system

Abstract

The system according to this embodiment aims to alleviate the financial and lifestyle anxieties of the elderly. [Solution] The system according to the embodiment comprises a pension management unit, a long-term care cost planning unit, a part-time job referral unit, a housing referral unit, and a utility cost review unit. The pension management unit collects pension information. The long-term care cost planning unit predicts future long-term care costs based on the information collected by the pension management unit. The part-time job referral unit refers to part-time jobs based on the information predicted by the long-term care cost planning unit. The housing referral unit proposes housing based on the information referred by the part-time job referral unit. The utility cost review unit reviews utility costs based on the information proposed by the housing referral unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a lack of comprehensive support for reducing the economic and life-related anxieties of the elderly, and there is room for improvement.

[0005] The system according to the embodiment aims to reduce the economic and life-related anxieties of the elderly.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a pension management unit, a long-term care cost planning unit, a part-time job referral unit, a housing referral unit, and a utility cost review unit. The pension management unit collects pension information. The long-term care cost planning unit predicts future long-term care costs based on the information collected by the pension management unit. The part-time job referral unit refers to part-time jobs based on the information predicted by the long-term care cost planning unit. The housing referral unit proposes housing based on the information referred by the part-time job referral unit. The utility cost review unit reviews utility costs based on the information proposed by the housing referral unit. [Effects of the Invention]

[0007] The system according to this embodiment can alleviate the financial and lifestyle anxieties of the elderly. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The generative AI concierge service according to an embodiment of the present invention is a system designed to alleviate and protect elderly people from financial and lifestyle anxieties. This generative AI concierge service is also designed to allow isolated and lonely elderly people to enjoy communication. Specifically, it provides the following functions: First, as pension management, the generative AI manages pensions and other income and suggests the optimal way to use them. Next, as long-term care cost planning, the generative AI predicts future long-term care costs and supports appropriate preparation. Furthermore, as part-time job introductions, the generative AI evaluates the skills and available time of individual elderly people and suggests ways to effectively utilize their spare time. As housing introductions, the generative AI suggests housing that meets the needs of elderly people. Finally, as a review of utility costs, the generative AI reviews fixed costs such as utilities and suggests ways to save money. This service aims to solve the problem that elderly people tend to be unfamiliar with the latest trends and technologies, and to protect them in a comprehensive way. The generative AI agent supports the lives of elderly people and provides an environment in which they can live with peace of mind. In this way, the generative AI concierge service can alleviate financial and lifestyle anxieties of elderly people and provide an environment in which they can live with peace of mind.

[0029] The AI-generated concierge service according to this embodiment comprises a pension management unit, a long-term care cost planning unit, a part-time job referral unit, a housing referral unit, and a utility cost review unit. The pension management unit collects pension information. Pension information includes, but is not limited to, public pensions, corporate pensions, and private pensions. The pension management unit obtains pension information from online systems, for example. The pension management unit can also manually input pension information. Furthermore, the pension management unit can periodically update pension information. For example, the pension management unit updates pension information monthly to maintain the latest information. The long-term care cost planning unit predicts future long-term care costs based on the information collected by the pension management unit. The long-term care cost planning unit predicts long-term care costs using, for example, historical data and statistical models. The long-term care cost planning unit can also predict long-term care costs considering the user's health status and living situation. For example, the long-term care cost planning unit predicts long-term care costs based on the user's health checkup data. The part-time job referral unit introduces part-time jobs based on the information predicted by the long-term care cost planning unit. The Part-Time Job Introduction Department introduces part-time jobs such as short-term part-time work and remote work. It can also introduce part-time jobs based on the user's skills and available time. For example, it might introduce part-time jobs based on the user's work history and qualifications. The Housing Introduction Department proposes housing based on the information introduced by the Part-Time Job Introduction Department. This department proposes housing options such as rental properties, shared housing, and nursing homes. It can also propose housing tailored to the user's needs, such as considering the user's health and lifestyle. The Utility Cost Review Department reviews utility costs based on the information proposed by the Housing Introduction Department. This department reviews fixed costs such as electricity, gas, and water bills. It can also propose ways to save money, such as suggesting the use of energy-efficient appliances or changing contract plans. As a result, the generated AI concierge service according to this embodiment can alleviate the financial and lifestyle anxieties of the elderly and provide an environment where they can live with peace of mind.

[0030] The Pension Management Department collects pension information. This information includes, but is not limited to, public pensions, corporate pensions, and private pensions. The Pension Management Department obtains pension information from online systems, for example. Specifically, it accesses government pension management systems and corporate pension portal sites and automatically retrieves the necessary data via APIs. The Pension Management Department can also manually enter pension information. For example, if a user provides pension information on paper documents, it provides an interface for manually entering that information into the database. Furthermore, the Pension Management Department can periodically update pension information. For example, it updates pension information monthly to maintain the latest information. This includes mechanisms for collecting the latest pension information through regular API calls and reminder notifications to users. The Pension Management Department also implements security measures to securely store the collected data and share it with other departments as needed. For example, the data is encrypted and access permissions are strictly controlled. This allows the Pension Management Department to efficiently and securely manage users' pension information and enable other departments to quickly access the information they need.

[0031] The Long-Term Care Cost Planning Department predicts future long-term care costs based on information collected by the Pension Management Department. For example, the Department uses historical data and statistical models to predict costs. Specifically, it analyzes past long-term care cost data and uses statistical regression models and machine learning algorithms to predict future costs. The Department can also predict long-term care costs considering the user's health status and living situation. For example, it predicts costs based on the user's health checkup data. This data includes health indicators such as blood pressure, blood sugar levels, and cholesterol levels, and is used to assess future long-term care risks. Furthermore, the Department also considers information such as the user's lifestyle, family structure, and living environment. For example, the necessary long-term care services and costs differ between elderly individuals living alone and those living with family, so the Department develops individually optimized long-term care cost plans considering these factors. The Department comprehensively analyzes this information to provide users with specific long-term care cost estimates and predictions of future cost fluctuations. This makes it easier for users to prepare for future long-term care costs and reduces financial anxiety.

[0032] The Part-Time Job Introduction Department introduces part-time jobs based on information predicted by the Care Cost Planning Department. For example, it introduces part-time jobs such as short-term work and remote work. Specifically, the Part-Time Job Introduction Department collects job information from online job platforms and companies, providing job information that matches the user's needs. The Part-Time Job Introduction Department can also introduce part-time jobs by evaluating the user's skills and available time. For example, it introduces part-time jobs based on the user's work history and qualifications. It registers the user's skills and experience in a database and uses an algorithm to match them with the most suitable job. Furthermore, the Part-Time Job Introduction Department considers the user's lifestyle and health condition to suggest part-time jobs that can be done within a reasonable range. For example, it suggests flexible working styles that suit the user's situation, such as part-time jobs that only require a few hours a week or remote work that can be done from home. The Part-Time Job Introduction Department comprehensively analyzes this information and provides users with specific job information and support for application procedures. This makes it easier for users to secure a source of income to supplement part of their care costs, thus achieving financial stability.

[0033] The Housing Introduction Department proposes housing based on information introduced by the Part-Time Job Introduction Department. The Housing Introduction Department proposes various types of housing, such as rentals, shared houses, and nursing homes. Specifically, it collects information from real estate databases and nursing home databases to propose housing that meets the user's needs. Furthermore, the Housing Introduction Department can also propose housing tailored to the user's needs. For example, it considers the user's health condition and lifestyle when proposing housing. It selects the optimal housing considering the level of care services the user requires and the convenience of daily life. In addition, the Housing Introduction Department provides multiple options considering the user's budget, desired area, and living environment. For example, it proposes a variety of housing options to suit the user's preferences, such as rental apartments in urban areas, shared houses in the suburbs, and facilities with comprehensive care services. The Housing Introduction Department comprehensively analyzes this information and provides users with specific housing proposals, arrangements for viewings, and support for contract procedures. This makes it easier for users to find the ideal housing and live with peace of mind.

[0034] The Utility Cost Review Department reviews utility costs based on information proposed by the Housing Introduction Department. The Utility Cost Review Department reviews fixed costs such as electricity, gas, and water bills. Specifically, it analyzes the user's current utility spending and assesses whether there is room for savings. The Utility Cost Review Department can also propose savings methods. For example, it suggests using energy-efficient appliances or changing contract plans. It evaluates the energy efficiency of the electrical appliances the user is using and recommends replacing them with more efficient ones. It also compares contract plans from electricity and gas companies and proposes switching to cheaper plans. Furthermore, the Utility Cost Review Department provides savings advice tailored to the user's lifestyle. For example, it suggests specific savings methods such as reviewing electricity usage times to avoid peak rates or installing water-saving showerheads. The Utility Cost Review Department comprehensively analyzes this information and provides users with specific savings plans and implementation procedures. This allows users to effectively reduce utility costs and alleviate their financial burden.

[0035] The pension management department can use generative AI to manage pensions and other income and suggest optimal ways to use them. For example, the pension management department can use generative AI to analyze pension information and suggest optimal usage. The pension management department can also use generative AI to predict income fluctuations and provide future income forecasts. For example, the pension management department can use generative AI to predict future income based on past income data. Furthermore, the pension management department can use generative AI to provide investment and savings advice. For example, the pension management department can use generative AI to suggest optimal investment destinations and savings methods. This enables optimal management of pensions and income. Generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the pension management department are performed using generative AI. For example, the pension management department inputs pension information into the generative AI, and the generative AI suggests optimal usage.

