that matches the user's hobbies and interests.

[0057] The plan generation unit can also provide a plan based on the user's values. For example, it can suggest eco-friendly investments to a user who is interested in environmental protection. It can also provide a plan that takes socially responsible investment (SRI) into consideration to a user who places importance on contributing to society. Furthermore, the plan generation unit can also suggest savings plans for future life events based on the user's values. This makes it possible to provide a personalized plan that matches the user's values.

[0058] The setting information acquisition unit can automatically acquire the user's past financial behavior data and provide it to the plan generation unit. For example, the setting information acquisition unit can automatically acquire the user's bank transaction history and credit card usage history to understand spending patterns and savings tendencies. The setting information acquisition unit also links with the user's investment account to automatically acquire the user's past investment history and risk tolerance. Furthermore, the setting information acquisition unit can automatically acquire the user's past income fluctuations and spending tendencies to create future income forecasts and spending plans. By automatically acquiring the user's past financial behavior data and providing it to the plan generation unit, a more accurate plan can be provided.

[0059] The plan generation unit can use generation AI to predict fluctuations in education costs by region and propose an optimal savings plan. For example, generation AI can be used to analyze past data on education costs by region and predict future cost fluctuations. For example, a savings plan can be proposed that takes into account differences in education costs between urban and rural areas. The plan generation unit can also predict fluctuations in education costs by region and build a system that proposes an optimal savings plan based on that prediction. For example, in regions where education costs are rising, it can advise users to start saving early. The plan generation unit can also use generation AI to predict future education costs by region and provide users with an optimal savings plan. For example, in regions where education costs are stable, it can propose a savings plan with reduced risk. This makes it possible to predict fluctuations in education costs by region and propose an optimal savings plan.

[0060] The plan generation unit can provide an educational plan that takes into account the academic performance and interests of the user's child. For example, by inputting the user's child's academic performance and interests, an educational plan based on that can be provided. For example, for a child interested in science, a plan aimed at entering a science university can be proposed. The plan generation unit also builds a system that generates an optimal educational plan taking into account the child's academic performance and interests. For example, for a child interested in a particular field, an educational plan specialized for that field can be provided. The plan generation unit also proposes an educational plan that takes into account the user's child's future path and career based on the user's child's academic performance and interests. For example, for a child interested in music, a plan aimed at entering a music university can be proposed. In this way, an educational plan that takes into account the user's child's academic performance and interests can be provided.

[0061] The processing flow of the first embodiment will be briefly explained below.

[0062] Step 1: The setting information acquisition unit acquires basic setting information of the user. For example, the setting information acquisition unit collects this information by inputting information such as age, income, and family composition. Step 2: The plan generation unit generates plans related to education, home purchases, and life events based on the setting information acquired by the setting information acquisition unit. For example, if the user inputs "I want to plan my child's education expenses," the plan generation unit will use that information to estimate education expenses and propose savings plans. Step 3: The plan modification unit modifies the plan generated by the plan generation unit according to the user's current situation and goals. For example, if the user's income increases or their family structure changes, the plan modification unit reevaluates the plan and provides an optimal plan.

[0063] (Example 2) The financial planner system according to the embodiment of the present invention acquires basic setting information from a user, generates a plan using a generation AI, and modifies the plan according to the user's situation and goals. This allows the financial planner system to provide an optimal financial plan tailored to the user's life.

[0064] A financial planner system according to an embodiment includes a setting information acquisition unit, a plan generation unit, and a plan correction unit. The setting information acquisition unit acquires basic setting information about a user. For example, the setting information acquisition unit collects information such as age, income, and family structure by inputting the information. The plan generation unit generates plans related to education, home purchase, and life events based on the setting information acquired by the setting information acquisition unit. For example, if a user inputs, "I want to plan my children's education expenses," the plan generation unit proposes an estimated education expense and a savings plan based on the information. The plan correction unit corrects the plan generated by the plan generation unit according to the user's current situation and goals. For example, if the user's income increases or their family structure changes, the plan correction unit reevaluates the plan and provides an optimal plan. This allows the financial planner system according to an embodiment to provide an optimal financial plan tailored to the user's life. For example, the user can plan their children's education expenses while preparing for home purchases and life events. Furthermore, even if the situation changes, the optimal plan can be maintained by making appropriate corrections.

[0065] The plan generation unit uses the generation AI to analyze the user's past financial behavior data and provide a more accurate plan. For example, the plan generation unit uses the generation AI to analyze the user's past bank transaction history and credit card usage history to understand spending patterns and savings tendencies. This allows for a more accurate plan based on the user's actual financial behavior. The plan generation unit also uses the generation AI to analyze the user's past investment history and risk tolerance to propose an optimal investment strategy. For example, it provides a plan that minimizes risk based on past investment successes and failures. The plan generation unit also uses the generation AI to analyze the user's past income fluctuations and spending tendencies to create future income forecasts and spending plans. This allows for a realistic plan tailored to the user's lifestyle. This allows for a more accurate plan to be provided by analyzing the user's past financial behavior data.