[0036] The Care Cost Planning Department can use generative AI to predict future care costs and support appropriate preparation. For example, the Care Cost Planning Department can use generative AI to predict care costs using historical data and statistical models. The Care Cost Planning Department can also use generative AI to predict care costs while considering the user's health status and living situation. For example, the Care Cost Planning Department can use generative AI to predict care costs based on health checkup data. Furthermore, the Care Cost Planning Department can use generative AI to provide advice on insurance enrollment and savings plans. For example, the Care Cost Planning Department can use generative AI to propose the optimal insurance plan and savings method. This makes it possible to predict and prepare for future care costs. Generative AI is implemented using, for example, machine learning models and deep learning. Some or all of the above processes in the Care Cost Planning Department are performed using generative AI. For example, the Care Cost Planning Department inputs care cost predictions into the generative AI, and the generative AI supports appropriate preparation.

[0037] The Part-Time Job Introduction Service uses generative AI to evaluate the skills and available time of individual seniors and propose ways to effectively utilize their spare time. For example, the generative AI can analyze a user's work history and qualifications to propose the most suitable part-time jobs. The part-time job introduction service can also evaluate a user's available time and propose appropriate jobs. For example, the generative AI can propose jobs based on the user's schedule. Furthermore, the generative AI can also provide remote work and short-term job options. For example, the generative AI can suggest remote work job postings. This allows seniors to effectively utilize their skills and time. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the part-time job introduction service are performed using the generative AI. For example, the part-time job introduction service inputs the user's skill information into the generative AI, which then proposes the most suitable jobs.

[0038] The housing referral service can use generative AI to propose housing options tailored to the needs of the elderly. For example, the generative AI can analyze a user's health condition and lifestyle to propose the most suitable housing. The housing referral service can also use generative AI to assess a user's financial situation and propose appropriate housing. For example, the generative AI can propose housing based on the user's income and expenses. Furthermore, the generative AI can provide options such as nursing homes and shared housing. For example, the generative AI can suggest information on nursing homes. This makes it possible to propose housing that meets the needs of the elderly. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the housing referral service are performed using generative AI. For example, the housing referral service inputs user needs information into the generative AI, which then proposes the most suitable housing.

[0039] The utility cost review department can use generating AI to review fixed costs such as utility bills and propose ways to save money. For example, the generating AI in the utility cost review department can analyze fixed costs such as electricity, gas, and water bills and propose the optimal way to save money. The utility cost review department can also have the generating AI suggest the use of energy-efficient equipment or changes to contract plans. For example, the generating AI in the utility cost review department can suggest energy-efficient home appliances. Furthermore, the generating AI in the utility cost review department can evaluate the user's lifestyle and propose appropriate ways to save money. For example, the generating AI in the utility cost review department can propose saving methods based on the user's usage patterns. This makes it possible to review and save on fixed costs such as utility bills. The generating AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processing in the utility cost review department is performed using the generating AI. For example, the utility cost review department inputs fixed cost information into the generating AI, and the generating AI proposes the optimal way to save money.

[0040] The pension management department can select the optimal management method by referring to the user's past income history when managing pensions. For example, the pension management department can analyze the user's past income history and propose the most efficient pension management method. The pension management department can also provide a stable pension management method by considering fluctuations in the user's income. For example, the pension management department can predict future income based on the user's past income data and adjust the pension management method accordingly. Furthermore, the pension management department can provide a forecast of future income based on the user's past income history. For example, the pension management department can use a generative AI to predict future income based on past income data. This enables optimal pension management based on past income history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the pension management department are performed using the generative AI. For example, the pension management department inputs past income data into the generative AI, and the generative AI selects the optimal management method.

[0041] The pension management department can customize how users use their pensions based on their current living situation. For example, the pension management department can propose the optimal way to use the pension, taking into account the user's current living expenses. It can also propose a pension usage plan that includes medical and long-term care expenses, taking into account the user's health condition. For example, the pension management department can customize the pension usage plan based on the user's health checkup data. Furthermore, the pension management department can also customize the pension usage plan by considering the user's family structure and living environment. For example, the pension management department can propose a pension usage plan based on the user's family structure and living environment. This ensures that the pension usage plan is tailored to the user's current living situation. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the pension management department are performed using the generation AI. For example, the pension management department inputs current living situation data into the generation AI, which then customizes the pension usage plan.

[0042] The pension management department can select the optimal pension management method when managing pensions, taking into account the user's geographical location information. For example, the pension management department can propose the optimal pension management method by considering the cost of living in the user's area. Furthermore, the pension management department can adjust how pensions are used by considering the availability of medical and nursing care facilities in the user's area. For example, the pension management department can select a pension management method based on information about medical facilities in the user's area. In addition, the pension management department can customize the pension management method by considering the cost of living and living environment in the user's area. For example, the pension management department can propose a pension management method based on price data in the user's area. This enables optimal pension management based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the pension management department are performed using the generation AI. For example, the pension management department inputs geographical location information into the generation AI, which then selects the optimal pension management method.

[0043] The pension management department can analyze users' social media activity during pension management to provide pension management advice. For example, the pension management department can analyze users' lifestyles and hobbies from their social media activity and propose how to use their pensions based on that analysis. The pension management department can also provide pension management advice considering users' social media interactions. For example, the pension management department can adjust pension management methods based on users' social media activity. Furthermore, the pension management department can predict future expenditures from users' social media activity and adjust pension management methods based on those predictions. For example, the pension management department can use a generative AI to analyze social media data and provide pension management advice. This provides pension management advice based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the pension management department are performed using the generative AI. For example, the pension management department inputs social media data into the generative AI, and the generative AI provides pension management advice.

[0044] The care cost planning unit can select the optimal planning method by referring to the user's past medical history when planning care costs. For example, the care cost planning unit can analyze the user's past medical history and propose the most efficient care cost planning method. The care cost planning unit can also provide a stable care cost planning method by considering fluctuations in the user's medical history. For example, the care cost planning unit can predict future medical expenses based on the user's past medical data and adjust the care cost planning method accordingly. Furthermore, the care cost planning unit can provide a forecast of future medical expenses based on the user's past medical history. For example, the care cost planning unit can use a generative AI to predict future medical expenses based on past medical data. This enables optimal care cost planning based on past medical history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the care cost planning unit are performed using the generative AI. For example, the care cost planning unit inputs past medical data into the generative AI, and the generative AI selects the optimal planning method.

[0045] The care cost planning unit can customize the prediction of care costs based on the user's current health status when planning care costs. For example, the care cost planning unit proposes an optimal care cost plan considering the user's current health status. The care cost planning unit can also provide a stable care cost planning method that takes into account fluctuations in the user's health status. For example, the care cost planning unit predicts future care costs based on the user's health check data and adjusts the care cost planning method accordingly. Furthermore, the care cost planning unit can also provide an outlook on future care costs based on the user's current health status. For example, the care cost planning unit uses a generative AI to predict future care costs based on current health data. This provides a prediction of care costs that is appropriate to the current health status. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the care cost planning unit are performed using the generative AI. For example, the care cost planning unit inputs current health data into the generative AI, and the generative AI customizes the prediction of care costs.

[0046] The care cost planning unit can select the optimal care cost planning method when planning care costs, taking into account the user's geographical location information. For example, the care cost planning unit proposes the optimal care cost planning method by considering the medical costs in the user's area. The care cost planning unit can also provide advice on care cost planning by considering the situation of care facilities in the user's area. For example, the care cost planning unit selects a care cost planning method based on information about care facilities in the user's area. Furthermore, the care cost planning unit can customize the care cost planning method by considering the cost of living and living environment in the user's area. For example, the care cost planning unit proposes a care cost planning method based on the cost of living data in the user's area. This enables optimal care cost planning based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the care cost planning unit are performed using the generation AI. For example, the care cost planning unit inputs geographical location information into the generation AI, and the generation AI selects the optimal care cost planning method.

[0047] The care cost planning department can analyze a user's social media activity and provide advice on care cost planning. For example, the department can analyze a user's lifestyle and hobbies from their social media activity and propose a care cost plan based on that. The care cost planning department can also provide advice on care cost planning by considering the user's social media interactions. For example, the department can adjust the care cost planning method based on the user's social media activity. Furthermore, the care cost planning department can predict future expenditures from the user's social media activity and adjust the care cost planning method based on that. For example, the care cost planning department can use a generative AI to analyze social media data and provide advice on care cost planning. This provides advice on care cost planning based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the care cost planning department are performed using the generative AI. For example, the care cost planning department inputs social media data into the generative AI, and the generative AI provides advice on care cost planning.

[0048] The part-time job referral service can select the most suitable part-time job by referring to the user's past work history when referring part-time jobs. For example, the part-time job referral service analyzes the user's past work history and proposes the most suitable part-time job. The part-time job referral service can also provide stable part-time jobs by taking into account fluctuations in the user's work history. For example, the part-time job referral service predicts future occupations based on the user's past work history data and selects part-time jobs based on that. Furthermore, the part-time job referral service can also provide future occupation prospects based on the user's past work history. For example, the part-time job referral service uses a generative AI to predict future occupations based on past work history data. This makes it possible to refer the most suitable part-time job based on past work history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the part-time job referral service are performed using the generative AI. For example, the part-time job referral service inputs past work history data into the generative AI, and the generative AI selects the most suitable part-time job.

[0049] The part-time job referral service can customize job suggestions based on the user's current skills when referring part-time jobs. For example, the part-time job referral service can suggest the most suitable part-time job considering the user's current skills. Furthermore, the part-time job referral service can provide stable part-time jobs by considering fluctuations in the user's skills. For example, the part-time job referral service can predict future skills based on the user's current skill data and select part-time jobs accordingly. In addition, the part-time job referral service can provide an outlook on future skills based on the user's current skills. For example, the part-time job referral service uses a generative AI to predict future skills based on current skill data. This allows for the provision of part-time job suggestions that match the user's current skills. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-described processes in the part-time job referral service are performed using the generative AI. For example, the part-time job referral service inputs current skill data into the generative AI, which then customizes the job suggestions.