[0066] The plan generation unit can add questions that reflect the user's lifestyle and values ​​and generate a personalized plan. The plan generation unit, for example, adds questions about the user's hobbies, interests, and values ​​and customizes the plan based on them. For example, a user who likes to travel is suggested a savings plan that takes travel expenses into account. The plan generation unit also adds questions about the user's lifestyle (e.g., health-consciousness, eco-consciousness) and personalizes the plan based on them. For example, a health-conscious user is provided with a plan that takes health-related expenses into account. The plan generation unit also adds questions about the user's future goals and dreams and generates a plan based on them. For example, a user who wants to start a business is suggested methods for preparing startup funds. In this way, personalized plans can be generated by adding questions that reflect the user's lifestyle and values.

[0067] The plan generation unit can use the emotion estimation function to provide an interface for reducing stress or anxiety felt by the user when entering data. For example, the plan generation unit analyzes the user's facial expressions and voice when entering data, and displays a message to help the user relax if the user feels stressed or anxious. For example, it displays a message such as "It's okay, please proceed slowly." The plan generation unit also uses the emotion estimation function to monitor the user's emotional state when entering data in real time, and changes the interface design if the user feels stressed. For example, it changes the color or font to enhance the relaxation effect. The plan generation unit also provides appropriate advice and support based on the emotion estimation data when the user enters data. For example, if the user finds entering data difficult, it divides the data into simple questions to prompt the user to enter data. This makes it possible to provide an interface for reducing stress and anxiety felt by the user when entering data.

[0068] The setting information acquisition unit allows the user to provide setting information by voice input, thereby improving convenience. The setting information acquisition unit, for example, allows the user to input basic information (age, income, family composition, etc.) by voice. For example, the user inputs "I am 35 years old and my annual income is 5 million yen." The setting information acquisition unit also uses voice recognition technology to build a system that can provide setting information by the user answering questions by voice. For example, the user inputs "I would like to plan my children's education expenses." The setting information acquisition unit also uses voice input to develop an interface that allows the user to easily provide setting information. For example, the voice input content is converted into text in real time and a confirmation screen is displayed. This allows the user to provide setting information by voice input, thereby improving convenience.

[0069] The setting information acquisition unit can work in conjunction with other financial services to automatically acquire setting information. The setting information acquisition unit, for example, works in conjunction with the user's bank account or credit card account to automatically acquire transaction history and balance information. This allows for an accurate understanding of the user's financial situation. The setting information acquisition unit also works in conjunction with investment accounts to automatically acquire the user's investment portfolio and risk tolerance. This allows for the proposal of an optimal investment strategy. The setting information acquisition unit also works in conjunction with other financial services (for example, insurance accounts) to automatically acquire the user's insurance contract information. This allows for the provision of plans that take into account insurance premiums and coverage details. This allows for the automatic acquisition of setting information by working in conjunction with other financial services.

[0070] The plan generation unit can use the emotion estimation function to analyze the emotions of the user when entering text in real time and provide positive feedback. For example, the plan generation unit analyzes the user's facial expressions and voice when entering text, and displays an encouraging message if the user is feeling positive emotions. For example, it displays a message such as "Great, keep it up." The plan generation unit also uses the emotion estimation function to monitor the user's emotional state when entering text in real time and provides an interface for eliciting positive emotions. For example, it displays success stories and positive feedback. The plan generation unit also provides feedback in real time based on the emotion estimation data when the user is entering text, and provides advice to strengthen positive emotions. For example, it displays appropriate encouragement or praise according to the content of the entry. In this way, the user's emotions when entering text can be analyzed in real time and positive feedback can be provided.

[0071] The plan generation unit can use the generation AI to predict fluctuations in education costs by region and propose an optimal savings plan. For example, the plan generation unit uses the generation AI to analyze past data on education costs by region and predict future cost fluctuations. For example, it proposes a savings plan that takes into account differences in education costs between urban and rural areas. The plan generation unit also predicts fluctuations in education costs by region and builds a system that proposes an optimal savings plan based on that prediction. For example, it advises users in regions where education costs are rising to start saving early. The plan generation unit also uses the generation AI to predict future education costs by region and provide users with an optimal savings plan. For example, it proposes a savings plan with reduced risk in regions where education costs are stable. This makes it possible to predict fluctuations in education costs by region and propose an optimal savings plan.

[0072] The plan generation unit can provide an educational plan that takes into account the academic performance and interests of the user's child. For example, the plan generation unit inputs the user's child's academic performance and interests and provides an educational plan based on the input. For example, for a child interested in science, a plan aimed at entering a science university is proposed. The plan generation unit also builds a system that generates an optimal educational plan taking into account the child's academic performance and interests. For example, for a child interested in a specific field, an educational plan specialized for that field is provided. The plan generation unit also proposes an educational plan that takes into account the user's child's future path and career based on the user's child's academic performance and interests. For example, for a child interested in music, a plan aimed at entering a music university is provided. In this way, an educational plan that takes into account the user's child's academic performance and interests can be provided.