[0050] The part-time job referral service can select the most suitable part-time job by considering the user's geographical location when referring part-time jobs. For example, the part-time job referral service can suggest the most suitable part-time job by considering job information in the user's area. It can also provide part-time jobs that are easy to commute to by considering the transportation situation in the user's area. For example, the part-time job referral service can select part-time jobs based on the transportation data of the user's area. Furthermore, the part-time job referral service can customize part-time jobs by considering the cost of living and living environment in the user's area. For example, the part-time job referral service can suggest part-time jobs based on the cost of living data of the user's area. This makes it possible to refer the most suitable part-time jobs based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the part-time job referral service are performed using the generation AI. For example, the part-time job referral service inputs geographical location information into the generation AI, and the generation AI selects the most suitable part-time job.

[0051] The part-time job referral service can analyze a user's social media activity to suggest part-time jobs. For example, it can analyze a user's interests and preferences from their social media activity and suggest part-time jobs based on that. It can also provide suitable part-time jobs by considering the user's social media interactions. For example, it can select part-time jobs based on the user's social media activity. Furthermore, it can predict future occupations from the user's social media activity and select part-time jobs based on that prediction. For example, the part-time job referral service uses a generative AI to analyze social media data and provide part-time job suggestions. This provides part-time job suggestions based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the part-time job referral service are performed using the generative AI. For example, the part-time job referral service inputs social media data into the generative AI, and the generative AI provides part-time job suggestions.

[0052] The housing introduction service can select the most suitable housing by referring to the user's past housing history during the housing introduction process. For example, the housing introduction service can analyze the user's past housing history and propose the most suitable housing. The housing introduction service can also provide stable housing by considering fluctuations in the user's housing history. For example, the housing introduction service can predict future housing needs based on the user's past housing data and select housing based on that prediction. Furthermore, the housing introduction service can provide future housing outlooks based on the user's past housing history. For example, the housing introduction service uses a generative AI to predict future housing needs based on past housing data. This makes it possible to propose the most suitable housing based on past housing history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction service are performed using the generative AI. For example, the housing introduction service inputs past housing data into the generative AI, and the generative AI selects the most suitable housing.

[0053] The housing introduction department can customize housing suggestions based on the user's current living situation. For example, it can suggest the most suitable housing considering the user's current living expenses. It can also suggest housing close to medical or nursing facilities considering the user's health condition. For example, it can customize housing suggestions based on the user's health check data. Furthermore, it can customize housing suggestions considering the user's family structure and living environment. For example, it can suggest housing based on the user's family structure and living environment. This provides housing suggestions that are tailored to the user's current living situation. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction department are performed using the generative AI. For example, the housing introduction department inputs current living situation data into the generative AI, and the generative AI customizes the housing suggestions.

[0054] The housing introduction department can select the most suitable housing by considering the user's geographical location information when introducing housing. For example, the housing introduction department can propose the most suitable housing by considering the cost of living in the user's area. It can also propose housing by considering the status of medical and nursing care facilities in the user's area. For example, the housing introduction department can select housing based on information about medical facilities in the user's area. Furthermore, the housing introduction department can customize housing proposals by considering the cost of living and living environment in the user's area. For example, the housing introduction department can propose housing based on the cost of living data in the user's area. This makes it possible to propose the most suitable housing based on geographical location information. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction department are performed using the generative AI. For example, the housing introduction department inputs geographical location information into the generative AI, and the generative AI selects the most suitable housing.

[0055] The housing introduction department can analyze a user's social media activity to provide housing suggestions when introducing housing options. For example, the housing introduction department can analyze a user's lifestyle and hobbies from their social media activity and propose housing options based on that. The housing introduction department can also provide suitable housing options by considering the user's social media interactions. For example, the housing introduction department can select housing options based on the user's social media activity. Furthermore, the housing introduction department can predict future housing needs based on the user's social media activity and select housing options based on that prediction. For example, the housing introduction department uses generative AI to analyze social media data and provide housing suggestions. This provides housing suggestions based on social media activity. Generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction department are performed using generative AI. For example, the housing introduction department inputs social media data into the generative AI, and the generative AI provides housing suggestions.

[0056] The utility cost review unit can select the optimal review method when reviewing utility costs by referring to the user's past utility cost history. For example, the utility cost review unit can analyze the user's past utility cost history and propose the most efficient utility cost review method. The utility cost review unit can also provide a stable utility cost review method by considering fluctuations in the user's utility costs. For example, the utility cost review unit can predict future utility costs based on the user's past utility cost data and adjust the utility cost review method accordingly. Furthermore, the utility cost review unit can also provide a forecast of future utility costs based on the user's past utility cost history. For example, the utility cost review unit can use a generating AI to predict future utility costs based on past utility cost data. This enables optimal utility cost review based on past utility cost history. The generating AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-described processes in the utility cost review unit are performed using the generating AI. For example, the utility cost review department inputs past utility cost data into a generating AI, which then selects the optimal review method.

[0057] The utility cost review unit can customize the review of utility costs based on the user's current living situation. For example, the utility cost review unit can propose the optimal utility cost review method considering the user's current living expenses. The utility cost review unit can also propose a utility cost review method that includes medical and nursing care costs, taking into account the user's health condition. For example, the utility cost review unit can customize the utility cost review method based on the user's health checkup data. Furthermore, the utility cost review unit can also customize the utility cost review method considering the user's family structure and living environment. For example, the utility cost review unit can propose a utility cost review method based on the user's family structure and living environment. This provides a utility cost review that is tailored to the user's current living situation. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the utility cost review unit are performed using the generation AI. For example, the utility cost review unit inputs current living situation data into the generation AI, and the generation AI customizes the utility cost review.

[0058] The utility cost review unit can select the optimal review method when reviewing utility costs, taking into account the user's geographical location information. For example, the utility cost review unit proposes the optimal review method by considering the utility costs in the user's area. The utility cost review unit can also provide advice on reviewing utility costs by considering the climate and weather in the user's area. For example, the utility cost review unit selects a utility cost review method based on climate data in the user's area. Furthermore, the utility cost review unit can customize the utility cost review method by considering the cost of living and living environment in the user's area. For example, the utility cost review unit proposes a utility cost review method based on price data in the user's area. This makes it possible to review utility costs optimally based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the utility cost review unit are performed using the generation AI. For example, the utility cost review unit inputs geographical location information into the generation AI, and the generation AI selects the optimal review method.

[0059] The utility cost review department can analyze a user's social media activity and provide advice on reviewing utility costs. For example, the utility cost review department can analyze a user's lifestyle and hobbies from their social media activity and propose a utility cost review based on that. The utility cost review department can also provide advice on reviewing utility costs by considering the user's social media interactions. For example, the utility cost review department can adjust the utility cost review method based on the user's social media activity. Furthermore, the utility cost review department can predict future expenditures from the user's social media activity and adjust the utility cost review method based on that. For example, the utility cost review department can use a generative AI to analyze social media data and provide advice on reviewing utility costs. This provides advice on reviewing utility costs based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processing in the utility cost review department is performed using the generative AI. For example, the utility cost review department inputs social media data into the generative AI, and the generative AI provides advice on reviewing utility costs.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The AI-generated concierge service can also include a health management department. This department collects user health data and monitors their health status. For example, it regularly records vital signs such as blood pressure, heart rate, and body temperature, and issues alerts if abnormalities are detected. The health management department can also manage user diet and exercise records and provide advice to support healthy lifestyle habits. For instance, it can analyze user dietary content and propose a nutritionally balanced meal plan. Furthermore, based on user health checkup data, the health management department can predict future health risks and suggest preventative measures. This allows for comprehensive management of the user's health status and supports a healthy lifestyle.

[0062] The AI-generated concierge service can also include a hobby activity support section. This section understands the user's hobbies and interests and suggests appropriate hobby activities based on that understanding. For example, it can introduce events and workshops in areas of interest to the user. It can also introduce communities and groups related to the user's hobbies, promoting social connections. For instance, it can suggest online communities or local clubs that the user can join. Furthermore, it can monitor the user's progress in their hobby activities and provide support to maintain motivation. This allows users to enjoy fulfilling hobby activities.

[0063] The AI-generated concierge service can also include a transportation suggestion function. This function proposes the most suitable mode of transportation based on the user's travel needs. For example, it might offer options such as public transport, taxis, or ride-sharing services, taking into account the user's destination and travel time. It can also suggest barrier-free transportation options, considering the user's health and physical limitations. For instance, it might provide information on wheelchair-accessible taxis and buses. Furthermore, it can analyze regular travel patterns based on the user's travel history and propose efficient routes. This allows for smoother support of the user's travel.

[0064] The AI-generated concierge service can also include an emergency contact support unit. This unit provides functions to ensure users receive prompt assistance in emergencies. For example, when a user presses an emergency button, the unit automatically sends a notification to pre-registered emergency contacts. The unit can also track the user's location in real time to enable a rapid response in emergencies. For example, it can provide the user's location information to emergency services. Furthermore, the unit can pre-register the user's health status and medical history, providing this information quickly to medical institutions in emergencies. This ensures users receive prompt and appropriate assistance in emergencies.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The Pension Management Department collects pension information. This information includes public pensions, corporate pensions, and private pensions. The Pension Management Department can obtain pension information from online systems and can also enter it manually. Furthermore, the Pension Management Department regularly updates the pension information to maintain up-to-date data. Step 2: The Long-Term Care Cost Planning Department predicts future long-term care costs based on information collected by the Pension Management Department. The Long-Term Care Cost Planning Department can also predict long-term care costs using historical data and statistical models, and may take into account the user's health status and living situation. For example, it may predict long-term care costs based on health checkup data. Step 3: The Part-Time Job Placement Department introduces part-time jobs based on the information predicted by the Care Cost Planning Department. The Part-Time Job Placement Department introduces part-time jobs such as short-term jobs and remote work, and recommends suitable jobs by evaluating the user's skills and available time. For example, part-time jobs are recommended based on work history and qualifications. Step 4: The Housing Introduction Department proposes housing options based on the information provided by the Part-Time Job Introduction Department. The Housing Introduction Department proposes various types of housing, such as rentals, shared housing, and nursing homes, tailoring the proposals to the user's needs. For example, they may propose housing options considering the user's health condition and lifestyle. Step 5: The Utility Cost Review Department reviews utility costs based on the information provided by the Housing Introduction Department. The Utility Cost Review Department reviews fixed costs such as electricity, gas, and water bills and proposes ways to save money. For example, they may suggest using energy-efficient appliances or changing contract plans.

[0067] (Example of form 2) The generative AI concierge service according to an embodiment of the present invention is a system designed to alleviate and protect elderly people from financial and lifestyle anxieties. This generative AI concierge service is also designed to allow isolated and lonely elderly people to enjoy communication. Specifically, it provides the following functions: First, as pension management, the generative AI manages pensions and other income and suggests the optimal way to use them. Next, as long-term care cost planning, the generative AI predicts future long-term care costs and supports appropriate preparation. Furthermore, as part-time job introductions, the generative AI evaluates the skills and available time of individual elderly people and suggests ways to effectively utilize their spare time. As housing introductions, the generative AI suggests housing that meets the needs of elderly people. Finally, as a review of utility costs, the generative AI reviews fixed costs such as utilities and suggests ways to save money. This service aims to solve the problem that elderly people tend to be unfamiliar with the latest trends and technologies, and to protect them in a comprehensive way. The generative AI agent supports the lives of elderly people and provides an environment in which they can live with peace of mind. In this way, the generative AI concierge service can alleviate financial and lifestyle anxieties of elderly people and provide an environment in which they can live with peace of mind.

[0068] The AI-generated concierge service according to this embodiment comprises a pension management unit, a long-term care cost planning unit, a part-time job referral unit, a housing referral unit, and a utility cost review unit. The pension management unit collects pension information. Pension information includes, but is not limited to, public pensions, corporate pensions, and private pensions. The pension management unit obtains pension information from online systems, for example. The pension management unit can also manually input pension information. Furthermore, the pension management unit can periodically update pension information. For example, the pension management unit updates pension information monthly to maintain the latest information. The long-term care cost planning unit predicts future long-term care costs based on the information collected by the pension management unit. The long-term care cost planning unit predicts long-term care costs using, for example, historical data and statistical models. The long-term care cost planning unit can also predict long-term care costs considering the user's health status and living situation. For example, the long-term care cost planning unit predicts long-term care costs based on the user's health checkup data. The part-time job referral unit introduces part-time jobs based on the information predicted by the long-term care cost planning unit. The Part-Time Job Introduction Department introduces part-time jobs such as short-term part-time work and remote work. It can also introduce part-time jobs based on the user's skills and available time. For example, it might introduce part-time jobs based on the user's work history and qualifications. The Housing Introduction Department proposes housing based on the information introduced by the Part-Time Job Introduction Department. This department proposes housing options such as rental properties, shared housing, and nursing homes. It can also propose housing tailored to the user's needs, such as considering the user's health and lifestyle. The Utility Cost Review Department reviews utility costs based on the information proposed by the Housing Introduction Department. This department reviews fixed costs such as electricity, gas, and water bills. It can also propose ways to save money, such as suggesting the use of energy-efficient appliances or changing contract plans. As a result, the generated AI concierge service according to this embodiment can alleviate the financial and lifestyle anxieties of the elderly and provide an environment where they can live with peace of mind.

[0069] The Pension Management Department collects pension information. This information includes, but is not limited to, public pensions, corporate pensions, and private pensions. The Pension Management Department obtains pension information from online systems, for example. Specifically, it accesses government pension management systems and corporate pension portal sites and automatically retrieves the necessary data via APIs. The Pension Management Department can also manually enter pension information. For example, if a user provides pension information on paper documents, it provides an interface for manually entering that information into the database. Furthermore, the Pension Management Department can periodically update pension information. For example, it updates pension information monthly to maintain the latest information. This includes mechanisms for collecting the latest pension information through regular API calls and reminder notifications to users. The Pension Management Department also implements security measures to securely store the collected data and share it with other departments as needed. For example, the data is encrypted and access permissions are strictly controlled. This allows the Pension Management Department to efficiently and securely manage users' pension information and enable other departments to quickly access the information they need.

[0070] The Long-Term Care Cost Planning Department predicts future long-term care costs based on information collected by the Pension Management Department. For example, the Department uses historical data and statistical models to predict costs. Specifically, it analyzes past long-term care cost data and uses statistical regression models and machine learning algorithms to predict future costs. The Department can also predict long-term care costs considering the user's health status and living situation. For example, it predicts costs based on the user's health checkup data. This data includes health indicators such as blood pressure, blood sugar levels, and cholesterol levels, and is used to assess future long-term care risks. Furthermore, the Department also considers information such as the user's lifestyle, family structure, and living environment. For example, the necessary long-term care services and costs differ between elderly individuals living alone and those living with family, so the Department develops individually optimized long-term care cost plans considering these factors. The Department comprehensively analyzes this information to provide users with specific long-term care cost estimates and predictions of future cost fluctuations. This makes it easier for users to prepare for future long-term care costs and reduces financial anxiety.

[0071] The Part-Time Job Introduction Department introduces part-time jobs based on information predicted by the Care Cost Planning Department. For example, it introduces part-time jobs such as short-term work and remote work. Specifically, the Part-Time Job Introduction Department collects job information from online job platforms and companies, providing job information that matches the user's needs. The Part-Time Job Introduction Department can also introduce part-time jobs by evaluating the user's skills and available time. For example, it introduces part-time jobs based on the user's work history and qualifications. It registers the user's skills and experience in a database and uses an algorithm to match them with the most suitable job. Furthermore, the Part-Time Job Introduction Department considers the user's lifestyle and health condition to suggest part-time jobs that can be done within a reasonable range. For example, it suggests flexible working styles that suit the user's situation, such as part-time jobs that only require a few hours a week or remote work that can be done from home. The Part-Time Job Introduction Department comprehensively analyzes this information and provides users with specific job information and support for application procedures. This makes it easier for users to secure a source of income to supplement part of their care costs, thus achieving financial stability.

[0072] The Housing Introduction Department proposes housing based on information introduced by the Part-Time Job Introduction Department. The Housing Introduction Department proposes various types of housing, such as rentals, shared houses, and nursing homes. Specifically, it collects information from real estate databases and nursing home databases to propose housing that meets the user's needs. Furthermore, the Housing Introduction Department can also propose housing tailored to the user's needs. For example, it considers the user's health condition and lifestyle when proposing housing. It selects the optimal housing considering the level of care services the user requires and the convenience of daily life. In addition, the Housing Introduction Department provides multiple options considering the user's budget, desired area, and living environment. For example, it proposes a variety of housing options to suit the user's preferences, such as rental apartments in urban areas, shared houses in the suburbs, and facilities with comprehensive care services. The Housing Introduction Department comprehensively analyzes this information and provides users with specific housing proposals, arrangements for viewings, and support for contract procedures. This makes it easier for users to find the ideal housing and live with peace of mind.

[0073] The Utility Cost Review Department reviews utility costs based on information proposed by the Housing Introduction Department. The Utility Cost Review Department reviews fixed costs such as electricity, gas, and water bills. Specifically, it analyzes the user's current utility spending and assesses whether there is room for savings. The Utility Cost Review Department can also propose savings methods. For example, it suggests using energy-efficient appliances or changing contract plans. It evaluates the energy efficiency of the electrical appliances the user is using and recommends replacing them with more efficient ones. It also compares contract plans from electricity and gas companies and proposes switching to cheaper plans. Furthermore, the Utility Cost Review Department provides savings advice tailored to the user's lifestyle. For example, it suggests specific savings methods such as reviewing electricity usage times to avoid peak rates or installing water-saving showerheads. The Utility Cost Review Department comprehensively analyzes this information and provides users with specific savings plans and implementation procedures. This allows users to effectively reduce utility costs and alleviate their financial burden.

[0074] The pension management department can use generative AI to manage pensions and other income and suggest optimal ways to use them. For example, the pension management department can use generative AI to analyze pension information and suggest optimal usage. The pension management department can also use generative AI to predict income fluctuations and provide future income forecasts. For example, the pension management department can use generative AI to predict future income based on past income data. Furthermore, the pension management department can use generative AI to provide investment and savings advice. For example, the pension management department can use generative AI to suggest optimal investment destinations and savings methods. This enables optimal management of pensions and income. Generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the pension management department are performed using generative AI. For example, the pension management department inputs pension information into the generative AI, and the generative AI suggests optimal usage.

[0075] The Care Cost Planning Department can use generative AI to predict future care costs and support appropriate preparation. For example, the Care Cost Planning Department can use generative AI to predict care costs using historical data and statistical models. The Care Cost Planning Department can also use generative AI to predict care costs while considering the user's health status and living situation. For example, the Care Cost Planning Department can use generative AI to predict care costs based on health checkup data. Furthermore, the Care Cost Planning Department can use generative AI to provide advice on insurance enrollment and savings plans. For example, the Care Cost Planning Department can use generative AI to propose the optimal insurance plan and savings method. This makes it possible to predict and prepare for future care costs. Generative AI is implemented using, for example, machine learning models and deep learning. Some or all of the above processes in the Care Cost Planning Department are performed using generative AI. For example, the Care Cost Planning Department inputs care cost predictions into the generative AI, and the generative AI supports appropriate preparation.

[0076] The Part-Time Job Introduction Service uses generative AI to evaluate the skills and available time of individual seniors and propose ways to effectively utilize their spare time. For example, the generative AI can analyze a user's work history and qualifications to propose the most suitable part-time jobs. The part-time job introduction service can also evaluate a user's available time and propose appropriate jobs. For example, the generative AI can propose jobs based on the user's schedule. Furthermore, the generative AI can also provide remote work and short-term job options. For example, the generative AI can suggest remote work job postings. This allows seniors to effectively utilize their skills and time. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the part-time job introduction service are performed using the generative AI. For example, the part-time job introduction service inputs the user's skill information into the generative AI, which then proposes the most suitable jobs.