[0073] The plan generation unit can use the emotion estimation function to provide advice to reduce parents' anxiety about education costs. For example, the plan generation unit uses the emotion estimation function to analyze parents' anxiety about education costs in real time and provide advice based on the results. For example, the plan generation unit displays a message such as "Don't worry, there will be no problem if you proceed as planned." The plan generation unit also builds a system that provides advice to reduce parents' anxiety about education costs. For example, based on the emotion estimation data, it displays a message to help parents relax if they are feeling anxious. The plan generation unit also uses the emotion estimation function to provide specific advice to reduce parents' anxiety about education costs. For example, it suggests ways to use scholarships or educational loans. This makes it possible to provide advice to reduce parents' anxiety about education costs.

[0074] The plan generation unit can provide a plan that also takes into account the costs of studying abroad or at an international school. For example, the plan generation unit provides an educational plan that takes into account the costs required for studying abroad. For example, it estimates tuition fees and living expenses at the destination and proposes a savings plan based on these. The plan generation unit also provides an educational plan that takes into account the costs of international schools. For example, it estimates tuition fees, textbook fees, and other related expenses and proposes a savings plan based on these. The plan generation unit also builds a system that takes into account the costs of studying abroad or at an international school and provides an optimal educational plan. For example, it suggests how to select a study abroad destination and how to use scholarships. This makes it possible to provide a plan that also takes into account the costs of studying abroad or at an international school.

[0075] The plan generation unit can automate the application procedures for educational loans or scholarships and propose them to users. The plan generation unit, for example, builds a system that automates the application procedures for educational loans and proposes them to users. For example, it automatically generates the necessary documents and completes the application procedures online. The plan generation unit also develops a system that automates the application procedures for scholarships and proposes them to users. For example, it automatically searches for scholarships that meet the user's conditions and supports the application procedures. The plan generation unit also builds a system that automates the application procedures for educational loans and scholarships and proposes the most suitable options to users. For example, it provides a comparison of multiple loans and scholarships and proposes the most suitable option. In this way, the application procedures for educational loans and scholarships can be automated and proposed to users.

[0076] The plan generation unit can use the emotion estimation function to analyze parents' emotions regarding their child's education and propose an optimal education plan. For example, the plan generation unit can use the emotion estimation function to analyze parents' emotions regarding their child's education in real time and propose an optimal education plan based on the results. For example, if a parent is feeling anxious, the plan generation unit can display a message to help the parent relax. The plan generation unit can also analyze parents' emotions regarding their child's education and build a system that provides an optimal education plan based on the results. For example, the plan generation unit can propose a plan that puts parents at ease based on the emotion data. The plan generation unit can also use the emotion estimation function to analyze parents' emotions regarding their child's education and provide specific advice based on the results. For example, if a parent is feeling anxious, the plan generation unit can suggest ways to use scholarships or educational loans. In this way, parents' emotions regarding their child's education can be analyzed and an optimal education plan can be proposed.

[0077] The plan generation unit can use the generation AI to predict trends in the real estate market for each region and suggest the optimal time to purchase. For example, the plan generation unit uses the generation AI to analyze past data on the real estate market for each region and predict future market trends. For example, it analyzes rising and falling price trends and suggests the optimal time to purchase. The plan generation unit also predicts trends in the real estate market for each region and builds a system that suggests the optimal time to purchase based on that. For example, it suggests purchasing during periods when prices are stable or when demand is low. The plan generation unit also uses the generation AI to predict the future real estate market for each region and provide the user with the optimal time to purchase. For example, it proposes a plan that recommends purchasing before prices rise. This makes it possible to predict trends in the real estate market for each region and suggest the optimal time to purchase.

[0078] The plan generation unit can provide a home plan that takes into account the user's lifestyle and future plans. The plan generation unit, for example, takes into account the user's lifestyle (e.g., whether they have a pet or like the outdoors) and provides a home plan based on that. For example, it can propose a pet-friendly home or a home with plenty of outdoor facilities. The plan generation unit also takes into account the user's future plans (e.g., whether they plan to have a larger family or continue working remotely) and provides a home plan based on that. For example, it can propose a home with many rooms or a home that can accommodate a home office. The plan generation unit also builds a system that provides an optimal home plan based on the user's lifestyle and future plans. For example, it can propose a customizable home plan that meets the user's needs. This makes it possible to provide a home plan that takes into account the user's lifestyle and future plans.