[0077] The housing referral service can use generative AI to propose housing options tailored to the needs of the elderly. For example, the generative AI can analyze a user's health condition and lifestyle to propose the most suitable housing. The housing referral service can also use generative AI to assess a user's financial situation and propose appropriate housing. For example, the generative AI can propose housing based on the user's income and expenses. Furthermore, the generative AI can provide options such as nursing homes and shared housing. For example, the generative AI can suggest information on nursing homes. This makes it possible to propose housing that meets the needs of the elderly. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the housing referral service are performed using generative AI. For example, the housing referral service inputs user needs information into the generative AI, which then proposes the most suitable housing.

[0078] The utility cost review department can use generating AI to review fixed costs such as utility bills and propose ways to save money. For example, the generating AI in the utility cost review department can analyze fixed costs such as electricity, gas, and water bills and propose the optimal way to save money. The utility cost review department can also have the generating AI suggest the use of energy-efficient equipment or changes to contract plans. For example, the generating AI in the utility cost review department can suggest energy-efficient home appliances. Furthermore, the generating AI in the utility cost review department can evaluate the user's lifestyle and propose appropriate ways to save money. For example, the generating AI in the utility cost review department can propose saving methods based on the user's usage patterns. This makes it possible to review and save on fixed costs such as utility bills. The generating AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processing in the utility cost review department is performed using the generating AI. For example, the utility cost review department inputs fixed cost information into the generating AI, and the generating AI proposes the optimal way to save money.

[0079] The pension management department can estimate the user's emotions and adjust pension management advice based on the estimated emotions. For example, if the user is feeling anxious, the pension management department's generating AI can provide reassuring advice. If the user is relaxed, the pension management department can also have the generating AI provide detailed pension management options. For example, the pension management department can have the generating AI adjust the advice based on the user's emotional state. Furthermore, if the user is in a hurry, the pension management department can have the generating AI provide concise and quick advice. For example, the pension management department can have the generating AI adjust the advice based on the user's emotion score. This ensures that pension management advice is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. Examples of generating AI include, but are not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the pension management department are performed using the generating AI. For example, the pension management department inputs user emotion data into the generating AI, which then adjusts the advice based on the emotions.

[0080] The pension management department can select the optimal management method by referring to the user's past income history when managing pensions. For example, the pension management department can analyze the user's past income history and propose the most efficient pension management method. The pension management department can also provide a stable pension management method by considering fluctuations in the user's income. For example, the pension management department can predict future income based on the user's past income data and adjust the pension management method accordingly. Furthermore, the pension management department can provide a forecast of future income based on the user's past income history. For example, the pension management department can use a generative AI to predict future income based on past income data. This enables optimal pension management based on past income history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the pension management department are performed using the generative AI. For example, the pension management department inputs past income data into the generative AI, and the generative AI selects the optimal management method.

[0081] The pension management department can customize how users use their pensions based on their current living situation. For example, the pension management department can propose the optimal way to use the pension, taking into account the user's current living expenses. It can also propose a pension usage plan that includes medical and long-term care expenses, taking into account the user's health condition. For example, the pension management department can customize the pension usage plan based on the user's health checkup data. Furthermore, the pension management department can also customize the pension usage plan by considering the user's family structure and living environment. For example, the pension management department can propose a pension usage plan based on the user's family structure and living environment. This ensures that the pension usage plan is tailored to the user's current living situation. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the pension management department are performed using the generation AI. For example, the pension management department inputs current living situation data into the generation AI, which then customizes the pension usage plan.

[0082] The pension management department can estimate the user's emotions and determine pension management priorities based on those emotions. For example, if the user is feeling anxious, the generating AI will prioritize and advise on the most important pension management items. If the user is relaxed, the generating AI can also provide a detailed pension management plan. For example, the pension management department will have the generating AI determine priorities according to the user's emotional state. Furthermore, if the user is in a hurry, the generating AI can provide concise and quick pension management advice. For example, the pension management department will have the generating AI determine priorities based on the user's emotion score. This ensures that pension management priorities are determined according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. Generating AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the pension management department are performed using the generating AI. For example, the pension management department inputs user emotion data into the generating AI, which then determines priorities based on the emotions.

[0083] The pension management department can select the optimal pension management method when managing pensions, taking into account the user's geographical location information. For example, the pension management department can propose the optimal pension management method by considering the cost of living in the user's area. Furthermore, the pension management department can adjust how pensions are used by considering the availability of medical and nursing care facilities in the user's area. For example, the pension management department can select a pension management method based on information about medical facilities in the user's area. In addition, the pension management department can customize the pension management method by considering the cost of living and living environment in the user's area. For example, the pension management department can propose a pension management method based on price data in the user's area. This enables optimal pension management based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the pension management department are performed using the generation AI. For example, the pension management department inputs geographical location information into the generation AI, which then selects the optimal pension management method.

[0084] The pension management department can analyze users' social media activity during pension management to provide pension management advice. For example, the pension management department can analyze users' lifestyles and hobbies from their social media activity and propose how to use their pensions based on that analysis. The pension management department can also provide pension management advice considering users' social media interactions. For example, the pension management department can adjust pension management methods based on users' social media activity. Furthermore, the pension management department can predict future expenditures from users' social media activity and adjust pension management methods based on those predictions. For example, the pension management department can use a generative AI to analyze social media data and provide pension management advice. This provides pension management advice based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the pension management department are performed using the generative AI. For example, the pension management department inputs social media data into the generative AI, and the generative AI provides pension management advice.

[0085] The care cost planning unit can estimate the user's emotions and adjust the care cost planning advice based on the estimated emotions. For example, if the user is feeling anxious, the generating AI can provide reassuring care cost planning advice. If the user is relaxed, the generating AI can also provide detailed care cost planning options. For example, the generating AI adjusts the advice according to the user's emotional state. Furthermore, if the user is in a hurry, the generating AI can provide concise and quick care cost planning advice. For example, the generating AI adjusts the advice based on the user's emotion score. This ensures that care cost planning advice is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the care cost planning unit are performed using the generating AI. For example, the care cost planning department inputs user emotional data into a generating AI, which then adjusts the advice based on those emotions.

[0086] The care cost planning unit can select the optimal planning method by referring to the user's past medical history when planning care costs. For example, the care cost planning unit can analyze the user's past medical history and propose the most efficient care cost planning method. The care cost planning unit can also provide a stable care cost planning method by considering fluctuations in the user's medical history. For example, the care cost planning unit can predict future medical expenses based on the user's past medical data and adjust the care cost planning method accordingly. Furthermore, the care cost planning unit can provide a forecast of future medical expenses based on the user's past medical history. For example, the care cost planning unit can use a generative AI to predict future medical expenses based on past medical data. This enables optimal care cost planning based on past medical history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the care cost planning unit are performed using the generative AI. For example, the care cost planning unit inputs past medical data into the generative AI, and the generative AI selects the optimal planning method.

[0087] The care cost planning unit can customize the prediction of care costs based on the user's current health status when planning care costs. For example, the care cost planning unit proposes an optimal care cost plan considering the user's current health status. The care cost planning unit can also provide a stable care cost planning method that takes into account fluctuations in the user's health status. For example, the care cost planning unit predicts future care costs based on the user's health check data and adjusts the care cost planning method accordingly. Furthermore, the care cost planning unit can also provide an outlook on future care costs based on the user's current health status. For example, the care cost planning unit uses a generative AI to predict future care costs based on current health data. This provides a prediction of care costs that is appropriate to the current health status. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the care cost planning unit are performed using the generative AI. For example, the care cost planning unit inputs current health data into the generative AI, and the generative AI customizes the prediction of care costs.

[0088] The care cost planning unit can estimate the user's emotions and determine the priorities of the care cost plan based on the estimated emotions. For example, if the user is feeling anxious, the generating AI will prioritize and advise on the most important care cost plan items. Furthermore, if the user is relaxed, the generating AI can provide a detailed care cost plan. For example, the generating AI will determine priorities according to the user's emotional state. Additionally, if the user is in a hurry, the generating AI can provide concise and quick care cost plan advice. For example, the generating AI will determine priorities based on the user's emotion score. This ensures that the care cost plan is prioritized according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the care cost planning unit are performed using the generating AI. For example, the care cost planning department inputs user emotional data into a generating AI, which then determines priorities based on those emotions.

[0089] The care cost planning unit can select the optimal care cost planning method when planning care costs, taking into account the user's geographical location information. For example, the care cost planning unit proposes the optimal care cost planning method by considering the medical costs in the user's area. The care cost planning unit can also provide advice on care cost planning by considering the situation of care facilities in the user's area. For example, the care cost planning unit selects a care cost planning method based on information about care facilities in the user's area. Furthermore, the care cost planning unit can customize the care cost planning method by considering the cost of living and living environment in the user's area. For example, the care cost planning unit proposes a care cost planning method based on the cost of living data in the user's area. This enables optimal care cost planning based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the care cost planning unit are performed using the generation AI. For example, the care cost planning unit inputs geographical location information into the generation AI, and the generation AI selects the optimal care cost planning method.

[0090] The care cost planning department can analyze a user's social media activity and provide advice on care cost planning. For example, the department can analyze a user's lifestyle and hobbies from their social media activity and propose a care cost plan based on that. The care cost planning department can also provide advice on care cost planning by considering the user's social media interactions. For example, the department can adjust the care cost planning method based on the user's social media activity. Furthermore, the care cost planning department can predict future expenditures from the user's social media activity and adjust the care cost planning method based on that. For example, the care cost planning department can use a generative AI to analyze social media data and provide advice on care cost planning. This provides advice on care cost planning based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the care cost planning department are performed using the generative AI. For example, the care cost planning department inputs social media data into the generative AI, and the generative AI provides advice on care cost planning.