[0079] The plan generation unit can use the emotion estimation function to provide advice to reduce a user's anxiety about purchasing a home. For example, the plan generation unit uses the emotion estimation function to analyze a user's anxiety about purchasing a home in real time and provide advice based on the results. For example, the plan generation unit displays a message such as "Don't worry, there will be no problem if you proceed as planned." The plan generation unit also builds a system that provides advice to reduce a user's anxiety about purchasing a home. For example, based on the emotion estimation data, it displays a message to relax a user who is feeling anxious. The plan generation unit also uses the emotion estimation function to provide specific advice to reduce a user's anxiety about purchasing a home. For example, it provides information on how to use a mortgage and maintenance costs after purchase. This makes it possible to provide advice to reduce a user's anxiety about purchasing a home.

[0080] The plan generation unit can provide a comprehensive home plan that also includes the cost of remodeling or renovation. The plan generation unit provides, for example, a comprehensive home plan that takes into account the cost of remodeling or renovation after purchasing a home. For example, it proposes a plan that includes a remodeling estimate and a renovation plan. The plan generation unit also builds a system that provides a comprehensive home plan that includes the cost of remodeling or renovation. For example, it proposes the selection of a remodeling contractor and a renovation schedule. The plan generation unit also takes into account the cost of remodeling or renovation after purchasing a home and provides an optimal home plan. For example, it proposes a plan that takes into account the need for remodeling and the effects of renovation. This makes it possible to provide a comprehensive home plan that also includes the cost of remodeling or renovation.

[0081] The plan generation unit can provide a long-term plan that also takes into account maintenance costs or taxes after purchasing a home. The plan generation unit provides, for example, a long-term plan that takes into account maintenance costs (e.g., repair costs, management fees) and taxes (property taxes, etc.) after purchasing a home. For example, it estimates annual maintenance costs and taxes and proposes a savings plan based on them. The plan generation unit also builds a system that provides a long-term plan that takes into account maintenance costs and taxes after purchasing a home. For example, it proposes a payment schedule for maintenance costs and taxes. The plan generation unit also takes into account maintenance costs and taxes after purchasing a home and provides an optimal long-term plan. For example, it provides advice on how to reduce the burden of maintenance costs and taxes. This makes it possible to provide a long-term plan that takes into account maintenance costs and taxes after purchasing a home.

[0082] The plan generation unit can use the emotion estimation function to analyze a user's emotions regarding home purchases and propose an optimal purchase plan. For example, the plan generation unit can use the emotion estimation function to analyze a user's emotions regarding home purchases in real time and propose an optimal purchase plan based on the results. For example, if a user is feeling anxious, the plan generation unit displays a message to help the user relax. The plan generation unit can also analyze a user's emotions regarding home purchases and build a system that provides an optimal purchase plan based on the results. For example, based on the emotion data, the plan generation unit can propose a plan that gives the user peace of mind. The plan generation unit can also use the emotion estimation function to analyze a user's emotions regarding home purchases and provide specific advice based on the results. For example, if a user is feeling anxious, the plan generation unit can provide information on how to use a mortgage and maintenance costs after purchase. In this way, the user's emotions regarding home purchases can be analyzed and an optimal purchase plan can be proposed.

[0083] The plan generation unit can use the generation AI to analyze the user's past life event data and propose an optimal financial plan. For example, the plan generation unit can use the generation AI to analyze the user's past life event data (e.g., marriage, childbirth, retirement, etc.) and propose an optimal financial plan for future life events. For example, a savings plan can be created based on past spending patterns. The plan generation unit can also analyze the user's past life event data and build a system that provides an optimal financial plan based on that data. For example, a savings plan for future events can be proposed based on the expenses incurred for past events. The plan generation unit can also use the generation AI to analyze the user's past life event data and provide a specific financial plan for future life events. For example, the plan generation unit can estimate the expenses for marriage and childbirth and propose a savings plan based on that. In this way, the user's past life event data can be analyzed and an optimal financial plan can be proposed.

[0084] The plan generation unit can provide an individualized life event plan that reflects the user's values ​​and lifestyle. The plan generation unit provides an individualized life event plan that reflects, for example, the user's values ​​(e.g., family-oriented, career-oriented, etc.) and lifestyle (e.g., health-conscious, eco-conscious). For example, a plan that emphasizes family events is proposed to a family-conscious user. The plan generation unit also builds a system that provides an optimal life event plan based on the user's values ​​and lifestyle. For example, a plan that emphasizes health-related events is proposed to a health-conscious user. The plan generation unit also provides an individualized life event plan that reflects the user's values ​​and lifestyle. For example, an environmentally conscious event plan is proposed to an eco-conscious user. In this way, an individualized life event plan that reflects the user's values ​​and lifestyle can be provided.

[0085] The plan generation unit can use the emotion estimation function to provide advice to reduce a user's anxiety about a life event. For example, the plan generation unit uses the emotion estimation function to analyze a user's anxiety about a life event in real time and provide advice based on the results. For example, the plan generation unit displays a message such as "Don't worry, there will be no problem if you proceed as planned." The plan generation unit also builds a system that provides advice to reduce a user's anxiety about a life event. For example, based on the emotion estimation data, the plan generation unit displays a message to help the user relax when the user feels anxious. The plan generation unit also uses the emotion estimation function to provide specific advice to reduce a user's anxiety about a life event. For example, the plan generation unit provides information about the costs involved in marriage and childbirth. This makes it possible to provide advice to reduce a user's anxiety about a life event.

[0086] The plan generation unit can provide a plan that takes into account special life events such as overseas travel or studying abroad. The plan generation unit provides a life event plan that takes into account the expenses required for overseas travel, for example. For example, it estimates the expenses at the travel destination and the cost of living, and proposes a savings plan based on that. The plan generation unit also provides a life event plan that takes into account the expenses required for studying abroad. For example, it estimates tuition fees, living expenses, and other related expenses, and proposes a savings plan based on that. The plan generation unit also builds a system that takes into account special life events such as overseas travel or studying abroad and provides an optimal plan. For example, it suggests how to select a travel destination and how to use scholarships. This makes it possible to provide a plan that takes into account special life events such as overseas travel or studying abroad.

[0087] The plan generation unit can automatically suggest insurance or financial products related to life events. The plan generation unit, for example, builds a system that automatically suggests insurance (e.g., wedding insurance, maternity insurance) or financial products (e.g., education loans, home loans) related to life events. For example, it automatically searches for and suggests insurance or financial products that meet the user's conditions. The plan generation unit also develops a system that automatically suggests insurance or financial products related to life events. For example, it automatically searches for insurance or financial products that meet the user's conditions and supports the application procedure. The plan generation unit also builds a system that automatically suggests insurance or financial products related to life events. For example, it provides a comparison result of multiple insurance or financial products and suggests the optimal option. This makes it possible to automatically suggest insurance or financial products related to life events.

[0088] The plan generation unit can use the emotion estimation function to analyze the user's emotions regarding life events and propose an optimal plan. For example, the plan generation unit can use the emotion estimation function to analyze the user's emotions regarding life events in real time and propose an optimal plan based on the results. For example, if the user is feeling anxious, the plan generation unit can display a message to help the user relax. The plan generation unit can also analyze the user's emotions regarding life events and build a system that provides an optimal plan based on the results. For example, the plan generation unit can propose a plan that makes the user feel at ease based on the emotion data. The plan generation unit can also use the emotion estimation function to analyze the user's emotions regarding life events and provide specific advice based on the results. For example, if the user is feeling anxious, the plan generation unit can provide information about the costs of marriage and childbirth. This makes it possible to analyze the user's emotions regarding life events and propose an optimal plan.

[0089] The plan generation unit can use the generation AI to propose an optimal investment strategy for achieving the user's long-term goals. For example, the plan generation unit uses the generation AI to analyze the user's past investment history and risk tolerance and propose an optimal investment strategy. For example, it provides an investment portfolio that maximizes returns while minimizing risk. The plan generation unit also builds a system that proposes an optimal investment strategy based on the user's long-term goals (e.g., retirement living expenses and children's education expenses). For example, it specifically indicates the investment amount and period required to achieve the goal. The plan generation unit also uses the generation AI to update the investment strategy for achieving the user's long-term goals in real time and provide an optimal plan. For example, it adjusts the investment strategy in response to market fluctuations. This makes it possible to propose an optimal investment strategy for achieving the user's long-term goals.

[0090] The plan generation unit can provide a long-term plan that reflects the user's lifestyle and values. The plan generation unit provides, for example, a long-term plan that reflects the user's lifestyle (e.g., health-conscious, eco-conscious) and values ​​(e.g., family-oriented, career-oriented). For example, a plan that takes health-related expenses into consideration is proposed for a health-conscious user. The plan generation unit also builds a system that provides an optimal long-term plan based on the user's values ​​and lifestyle. For example, a plan that emphasizes family events is proposed for a family-oriented user. The plan generation unit also provides a long-term plan that reflects the user's lifestyle and values. For example, an environmentally friendly plan is proposed for an eco-conscious user. In this way, a long-term plan that reflects the user's lifestyle and values ​​can be provided.

[0091] The plan generation unit can use the emotion estimation function to provide advice to help the user maintain motivation toward long-term goals. For example, the plan generation unit uses the emotion estimation function to analyze the user's motivation toward long-term goals in real time and provide advice based on the results. For example, the plan generation unit displays a message such as "Great progress, keep it up." The plan generation unit also builds a system that provides advice to help the user maintain motivation toward long-term goals. For example, based on the emotion estimation data, it displays an encouraging message when the user is losing motivation. The plan generation unit also uses the emotion estimation function to provide specific advice to help the user maintain motivation toward long-term goals. For example, it suggests a way to accumulate small successes toward goal achievement. This makes it possible to provide advice to help the user maintain motivation toward long-term goals.