[0091] The Gap Bit Recommendation Unit can estimate the user's emotions and adjust the method of recommending Gap Bits based on the estimated emotions. For example, if the user is feeling anxious, the Generating AI will recommend Gap Bits that provide a sense of reassurance. Also, if the user is relaxed, the Generating AI can provide detailed Gap Bit options. For example, the Generating AI adjusts the recommendation method according to the user's emotional state. Furthermore, if the user is in a hurry, the Generating AI can provide concise and quick Gap Bit recommendations. For example, the Generating AI adjusts the recommendation method based on the user's emotion score. This provides Gap Bit recommendations that are appropriate for the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or Generating AI. Generating AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the Gap Bit Recommendation Unit is performed using Generating AI. For example, the part-time job referral section inputs user emotion data into a generating AI, which then adjusts the referral method based on the emotion.

[0092] The part-time job referral service can select the most suitable part-time job by referring to the user's past work history when referring part-time jobs. For example, the part-time job referral service analyzes the user's past work history and proposes the most suitable part-time job. The part-time job referral service can also provide stable part-time jobs by taking into account fluctuations in the user's work history. For example, the part-time job referral service predicts future occupations based on the user's past work history data and selects part-time jobs based on that. Furthermore, the part-time job referral service can also provide future occupation prospects based on the user's past work history. For example, the part-time job referral service uses a generative AI to predict future occupations based on past work history data. This makes it possible to refer the most suitable part-time job based on past work history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processes in the part-time job referral service are performed using the generative AI. For example, the part-time job referral service inputs past work history data into the generative AI, and the generative AI selects the most suitable part-time job.

[0093] The part-time job referral service can customize job suggestions based on the user's current skills when referring part-time jobs. For example, the part-time job referral service can suggest the most suitable part-time job considering the user's current skills. Furthermore, the part-time job referral service can provide stable part-time jobs by considering fluctuations in the user's skills. For example, the part-time job referral service can predict future skills based on the user's current skill data and select part-time jobs accordingly. In addition, the part-time job referral service can provide an outlook on future skills based on the user's current skills. For example, the part-time job referral service uses a generative AI to predict future skills based on current skill data. This allows for the provision of part-time job suggestions that match the user's current skills. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-described processes in the part-time job referral service are performed using the generative AI. For example, the part-time job referral service inputs current skill data into the generative AI, which then customizes the job suggestions.

[0094] The gap-bite recommendation unit can estimate the user's emotions and prioritize gap-bites based on those emotions. For example, if the user is feeling anxious, the generation AI will prioritize recommending the most important gap-bites. If the user is relaxed, the generation AI can also provide more detailed gap-bite options. For example, the generation AI will prioritize based on the user's emotional state. Furthermore, if the user is in a hurry, the generation AI can provide concise and quick gap-bite recommendations. For example, the generation AI will prioritize based on the user's emotion score. This ensures that gap-bite priorities are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generation AI. The generation AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the gap-bite recommendation unit are performed using generation AI. For example, the part-time job referral service inputs user emotional data into a generating AI, which then determines priorities based on those emotions.

[0095] The part-time job referral service can select the most suitable part-time job by considering the user's geographical location when referring part-time jobs. For example, the part-time job referral service can suggest the most suitable part-time job by considering job information in the user's area. It can also provide part-time jobs that are easy to commute to by considering the transportation situation in the user's area. For example, the part-time job referral service can select part-time jobs based on the transportation data of the user's area. Furthermore, the part-time job referral service can customize part-time jobs by considering the cost of living and living environment in the user's area. For example, the part-time job referral service can suggest part-time jobs based on the cost of living data of the user's area. This makes it possible to refer the most suitable part-time jobs based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the part-time job referral service are performed using the generation AI. For example, the part-time job referral service inputs geographical location information into the generation AI, and the generation AI selects the most suitable part-time job.

[0096] The part-time job referral service can analyze a user's social media activity to suggest part-time jobs. For example, it can analyze a user's interests and preferences from their social media activity and suggest part-time jobs based on that. It can also provide suitable part-time jobs by considering the user's social media interactions. For example, it can select part-time jobs based on the user's social media activity. Furthermore, it can predict future occupations from the user's social media activity and select part-time jobs based on that prediction. For example, the part-time job referral service uses a generative AI to analyze social media data and provide part-time job suggestions. This provides part-time job suggestions based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the part-time job referral service are performed using the generative AI. For example, the part-time job referral service inputs social media data into the generative AI, and the generative AI provides part-time job suggestions.

[0097] The housing recommendation system can estimate the user's emotions and adjust its housing recommendation methods based on those emotions. For example, if the user is feeling anxious, the system's generative AI will suggest housing options that provide a sense of security. If the user is relaxed, the system's generative AI can also provide detailed housing options. For example, the system's generative AI adjusts its recommendation methods according to the user's emotional state. Furthermore, if the user is in a hurry, the system's generative AI can provide concise and quick housing recommendations. For example, the system's generative AI adjusts its recommendation methods based on the user's emotion score. This ensures that housing recommendations are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the housing recommendation system are performed using generative AI. For example, the housing recommendation system inputs user emotion data into the generative AI, which then adjusts its recommendation methods based on the emotions.

[0098] The housing introduction service can select the most suitable housing by referring to the user's past housing history during the housing introduction process. For example, the housing introduction service can analyze the user's past housing history and propose the most suitable housing. The housing introduction service can also provide stable housing by considering fluctuations in the user's housing history. For example, the housing introduction service can predict future housing needs based on the user's past housing data and select housing based on that prediction. Furthermore, the housing introduction service can provide future housing outlooks based on the user's past housing history. For example, the housing introduction service uses a generative AI to predict future housing needs based on past housing data. This makes it possible to propose the most suitable housing based on past housing history. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction service are performed using the generative AI. For example, the housing introduction service inputs past housing data into the generative AI, and the generative AI selects the most suitable housing.

[0099] The housing introduction department can customize housing suggestions based on the user's current living situation. For example, it can suggest the most suitable housing considering the user's current living expenses. It can also suggest housing close to medical or nursing facilities considering the user's health condition. For example, it can customize housing suggestions based on the user's health check data. Furthermore, it can customize housing suggestions considering the user's family structure and living environment. For example, it can suggest housing based on the user's family structure and living environment. This provides housing suggestions that are tailored to the user's current living situation. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction department are performed using the generative AI. For example, the housing introduction department inputs current living situation data into the generative AI, and the generative AI customizes the housing suggestions.

[0100] The housing recommendation system can estimate the user's emotions and prioritize housing options based on those emotions. For example, if the user is feeling anxious, the system's generative AI will prioritize and suggest the most important housing features. If the user is relaxed, the system's generative AI can also provide detailed housing options. For example, the system's generative AI will prioritize options according to the user's emotional state. Furthermore, if the user is in a hurry, the system's generative AI can provide concise and quick housing suggestions. For example, the system's generative AI will prioritize options based on the user's emotion score. This ensures that housing priorities are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the housing recommendation system are performed using generative AI. For example, the housing recommendation system inputs user emotion data into the generative AI, which then determines priorities based on those emotions.

[0101] The housing introduction department can select the most suitable housing by considering the user's geographical location information when introducing housing. For example, the housing introduction department can propose the most suitable housing by considering the cost of living in the user's area. It can also propose housing by considering the status of medical and nursing care facilities in the user's area. For example, the housing introduction department can select housing based on information about medical facilities in the user's area. Furthermore, the housing introduction department can customize housing proposals by considering the cost of living and living environment in the user's area. For example, the housing introduction department can propose housing based on the cost of living data in the user's area. This makes it possible to propose the most suitable housing based on geographical location information. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction department are performed using the generative AI. For example, the housing introduction department inputs geographical location information into the generative AI, and the generative AI selects the most suitable housing.

[0102] The housing introduction department can analyze a user's social media activity to provide housing suggestions when introducing housing options. For example, the housing introduction department can analyze a user's lifestyle and hobbies from their social media activity and propose housing options based on that. The housing introduction department can also provide suitable housing options by considering the user's social media interactions. For example, the housing introduction department can select housing options based on the user's social media activity. Furthermore, the housing introduction department can predict future housing needs based on the user's social media activity and select housing options based on that prediction. For example, the housing introduction department uses generative AI to analyze social media data and provide housing suggestions. This provides housing suggestions based on social media activity. Generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the housing introduction department are performed using generative AI. For example, the housing introduction department inputs social media data into the generative AI, and the generative AI provides housing suggestions.

[0103] The utility cost review unit can estimate the user's emotions and adjust utility cost review advice based on the estimated emotions. For example, if the user is feeling anxious, the generating AI can provide reassuring utility cost review advice. Furthermore, if the user is relaxed, the generating AI can provide detailed utility cost review options. For example, the generating AI can adjust the advice according to the user's emotional state. Additionally, if the user is in a hurry, the generating AI can provide concise and quick utility cost review advice. For example, the generating AI can adjust the advice based on the user's emotion score. This ensures that utility cost review advice is tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the utility cost review unit are performed using the generating AI. For example, the utility cost review department inputs user emotion data into a generating AI, which then adjusts the advice based on those emotions.

[0104] The utility cost review unit can select the optimal review method when reviewing utility costs by referring to the user's past utility cost history. For example, the utility cost review unit can analyze the user's past utility cost history and propose the most efficient utility cost review method. The utility cost review unit can also provide a stable utility cost review method by considering fluctuations in the user's utility costs. For example, the utility cost review unit can predict future utility costs based on the user's past utility cost data and adjust the utility cost review method accordingly. Furthermore, the utility cost review unit can also provide a forecast of future utility costs based on the user's past utility cost history. For example, the utility cost review unit can use a generating AI to predict future utility costs based on past utility cost data. This enables optimal utility cost review based on past utility cost history. The generating AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-described processes in the utility cost review unit are performed using the generating AI. For example, the utility cost review department inputs past utility cost data into a generating AI, which then selects the optimal review method.