[0092] The plan generation unit can provide a long-term plan according to the user's health condition and life stage. The plan generation unit provides, for example, a long-term plan that takes into account the user's health condition (e.g., whether or not the user has a chronic illness, health checkup results). For example, it proposes a savings plan that takes into account expenses for maintaining health. The plan generation unit also builds a system that provides long-term plans according to the user's life stage (e.g., marriage, childbirth, retirement). For example, it estimates expenses and income for each life stage and proposes a plan based on that. The plan generation unit also provides an optimal long-term plan based on the user's health condition and life stage. For example, it proposes an estimated medical expense according to the user's health condition and an expenditure plan according to the user's life stage. This makes it possible to provide a long-term plan according to the user's health condition and life stage.

[0093] The plan generation unit can automatically suggest insurance or financial products related to a long-term plan. The plan generation unit, for example, builds a system that automatically suggests insurance (e.g., life insurance, medical insurance) or financial products (e.g., pensions, investment trusts) related to a long-term plan. For example, it automatically searches for and suggests insurance or financial products that meet a user's conditions. The plan generation unit also develops a system that automatically suggests insurance or financial products related to a long-term plan. For example, it automatically searches for insurance or financial products that meet a user's conditions and supports application procedures. The plan generation unit also builds a system that automatically suggests insurance or financial products related to a long-term plan. For example, it provides a comparison result of multiple insurance or financial products and suggests the optimal option. This makes it possible to automatically suggest insurance or financial products related to a long-term plan.

[0094] The plan generation unit can use the emotion estimation function to analyze the user's emotions regarding long-term goals and propose an optimal plan. For example, the plan generation unit can use the emotion estimation function to analyze the user's emotions regarding long-term goals in real time and propose an optimal plan based on the results. For example, if the user is feeling anxious, a message to help the user relax is displayed. The plan generation unit can also analyze the user's emotions regarding long-term goals and build a system that provides an optimal plan based on the results. For example, a plan that makes the user feel at ease is proposed based on the emotion data. The plan generation unit can also use the emotion estimation function to analyze the user's emotions regarding long-term goals and provide specific advice based on the results. For example, if the user is feeling anxious, information about investment strategies and savings plans is provided. In this way, the user's emotions regarding long-term goals can be analyzed and an optimal plan can be proposed.

[0095] The plan correction unit can use the generation AI to provide real-time plan corrections in response to changes in the user's situation. For example, the plan correction unit uses the generation AI to analyze fluctuations in the user's income and expenses in real time and revise the plan based on the results. For example, if income increases, the plan correction unit suggests increasing savings. The plan correction unit also builds a system that provides real-time plan corrections in response to changes in the user's situation (for example, changes in family composition or health condition). For example, if the number of family members increases, the plan correction unit suggests reviewing education expenses. The plan correction unit also uses the generation AI to provide real-time plan corrections in response to changes in the user's situation. For example, if the user's health condition worsens, the plan correction unit revise the estimated medical expenses. This makes it possible to provide real-time plan corrections in response to changes in the user's situation.

[0096] The plan correction unit can provide plan corrections that reflect changes in the user's lifestyle and values. The plan correction unit, for example, provides plan corrections that reflect changes in the user's lifestyle (e.g., health-consciousness, eco-consciousness). For example, if the user becomes more health-conscious, a suggestion is made to increase health-related spending. The plan correction unit also constructs a system that provides plan corrections that reflect changes in the user's values ​​(e.g., family-focused, career-focused). For example, if the user becomes more career-focused, a suggestion is made to increase spending for career advancement. The plan correction unit also provides plan corrections that reflect changes in the user's lifestyle and values. For example, if the user becomes more eco-conscious, a suggestion is made to increase environmentally friendly spending. In this way, it is possible to provide plan corrections that reflect changes in the user's lifestyle and values.

[0097] The plan correction unit can use the emotion estimation function to provide advice to reduce the user's anxiety about a change in situation. For example, the plan correction unit uses the emotion estimation function to analyze the user's anxiety about a change in situation in real time and provide advice based on the results. For example, the plan correction unit displays a message such as "It's okay, there will be no problem if you proceed as planned." The plan correction unit also builds a system that provides advice to reduce the user's anxiety about a change in situation. For example, based on the emotion estimation data, a message to help the user relax is displayed when the user is feeling anxious. The plan correction unit also uses the emotion estimation function to provide specific advice to reduce the user's anxiety about a change in situation. For example, it suggests ways to review expenses if income has decreased. This makes it possible to provide advice to reduce the user's anxiety about a change in situation.

[0098] The plan correction unit can provide plan corrections in accordance with changes in the user's health condition or life stage. The plan correction unit, for example, provides plan corrections that reflect changes in the user's health condition (e.g., whether or not the user has a chronic illness, health checkup results). For example, if the user's health condition worsens, the plan correction unit corrects the estimated medical expenses. The plan correction unit also builds a system that provides plan corrections in accordance with changes in the user's life stage (e.g., marriage, childbirth, retirement). For example, it estimates expenses and income for each life stage and proposes a plan based on that. The plan correction unit also provides optimal plan corrections based on changes in the user's health condition or life stage. For example, it proposes estimated medical expenses according to the user's health condition and a spending plan according to the life stage. This makes it possible to provide plan corrections in accordance with changes in the user's health condition or life stage.

[0099] The plan adjustment unit can automatically suggest insurance or financial products related to the plan adjustment. The plan adjustment unit, for example, builds a system that automatically suggests insurance (e.g., life insurance, medical insurance) or financial products (e.g., pensions, investment trusts) related to the plan adjustment. For example, it automatically searches for and suggests insurance or financial products that meet the user's conditions. The plan adjustment unit also develops a system that automatically suggests insurance or financial products related to the plan adjustment. For example, it automatically searches for insurance or financial products that meet the user's conditions and supports the application procedure. The plan adjustment unit also builds a system that automatically suggests insurance or financial products related to the plan adjustment. For example, it provides a comparison result of multiple insurance or financial products and suggests the optimal option. This makes it possible to automatically suggest insurance or financial products related to the plan adjustment.

[0100] The plan correction unit can use the emotion estimation function to analyze the user's emotions in response to a change in situation and propose an optimal plan correction. The plan correction unit, for example, uses the emotion estimation function to analyze the user's emotions in response to a change in situation in real time and propose an optimal plan correction based on the results. For example, if the user is feeling anxious, it displays a message to help the user relax. The plan correction unit also analyzes the user's emotions in response to a change in situation and builds a system that provides an optimal plan correction based on the results. For example, it proposes a plan that makes the user feel at ease based on the emotion data. The plan correction unit also uses the emotion estimation function to analyze the user's emotions in response to a change in situation and provides specific advice based on the results. For example, if the user is feeling anxious, it suggests a way to review expenses if income has decreased. In this way, it is possible to analyze the user's emotions in response to a change in situation and propose an optimal plan correction.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The setting information acquisition unit can also acquire information about the user's health condition. For example, if the user has a chronic illness, by inputting that information, a plan that takes health-related expenses into consideration can be provided. The setting information acquisition unit can also estimate future medical expenses by inputting the user's health checkup results. Furthermore, it can also propose a spending plan for maintaining health based on the user's health condition. This makes it possible to provide the user with an optimal financial plan tailored to their health condition.

[0103] The plan generation unit can also provide plans based on the user's hobbies and interests. For example, a savings plan that takes travel expenses into account is proposed for a user who enjoys traveling. Also, a plan that takes sports-related expenses into account is proposed for a user who enjoys sports. Furthermore, the plan generation unit can also propose savings plans for future life events based on the user's hobbies and interests. This makes it possible to provide a personalized plan that matches the user's hobbies and interests.

[0104] The plan generation unit can also provide a plan based on the user's values. For example, it can suggest eco-friendly investments to a user who is interested in environmental protection. It can also provide a plan that takes socially responsible investment (SRI) into consideration to a user who places importance on contributing to society. Furthermore, the plan generation unit can also suggest savings plans for future life events based on the user's values. This makes it possible to provide a personalized plan that matches the user's values.

[0105] The plan generation unit can use the emotion estimation function to analyze the emotions of the user when they enter text in real time and provide positive feedback. For example, it can analyze the user's facial expressions and voice when they enter text and display an encouraging message if they are feeling positive emotions. For example, it can display a message such as "Great, keep it up." The plan generation unit also uses the emotion estimation function to monitor the user's emotional state when they enter text in real time and provide an interface for eliciting positive emotions. For example, it can display success stories and positive feedback. The plan generation unit also provides feedback in real time based on the emotion estimation data when the user enters text and provides advice to strengthen positive emotions. For example, it can display appropriate encouragement or praise according to the content of the input. This makes it possible to analyze the emotions of the user when they enter text in real time and provide positive feedback.

[0106] The setting information acquisition unit can analyze the user's voice input and use the emotion estimation function to provide an interface that reduces the stress or anxiety the user feels when entering information. For example, when the user is entering basic information by voice, the emotion estimation function can be used to display a message to help the user relax if the user feels stressed or anxious. For example, a message such as "It's okay, please proceed slowly" can be displayed. The setting information acquisition unit can also monitor the user's emotional state during voice input in real time and change the interface design if the user feels stressed. For example, the color or font can be changed to enhance the relaxation effect. The setting information acquisition unit can also provide appropriate advice and support based on the emotion estimation data during voice input. For example, if the user finds input difficult, the system can prompt the user to enter information by breaking it down into simple questions. This makes it possible to provide an interface that reduces the stress and anxiety the user feels when entering information by voice.

[0107] The setting information acquisition unit can automatically acquire the user's past financial behavior data and provide it to the plan generation unit. For example, the setting information acquisition unit can automatically acquire the user's bank transaction history and credit card usage history to understand spending patterns and savings tendencies. The setting information acquisition unit also links with the user's investment account to automatically acquire the user's past investment history and risk tolerance. Furthermore, the setting information acquisition unit can automatically acquire the user's past income fluctuations and spending tendencies to create future income forecasts and spending plans. By automatically acquiring the user's past financial behavior data and providing it to the plan generation unit, a more accurate plan can be provided.