[0105] The utility cost review unit can customize the review of utility costs based on the user's current living situation. For example, the utility cost review unit can propose the optimal utility cost review method considering the user's current living expenses. The utility cost review unit can also propose a utility cost review method that includes medical and nursing care costs, taking into account the user's health condition. For example, the utility cost review unit can customize the utility cost review method based on the user's health checkup data. Furthermore, the utility cost review unit can also customize the utility cost review method considering the user's family structure and living environment. For example, the utility cost review unit can propose a utility cost review method based on the user's family structure and living environment. This provides a utility cost review that is tailored to the user's current living situation. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the utility cost review unit are performed using the generation AI. For example, the utility cost review unit inputs current living situation data into the generation AI, and the generation AI customizes the utility cost review.

[0106] The utility cost review unit can estimate the user's emotions and determine the priority of utility cost reviews based on the estimated emotions. For example, if the user is feeling anxious, the generating AI will prioritize and advise on the most important utility cost review items. Also, if the user is relaxed, the generating AI can provide a detailed utility cost review plan. For example, the generating AI will determine priorities according to the user's emotional state. Furthermore, if the user is in a hurry, the generating AI can provide concise and quick utility cost review advice. For example, the generating AI will determine priorities based on the user's emotion score. This determines the priority of utility cost reviews according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the utility cost review unit is performed using a generating AI. For example, the utility cost review department inputs user emotion data into a generating AI, which then determines priorities based on those emotions.

[0107] The utility cost review unit can select the optimal review method when reviewing utility costs, taking into account the user's geographical location information. For example, the utility cost review unit proposes the optimal review method by considering the utility costs in the user's area. The utility cost review unit can also provide advice on reviewing utility costs by considering the climate and weather in the user's area. For example, the utility cost review unit selects a utility cost review method based on climate data in the user's area. Furthermore, the utility cost review unit can customize the utility cost review method by considering the cost of living and living environment in the user's area. For example, the utility cost review unit proposes a utility cost review method based on price data in the user's area. This makes it possible to review utility costs optimally based on geographical location information. The generation AI is implemented using, for example, machine learning models or deep learning. Some or all of the above-mentioned processes in the utility cost review unit are performed using the generation AI. For example, the utility cost review unit inputs geographical location information into the generation AI, and the generation AI selects the optimal review method.

[0108] The utility cost review department can analyze a user's social media activity and provide advice on reviewing utility costs. For example, the utility cost review department can analyze a user's lifestyle and hobbies from their social media activity and propose a utility cost review based on that. The utility cost review department can also provide advice on reviewing utility costs by considering the user's social media interactions. For example, the utility cost review department can adjust the utility cost review method based on the user's social media activity. Furthermore, the utility cost review department can predict future expenditures from the user's social media activity and adjust the utility cost review method based on that. For example, the utility cost review department can use a generative AI to analyze social media data and provide advice on reviewing utility costs. This provides advice on reviewing utility costs based on social media activity. The generative AI is implemented using, for example, machine learning models or deep learning. Some or all of the above processing in the utility cost review department is performed using the generative AI. For example, the utility cost review department inputs social media data into the generative AI, and the generative AI provides advice on reviewing utility costs.

[0109] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0110] The AI-generated concierge service can also include a health management department. This department collects user health data and monitors their health status. For example, it regularly records vital signs such as blood pressure, heart rate, and body temperature, and issues alerts if abnormalities are detected. The health management department can also manage user diet and exercise records and provide advice to support healthy lifestyle habits. For instance, it can analyze user dietary content and propose a nutritionally balanced meal plan. Furthermore, based on user health checkup data, the health management department can predict future health risks and suggest preventative measures. This allows for comprehensive management of the user's health status and supports a healthy lifestyle.

[0111] The AI-generated concierge service can also include a hobby activity support section. This section understands the user's hobbies and interests and suggests appropriate hobby activities based on that understanding. For example, it can introduce events and workshops in areas of interest to the user. It can also introduce communities and groups related to the user's hobbies, promoting social connections. For instance, it can suggest online communities or local clubs that the user can join. Furthermore, it can monitor the user's progress in their hobby activities and provide support to maintain motivation. This allows users to enjoy fulfilling hobby activities.

[0112] The AI-generated concierge service can also include a mental health support section. This section estimates the user's emotions and provides mental health support based on those estimates. For example, if the user is feeling stressed, the mental health support section provides advice on relaxation techniques and stress management. If the user is feeling lonely, the mental health support section can also suggest ways to increase opportunities for communication. For instance, it could offer online chat or video call options that the user can participate in. Furthermore, the mental health support section can regularly monitor the user's emotional state and suggest professional counseling as needed. This allows for comprehensive support of the user's mental health.

[0113] The AI-generated concierge service can also include a transportation suggestion function. This function proposes the most suitable mode of transportation based on the user's travel needs. For example, it might offer options such as public transport, taxis, or ride-sharing services, taking into account the user's destination and travel time. It can also suggest barrier-free transportation options, considering the user's health and physical limitations. For instance, it might provide information on wheelchair-accessible taxis and buses. Furthermore, it can analyze regular travel patterns based on the user's travel history and propose efficient routes. This allows for smoother support of the user's travel.

[0114] The AI-generated concierge service can also include an emergency contact support unit. This unit provides functions to ensure users receive prompt assistance in emergencies. For example, when a user presses an emergency button, the unit automatically sends a notification to pre-registered emergency contacts. The unit can also track the user's location in real time to enable a rapid response in emergencies. For example, it can provide the user's location information to emergency services. Furthermore, the unit can pre-register the user's health status and medical history, providing this information quickly to medical institutions in emergencies. This ensures users receive prompt and appropriate assistance in emergencies.

[0115] The AI-generated concierge service can also include an emotional journal function. This function is a tool for users to record their daily emotions and deepen their self-understanding. For example, the emotional journal allows users to record their emotions and events of the day in text or voice. Furthermore, the emotional journal can analyze the user's emotional data to identify emotional patterns and triggers. For instance, it can analyze what emotions a user is likely to experience in specific situations. Additionally, the emotional journal can provide users with advice on emotional management. For example, it can suggest relaxation methods when a user is feeling stressed. This allows users to deepen their self-understanding and effectively manage their emotions.

[0116] The AI-generated concierge service can also include a reminder function. This function helps users avoid forgetting important appointments and tasks. For example, the reminder function periodically notifies users of appointments and tasks they have set. It can also analyze the user's schedule and send reminders at the optimal time. For instance, it can avoid sending notifications during busy periods. Furthermore, the reminder function can adjust the content and timing of reminders based on the user's emotional state. For example, if the user is feeling stressed, it might suggest activities to help them relax. This allows users to manage their appointments and tasks more efficiently.

[0117] The AI-generated concierge service can also include a learning support function. This function provides support to help users acquire new skills and knowledge. For example, it suggests appropriate learning resources based on the user's interests and goals. It can also monitor the user's learning progress and provide feedback as needed. For instance, it suggests the next steps based on the user's learning progress. Furthermore, it can consider the user's emotional state and provide support to maintain learning motivation. For example, if the user is feeling anxious about learning, it can send encouraging messages. This allows the user to learn effectively.

[0118] The AI-generated concierge service can also include a travel planning support function. This function provides features to assist users with their travel planning. For example, it can suggest optimal travel plans based on the user's preferences and budget. It can also refer to the user's past travel history to suggest destinations and activities that suit their preferences. For instance, it can suggest new travel plans based on places the user has visited and activities they have participated in. Furthermore, it can customize travel suggestions by considering the user's emotional state. For example, if the user is seeking relaxation, it might suggest resort or spa options. This allows users to create a satisfying travel plan.

[0119] The AI-generated concierge service can also include a pet care support section. This section provides functions to support the health and well-being of the user's pet. For example, it collects pet health data and monitors their health status. It can also manage records of the pet's diet and exercise, and provide advice to support healthy lifestyle habits. For instance, it can analyze the pet's diet and suggest a nutritionally balanced meal plan. Furthermore, it can estimate the pet's emotional state and adjust care methods based on the estimated emotions. For example, if the pet is stressed, it can suggest relaxation methods. This allows the user's pet to live a healthy and happy life.

[0120] The following briefly describes the processing flow for example form 2.

[0121] Step 1: The Pension Management Department collects pension information. This information includes public pensions, corporate pensions, and private pensions. The Pension Management Department can obtain pension information from online systems and can also enter it manually. Furthermore, the Pension Management Department regularly updates the pension information to maintain up-to-date data. Step 2: The Long-Term Care Cost Planning Department predicts future long-term care costs based on information collected by the Pension Management Department. The Long-Term Care Cost Planning Department can also predict long-term care costs using historical data and statistical models, and may take into account the user's health status and living situation. For example, it may predict long-term care costs based on health checkup data. Step 3: The Part-Time Job Placement Department introduces part-time jobs based on the information predicted by the Care Cost Planning Department. The Part-Time Job Placement Department introduces part-time jobs such as short-term jobs and remote work, and recommends suitable jobs by evaluating the user's skills and available time. For example, part-time jobs are recommended based on work history and qualifications. Step 4: The Housing Introduction Department proposes housing options based on the information provided by the Part-Time Job Introduction Department. The Housing Introduction Department proposes various types of housing, such as rentals, shared housing, and nursing homes, tailoring the proposals to the user's needs. For example, they may propose housing options considering the user's health condition and lifestyle. Step 5: The Utility Cost Review Department reviews utility costs based on the information provided by the Housing Introduction Department. The Utility Cost Review Department reviews fixed costs such as electricity, gas, and water bills and proposes ways to save money. For example, they may suggest using energy-efficient appliances or changing contract plans.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0124] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0125] Each of the above-mentioned elements, including the pension management department, long-term care cost planning department, part-time job referral department, housing referral department, and utility cost review department, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the pension management department collects pension information by the control unit 46A of the smart device 14 and manages the pension information by the specific processing unit 290 of the data processing device 12. The long-term care cost planning department predicts long-term care costs by the specific processing unit 290 of the data processing device 12 and presents them to the user by the control unit 46A of the smart device 14. The part-time job referral department evaluates the user's skills and available time by the control unit 46A of the smart device 14 and recommends appropriate part-time jobs by the specific processing unit 290 of the data processing device 12. The housing referral department proposes housing by the specific processing unit 290 of the data processing device 12 and presents them to the user by the control unit 46A of the smart device 14. The utility cost review unit, for example, reviews utility costs using the specific processing unit 290 of the data processing device 12, and proposes saving methods using the control unit 46A of the smart device 14. The correspondence between each unit and the devices and control units is not limited to the example described above, and various modifications are possible.