[0108] The plan generation unit can use the emotion estimation function to analyze the emotions of the user when they enter text in real time and provide positive feedback. For example, it can analyze the user's facial expressions and voice when they enter text and display an encouraging message if they are feeling positive emotions. For example, it can display a message such as "Great, keep it up." The plan generation unit also uses the emotion estimation function to monitor the user's emotional state when they enter text in real time and provide an interface for eliciting positive emotions. For example, it can display success stories and positive feedback. The plan generation unit also provides feedback in real time based on the emotion estimation data when the user enters text and provides advice to strengthen positive emotions. For example, it can display appropriate encouragement or praise according to the content of the input. This makes it possible to analyze the emotions of the user when they enter text in real time and provide positive feedback.

[0109] The plan generation unit can use generation AI to predict fluctuations in education costs by region and propose an optimal savings plan. For example, generation AI can be used to analyze past data on education costs by region and predict future cost fluctuations. For example, a savings plan can be proposed that takes into account differences in education costs between urban and rural areas. The plan generation unit can also predict fluctuations in education costs by region and build a system that proposes an optimal savings plan based on that prediction. For example, in regions where education costs are rising, it can advise users to start saving early. The plan generation unit can also use generation AI to predict future education costs by region and provide users with an optimal savings plan. For example, in regions where education costs are stable, it can propose a savings plan with reduced risk. This makes it possible to predict fluctuations in education costs by region and propose an optimal savings plan.

[0110] The plan generation unit can provide an educational plan that takes into account the academic performance and interests of the user's child. For example, by inputting the user's child's academic performance and interests, an educational plan based on that can be provided. For example, for a child interested in science, a plan aimed at entering a science university can be proposed. The plan generation unit also builds a system that generates an optimal educational plan taking into account the child's academic performance and interests. For example, for a child interested in a particular field, an educational plan specialized for that field can be provided. The plan generation unit also proposes an educational plan that takes into account the user's child's future path and career based on the user's child's academic performance and interests. For example, for a child interested in music, a plan aimed at entering a music university can be proposed. In this way, an educational plan that takes into account the user's child's academic performance and interests can be provided.

[0111] The plan generation unit can use the emotion estimation function to provide advice to reduce parents' anxiety about education costs. For example, the emotion estimation function can be used to analyze parents' anxiety about education costs in real time and provide advice based on the results. For example, a message such as "Don't worry, there will be no problem if you proceed as planned" can be displayed. The plan generation unit also builds a system that provides advice to reduce parents' anxiety about education costs. For example, based on the emotion estimation data, a message to relax parents who are feeling anxious can be displayed. The plan generation unit can also use the emotion estimation function to provide specific advice to reduce parents' anxiety about education costs. For example, it can suggest ways to use scholarships or educational loans. This makes it possible to provide advice to reduce parents' anxiety about education costs.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The setting information acquisition unit acquires basic setting information of the user. For example, the setting information acquisition unit collects this information by inputting information such as age, income, and family composition. Step 2: The plan generation unit generates plans related to education, home purchases, and life events based on the setting information acquired by the setting information acquisition unit. For example, if the user inputs "I want to plan my child's education expenses," the plan generation unit will use that information to estimate education expenses and propose savings plans. Step 3: The plan modification unit modifies the plan generated by the plan generation unit according to the user's current situation and goals. For example, if the user's income increases or their family structure changes, the plan modification unit reevaluates the plan and provides an optimal plan.

[0114] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0120] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0124] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0125] 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.

[0126] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0133] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0135] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0139] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] 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.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0142] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0148] 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.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0154] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0155] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] 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.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0158] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0160] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0161] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0162] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0164] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0165] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0166] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0167] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0168] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0169] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0170] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0171] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0172] 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.

[0173] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0174] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0175] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific process may be a single processor.

[0176] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0177] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0178] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0179] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0180] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0181] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a setting information acquisition unit that acquires basic setting information of a user; a plan generation unit that generates plans related to education, home purchase, and life events based on the setting information acquired by the setting information acquisition unit; a plan modification unit that modifies the plan generated by the plan generation unit in accordance with the user's current situation and goals. A system characterized by:

2. The plan generation unit Using generative AI, the user's past financial behavior data is analyzed to provide a more accurate plan.

2. The system of claim 1.

3. The plan generation unit Add questions that reflect the user's lifestyle and values ​​to generate a personalized plan.

2. The system of claim 1.

4. The plan generation unit To provide an interface for reducing stress or anxiety felt by the user when inputting data 2. The system of claim 1.

5. The setting information acquisition unit The user can provide the setting information by voice input, thereby improving convenience.

2. The system of claim 1.

Images