[0126] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0127] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0128] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0130] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0132] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0133] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0134] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0135] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0136] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0140] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] Each of the multiple elements mentioned above, including the pension management department, long-term care cost planning department, part-time job referral department, housing referral department, and utility cost review department, is implemented, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the pension management department collects pension information by the control unit 46A of the smart glasses 214 and manages the pension information by the specific processing unit 290 of the data processing device 12. The long-term care cost planning department predicts long-term care costs by the specific processing unit 290 of the data processing device 12 and presents them to the user by the control unit 46A of the smart glasses 214. The part-time job referral department evaluates the user's skills and available time by the control unit 46A of the smart glasses 214 and recommends appropriate part-time jobs by the specific processing unit 290 of the data processing device 12. The housing referral department proposes housing by the specific processing unit 290 of the data processing device 12 and presents them to the user by the control unit 46A of the smart glasses 214. The utility cost review unit, for example, reviews utility costs using the specific processing unit 290 of the data processing device 12, and proposes saving methods using the control unit 46A of the smart glasses 214. The correspondence between each unit and the devices and control units is not limited to the example described above, and various modifications are possible.

[0142] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0143] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0144] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0145] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0146] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0148] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0149] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0150] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0151] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0152] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0156] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0157] Each of the multiple elements mentioned above, including the pension management department, long-term care cost planning department, part-time job referral department, housing referral department, and utility cost review department, is implemented, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the pension management department collects pension information by the control unit 46A of the headset terminal 314 and manages the pension information by the specific processing unit 290 of the data processing device 12. The long-term care cost planning department predicts long-term care costs by the specific processing unit 290 of the data processing device 12 and presents them to the user by the control unit 46A of the headset terminal 314. The part-time job referral department evaluates the user's skills and available time by the control unit 46A of the headset terminal 314 and recommends appropriate part-time jobs by the specific processing unit 290 of the data processing device 12. The housing referral department proposes housing by the specific processing unit 290 of the data processing device 12 and presents them to the user by the control unit 46A of the headset terminal 314. The utility cost review unit, for example, reviews utility costs using the specific processing unit 290 of the data processing device 12 and proposes saving methods using the control unit 46A of the headset terminal 314. The correspondence between each unit and the devices and control units is not limited to the example described above and can be modified in various ways.

[0158] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0159] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0160] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0162] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0164] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0165] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0166] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0167] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0168] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0169] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0170] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0172] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0173] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0174] Each of the multiple elements mentioned above, including the pension management department, long-term care cost planning department, part-time job referral department, housing referral department, and utility cost review department, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the pension management department collects pension information by the control unit 46A of the robot 414 and manages the pension information by the specific processing unit 290 of the data processing unit 12. The long-term care cost planning department predicts long-term care costs by the specific processing unit 290 of the data processing unit 12 and presents them to the user by the control unit 46A of the robot 414. The part-time job referral department evaluates the user's skills and available time by the control unit 46A of the robot 414 and recommends appropriate part-time jobs by the specific processing unit 290 of the data processing unit 12. The housing referral department proposes housing by the specific processing unit 290 of the data processing unit 12 and presents them to the user by the control unit 46A of the robot 414. The utility cost review unit, for example, reviews utility costs using the specific processing unit 290 of the data processing device 12, and proposes energy-saving methods using the control unit 46A of the robot 414. The correspondence between each unit and the devices and control units is not limited to the example described above, and various modifications are possible.

[0175] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0176] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0177] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0178] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0179] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0180] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0183] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0184] 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.

[0185] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0186] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0187] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0188] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0189] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0190] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0191] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0192] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0193] (Note 1) The pension management department collects pension information, The Long-Term Care Cost Planning Department predicts future long-term care costs based on information collected by the aforementioned Pension Management Department, A part-time job referral department introduces part-time jobs based on information predicted by the aforementioned long-term care cost planning department, Based on the information provided by the aforementioned part-time job referral service, the housing referral service proposes housing options. The system includes a utility cost review unit that reviews utility costs based on information proposed by the aforementioned housing introduction unit. A system characterized by the following features. (Note 2) The aforementioned pension management department, Using AI-generated data, we manage pensions and other income and suggest the optimal way to use them. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned care cost planning department, Using generative AI, we predict future care costs and support appropriate preparation. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned gap bite introduction section is Using generative AI, we evaluate the skills and available time of individual seniors and suggest ways to make effective use of their spare time. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned housing introduction department, We use generative AI to propose housing options tailored to the needs of the elderly. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned utility cost review department, Using AI generation, we review fixed costs such as utility bills and suggest ways to save money. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned pension management department, It estimates the user's emotions and adjusts pension management advice based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned pension management department, When managing pensions, the system selects the optimal management method by referring to the user's past income history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned pension management department, When managing pensions, the system customizes how pensions are used based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned pension management department, It estimates the user's emotions and determines pension management priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned pension management department, When managing pensions, the optimal pension management method is selected by considering the user's geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned pension management department, When managing pensions, we analyze users' social media activity to provide pension management advice. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned care cost planning department, The system estimates the user's emotions and adjusts the advice on care cost planning based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned care cost planning department, When planning long-term care costs, the optimal planning method is selected by referring to the user's past medical history. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned care cost planning department, When planning long-term care costs, customize the forecast based on the user's current health status. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned care cost planning department, The system estimates the user's emotions and prioritizes care cost plans based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned care cost planning department, When planning long-term care costs, the optimal method of planning long-term care costs is selected by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned care cost planning department, When creating a care cost plan, we analyze the user's social media activity to provide advice on the care cost plan. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned gap bite introduction section is The system estimates the user's emotions and adjusts how it introduces part-time jobs based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned gap bite introduction section is When introducing part-time jobs, the system selects the most suitable job by referring to the user's past work history. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned gap bite introduction section is When introducing part-time jobs, the system customizes job suggestions based on the user's current skills. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned gap bite introduction section is The system estimates the user's emotions and prioritizes available slots based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned gap bite introduction section is When introducing part-time jobs, the system selects the most suitable job by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned gap bite introduction section is When introducing part-time jobs, the system analyzes the user's social media activity to provide job suggestions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned housing introduction department, The system estimates the user's emotions and adjusts the housing suggestions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned housing introduction department, When introducing properties, the system selects the most suitable home by referring to the user's past housing history. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned housing introduction department, When introducing housing options, the system customizes housing suggestions based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned housing introduction department, It estimates the user's emotions and determines housing priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned housing introduction department, When introducing properties, the system selects the most suitable property by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned housing introduction department, When introducing properties, we analyze the user's social media activity to provide property recommendations. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned utility cost review department, The system estimates the user's emotions and adjusts the advice on reviewing utility costs based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned utility cost review department, When reviewing utility costs, the system selects the optimal review method by referring to the user's past utility cost history. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned utility cost review department, When reviewing utility costs, customize the review based on the user's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned utility cost review department, The system estimates the user's emotions and determines the priority of reviewing utility costs based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned utility cost review department, When reviewing utility costs, the optimal review method is selected by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned utility cost review department, When reviewing utility costs, we analyze the user's social media activity to provide advice on how to reduce utility expenses. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The pension management department collects pension information, The Long-Term Care Cost Planning Department predicts future long-term care costs based on information collected by the aforementioned Pension Management Department, A part-time job referral department introduces part-time jobs based on information predicted by the aforementioned long-term care cost planning department, Based on the information provided by the aforementioned part-time job referral service, the housing referral service proposes housing options. The system includes a utility cost review unit that reviews utility costs based on information proposed by the aforementioned housing introduction unit. A system characterized by the following features.

2. The aforementioned pension management department, Using AI to generate data, we manage pensions and other income and suggest the optimal way to use it. The system according to feature 1.

3. The aforementioned care cost planning department, Using AI to predict future care costs and support appropriate preparation. The system according to feature 1.

4. The aforementioned gap bite introduction section is Using generative AI, we evaluate the skills and available time of individual seniors and propose ways to make effective use of their spare time. The system according to feature 1.

5. The aforementioned housing introduction department, Using generative AI, we propose housing options tailored to the needs of the elderly. The system according to feature 1.

6. The aforementioned utility cost review department, Using AI generation, we review fixed costs such as utility bills and suggest ways to save money. The system according to feature 1.

7. The aforementioned pension management department, It estimates the user's emotions and adjusts pension management advice based on those estimated emotions. The system according to feature 1.

8. The aforementioned pension management department, When managing pensions, the system selects the optimal management method by referring to the user's past income history. The system according to feature 1.

9. The aforementioned pension management department, When managing pensions, the system customizes how pensions are used based on the user's current living situation. The system according to feature 1.

10. The aforementioned pension management department, It estimates the user's emotions and determines pension management priorities based on those estimated emotions. The system according to feature 1.

Images